Gemini 3.5 Flash-Lite is Google’s execution-focused multimodal text profile for repeated data work and focused subagent tasks. It builds on Gemini 3.1 Flash-Lite, improving document understanding, tool reliability and multi-turn instruction following. It accepts text, images, audio, video and PDF and returns text. A useful result is one extracted record, a classification, a short translation or a bounded tool-assisted analysis within a larger task.
For document parsing, define the fields that matter and the evidence each field must retain. Provide the relevant pages and specify how to represent absent or ambiguous information. For support-message extraction, extract a product code, mentioned issue and supporting sentence from a support message, keeping the message identifier in the answer. A document with multiple candidates for a field should not silently collapse them into one guessed value. Structured JSON can make the result usable for later processing when its schema matches the actual task.
The documented thinking levels are minimal, low, medium and high, with minimal as the default. The maker recommends it for high-volume extraction, routing and classification, while medium or high is appropriate for autonomous subagent work involving tool calls, code execution or several reasoning steps. The guide specifically advises increasing effort for those longer tasks to avoid premature tool termination. A one-field extraction and a document comparison with exceptions therefore benefit from different effort choices. Minimal is a supported setting of this edition rather than a general setting to transfer to every Flash model.
A focused subagent brief should contain one job, its source material, permitted tools and the required final form. For example, it can examine a table for a stated rule and return the affected rows with the relevant values. The maker also highlights tabular-data processing and frontend JavaScript work assisted by lightweight code execution. The surrounding application remains responsible for running a requested function and returning the real result. Keep a finished result distinguishable from an unexecuted suggestion or an unresolved input question.
The exact 3.5 Flash-Lite page lists function calling, code execution, file search, search grounding, Maps grounding and URL context, with Computer Use marked as preview. Structured output and thinking are supported. For a multi-turn persona or task, retain the actual instructions and tool observations so later replies follow the same assignment. The developer guide highlights stronger persona persistence than 3.1 Flash-Lite. Use a concise role and output contract rather than redefining the objective at every follow-up.
The guide also deprecates legacy sampling settings and prefilled final model turns for this edition. Control a bounded answer with explicit instructions or a schema rather than trying to start the answer inside a synthetic model-role turn. Preserve the Gemini 3 thought-signature context where the interface requires it, and match function results to their calls. These preparation rules support a continuation that still has the evidence needed to complete the same job.
The native card lists up to 1M context and 64K text output; the exact API page specifies 1,048,576 input tokens and 65,536 output tokens. Instructions, records, history and media all contribute to input preparation. Caching, batch, Flex and Priority options are listed for the producer profile. For repeated requests, use stable identifiers and a compact consistent answer format so each extraction can be compared with its source. Audio, image or video input produces a text interpretation or transcript in this profile, rather than generated speech or artwork.
Possible limitations include hallucinations and occasional delays or timeouts. Its knowledge cutoff is March 2026, with some domains limited to January 2025. Source-dependent extraction should return what the supplied material supports; current-fact questions need current evidence. Compared with 3.1 Flash-Lite, this profile adds the documented execution and computer-use capabilities, while 3.6 Flash emphasizes more complex coding and spatial work. Review extracted fields, tool results and retained instructions before incorporating the answer into a larger workflow.
", "aboutText": "Gemini 3.5 Flash-Lite is Google’s execution-focused multimodal text profile for repeated data work and focused subagent tasks. It builds on Gemini 3.1 Flash-Lite, improving document understanding, tool reliability and multi-turn instruction following. It accepts text, images, audio, video and PDF and returns text. A useful result is one extracted record, a classification, a short translation or a bounded tool-assisted analysis within a larger task.\n\nFor document parsing, define the fields that matter and the evidence each field must retain. Provide the relevant pages and specify how to represent absent or ambiguous information. For support-message extraction, extract a product code, mentioned issue and supporting sentence from a support message, keeping the message identifier in the answer. A document with multiple candidates for a field should not silently collapse them into one guessed value. Structured JSON can make the result usable for later processing when its schema matches the actual task.\n\nThe documented thinking levels are minimal, low, medium and high, with minimal as the default. The maker recommends it for high-volume extraction, routing and classification, while medium or high is appropriate for autonomous subagent work involving tool calls, code execution or several reasoning steps. The guide specifically advises increasing effort for those longer tasks to avoid premature tool termination. A one-field extraction and a document comparison with exceptions therefore benefit from different effort choices. Minimal is a supported setting of this edition rather than a general setting to transfer to every Flash model.\n\nA focused subagent brief should contain one job, its source material, permitted tools and the required final form. For example, it can examine a table for a stated rule and return the affected rows with the relevant values. The maker also highlights tabular-data processing and frontend JavaScript work assisted by lightweight code execution. The surrounding application remains responsible for running a requested function and returning the real result. Keep a finished result distinguishable from an unexecuted suggestion or an unresolved input question.\n\nThe exact 3.5 Flash-Lite page lists function calling, code execution, file search, search grounding, Maps grounding and URL context, with Computer Use marked as preview. Structured output and thinking are supported. For a multi-turn persona or task, retain the actual instructions and tool observations so later replies follow the same assignment. The developer guide highlights stronger persona persistence than 3.1 Flash-Lite. Use a concise role and output contract rather than redefining the objective at every follow-up.\n\nThe guide also deprecates legacy sampling settings and prefilled final model turns for this edition. Control a bounded answer with explicit instructions or a schema rather than trying to start the answer inside a synthetic model-role turn. Preserve the Gemini 3 thought-signature context where the interface requires it, and match function results to their calls. These preparation rules support a continuation that still has the evidence needed to complete the same job.\n\nThe native card lists up to 1M context and 64K text output; the exact API page specifies 1,048,576 input tokens and 65,536 output tokens. Instructions, records, history and media all contribute to input preparation. Caching, batch, Flex and Priority options are listed for the producer profile. For repeated requests, use stable identifiers and a compact consistent answer format so each extraction can be compared with its source. Audio, image or video input produces a text interpretation or transcript in this profile, rather than generated speech or artwork.\n\nPossible limitations include hallucinations and occasional delays or timeouts. Its knowledge cutoff is March 2026, with some domains limited to January 2025. Source-dependent extraction should return what the supplied material supports; current-fact questions need current evidence. Compared with 3.1 Flash-Lite, this profile adds the documented execution and computer-use capabilities, while 3.6 Flash emphasizes more complex coding and spatial work. Review extracted fields, tool results and retained instructions before incorporating the answer into a larger workflow.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Extract a support message record\n\nExtract fields from message S-91: "The pump P-28 stopped after ten minutes. I bought two, but only one has this issue. Please arrange a replacement." Return message ID, product code, issue, purchased quantity and affected quantity in a small table. Include the exact supporting phrase for each extracted value.A field/value/evidence table retaining S-91 and separating purchased from affected quantity.Check that two purchased pumps do not become two defective pumps.gemini-3.5-flash-liteGemini 3.5 Flash-Lite is Google’s multimodal model for focused subagent tasks, document parsing and repeated data extraction. Its default minimal reasoning suits bounded records; medium or high is documented for multi-step tool work. It returns text or structured results from text, images, audio, video and PDF.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 3.5 Flash-Lite is Google’s execution-focused multimodal text profile for repeated data work and focused subagent tasks. It builds on Gemini 3.1 Flash-Lite, improving document understanding, tool reliability and multi-turn instruction following. It accepts text, images, audio, video and PDF and returns text. A useful result is one extracted record, a classification, a short translation or a bounded tool-assisted analysis within a larger task.
For document parsing, define the fields that matter and the evidence each field must retain. Provide the relevant pages and specify how to represent absent or ambiguous information. For support-message extraction, extract a product code, mentioned issue and supporting sentence from a support message, keeping the message identifier in the answer. A document with multiple candidates for a field should not silently collapse them into one guessed value. Structured JSON can make the result usable for later processing when its schema matches the actual task.
The documented thinking levels are minimal, low, medium and high, with minimal as the default. The maker recommends it for high-volume extraction, routing and classification, while medium or high is appropriate for autonomous subagent work involving tool calls, code execution or several reasoning steps. The guide specifically advises increasing effort for those longer tasks to avoid premature tool termination. A one-field extraction and a document comparison with exceptions therefore benefit from different effort choices. Minimal is a supported setting of this edition rather than a general setting to transfer to every Flash model.
A focused subagent brief should contain one job, its source material, permitted tools and the required final form. For example, it can examine a table for a stated rule and return the affected rows with the relevant values. The maker also highlights tabular-data processing and frontend JavaScript work assisted by lightweight code execution. The surrounding application remains responsible for running a requested function and returning the real result. Keep a finished result distinguishable from an unexecuted suggestion or an unresolved input question.
The exact 3.5 Flash-Lite page lists function calling, code execution, file search, search grounding, Maps grounding and URL context, with Computer Use marked as preview. Structured output and thinking are supported. For a multi-turn persona or task, retain the actual instructions and tool observations so later replies follow the same assignment. The developer guide highlights stronger persona persistence than 3.1 Flash-Lite. Use a concise role and output contract rather than redefining the objective at every follow-up.
The guide also deprecates legacy sampling settings and prefilled final model turns for this edition. Control a bounded answer with explicit instructions or a schema rather than trying to start the answer inside a synthetic model-role turn. Preserve the Gemini 3 thought-signature context where the interface requires it, and match function results to their calls. These preparation rules support a continuation that still has the evidence needed to complete the same job.
The native card lists up to 1M context and 64K text output; the exact API page specifies 1,048,576 input tokens and 65,536 output tokens. Instructions, records, history and media all contribute to input preparation. Caching, batch, Flex and Priority options are listed for the producer profile. For repeated requests, use stable identifiers and a compact consistent answer format so each extraction can be compared with its source. Audio, image or video input produces a text interpretation or transcript in this profile, rather than generated speech or artwork.
Possible limitations include hallucinations and occasional delays or timeouts. Its knowledge cutoff is March 2026, with some domains limited to January 2025. Source-dependent extraction should return what the supplied material supports; current-fact questions need current evidence. Compared with 3.1 Flash-Lite, this profile adds the documented execution and computer-use capabilities, while 3.6 Flash emphasizes more complex coding and spatial work. Review extracted fields, tool results and retained instructions before incorporating the answer into a larger workflow.
POST /v1/messagestext, imagetext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gemini-3.5-flash-lite | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring|content_block[] | RequirementRequired | Values & limits | Default— |
Fieldsystem | Typestring|content_block[] | RequirementOptional | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits Minimum: 1 Limit applies to: exact selected model/card ceiling | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstop_sequences | Typestring[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools | Typetool[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].name | Typestring | RequirementOptional | Values & limits Applies when: tool supplied | Default— |
Fieldtools[].description | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools[].input_schema | TypeJSON_schema | RequirementOptional | Values & limits | Default— |
Fieldtool_choice | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldthinking.type | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldthinking.budget_tokens | Typeinteger | RequirementOptional | Values & limits Model-specific | Default— |
Fieldoutput_config.effort | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmetadata | Typeobject | RequirementOptional | Values & limits | Default— |
Fieldcache_control | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Text · UTF8 text
messages[].content or type=text block
Text + image
{type:image,source:{type:base64,media_type,data}} or source type=url
| Parameter | Contract |
|---|---|
Parametermaterial_types | Contracttext, image |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractnull |
Parametercontent_type | Contractapplication/json |
Parametertext_file_material | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |
Lifecycle: exact retained published method
Method shapes and IDs are exact; supplier capability is separate from admission.
POST /v1/messagesAiloot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "gemini-3.5-flash-lite", "max_tokens": 1024, "messages": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\\n\\n"+text}]\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "gemini-3.5-flash-lite", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="image/png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "image/jpeg" if raw.startswith(b"\\xff\\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nimport anthropic\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nmsg = client.messages.create(\n model="gemini-3.5-flash-lite",\n max_tokens=1024,\n messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(msg.to_dict(mode="json"))\nimport Anthropic from "@anthropic-ai/sdk";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n model: "gemini-3.5-flash-lite",\n max_tokens: 1024,\n messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],\n});\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(msg);\nimport anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.messages.stream(model='gemini-3.5-flash-lite',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_message()\n save_result(final.to_dict(mode="json"),"stream-result")\njson or SSE
Keep every complete returned response, file and content part.
Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldmodel | Typestring |
Fieldcontent[] | Typetext|thinking|tool_use|other content block |
Fieldstop_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot gemini-3.5-flash-lite, gemini-flash-lite, gemini-flash-lite-latest
Ailoot Ultra gemini-3.5-flash-lite, google/gemini-3.5-flash-lite
/chat/completions
google/gemini-3.5-flash-lite, gemini-flash-lite, gemini-flash-lite-latest, gemini-3.5-flash-lite, gemini-3.5-flash-lite
gemini-3.5-flash-liteGemini 3.5 Flash-Lite is Google’s multimodal model for focused subagent tasks, document parsing and repeated data extraction. Its default minimal reasoning suits bounded records; medium or high is documented for multi-step tool work. It returns text or structured results from text, images, audio, video and PDF.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 3.5 Flash-Lite is Google’s execution-focused multimodal text profile for repeated data work and focused subagent tasks. It builds on Gemini 3.1 Flash-Lite, improving document understanding, tool reliability and multi-turn instruction following. It accepts text, images, audio, video and PDF and returns text. A useful result is one extracted record, a classification, a short translation or a bounded tool-assisted analysis within a larger task.
For document parsing, define the fields that matter and the evidence each field must retain. Provide the relevant pages and specify how to represent absent or ambiguous information. For support-message extraction, extract a product code, mentioned issue and supporting sentence from a support message, keeping the message identifier in the answer. A document with multiple candidates for a field should not silently collapse them into one guessed value. Structured JSON can make the result usable for later processing when its schema matches the actual task.
The documented thinking levels are minimal, low, medium and high, with minimal as the default. The maker recommends it for high-volume extraction, routing and classification, while medium or high is appropriate for autonomous subagent work involving tool calls, code execution or several reasoning steps. The guide specifically advises increasing effort for those longer tasks to avoid premature tool termination. A one-field extraction and a document comparison with exceptions therefore benefit from different effort choices. Minimal is a supported setting of this edition rather than a general setting to transfer to every Flash model.
A focused subagent brief should contain one job, its source material, permitted tools and the required final form. For example, it can examine a table for a stated rule and return the affected rows with the relevant values. The maker also highlights tabular-data processing and frontend JavaScript work assisted by lightweight code execution. The surrounding application remains responsible for running a requested function and returning the real result. Keep a finished result distinguishable from an unexecuted suggestion or an unresolved input question.
The exact 3.5 Flash-Lite page lists function calling, code execution, file search, search grounding, Maps grounding and URL context, with Computer Use marked as preview. Structured output and thinking are supported. For a multi-turn persona or task, retain the actual instructions and tool observations so later replies follow the same assignment. The developer guide highlights stronger persona persistence than 3.1 Flash-Lite. Use a concise role and output contract rather than redefining the objective at every follow-up.
The guide also deprecates legacy sampling settings and prefilled final model turns for this edition. Control a bounded answer with explicit instructions or a schema rather than trying to start the answer inside a synthetic model-role turn. Preserve the Gemini 3 thought-signature context where the interface requires it, and match function results to their calls. These preparation rules support a continuation that still has the evidence needed to complete the same job.
The native card lists up to 1M context and 64K text output; the exact API page specifies 1,048,576 input tokens and 65,536 output tokens. Instructions, records, history and media all contribute to input preparation. Caching, batch, Flex and Priority options are listed for the producer profile. For repeated requests, use stable identifiers and a compact consistent answer format so each extraction can be compared with its source. Audio, image or video input produces a text interpretation or transcript in this profile, rather than generated speech or artwork.
Possible limitations include hallucinations and occasional delays or timeouts. Its knowledge cutoff is March 2026, with some domains limited to January 2025. Source-dependent extraction should return what the supplied material supports; current-fact questions need current evidence. Compared with 3.1 Flash-Lite, this profile adds the documented execution and computer-use capabilities, while 3.6 Flash emphasizes more complex coding and spatial work. Review extracted fields, tool results and retained instructions before incorporating the answer into a larger workflow.
POST /v1beta/models/{model}:generateContenttext, imagetext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldpath.model | Typestring | RequirementRequired | Values & limits gemini-3.5-flash-lite | Default— |
Fieldcontents | Typecontent[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldcontents[].role | Typestring | RequirementOptional | Values & limits user, model | Default— |
Fieldcontents[].parts | Typepart[] | RequirementRequired | Values & limits | Default— |
FieldsystemInstruction | Typecontent | RequirementOptional | Values & limits | Default— |
FieldgenerationConfig.maxOutputTokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
FieldgenerationConfig.temperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
FieldgenerationConfig.topP | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
FieldgenerationConfig.topK | Typeinteger | RequirementOptional | Values & limits Model-specific | Default— |
FieldgenerationConfig.stopSequences | Typestring[] | RequirementOptional | Values & limits Model-specific | Default— |
FieldgenerationConfig.thinkingConfig.includeThoughts | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
FieldgenerationConfig.thinkingConfig.thinkingBudget | Typeinteger | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].functionDeclarations | Typefunction_declaration[] | RequirementOptional | Values & limits Model-specific | Default— |
FieldtoolConfig.functionCallingConfig.mode | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
FieldsafetySettings | Typeobject[] | RequirementOptional | Values & limits Model-specific | Default— |
FieldsessionId | Typestring | RequirementOptional | Values & limits | Default— |
Text · UTF8 text
contents[].parts[].text
Text + image
parts[].inlineData={mimeType,data}
| Parameter | Contract |
|---|---|
Parametermaterial_types | Contracttext, image |
Parameterrequired | Contractcontents |
Parameteroptional_controls | Contractnull |
Parametercontent_type | Contractapplication/json |
Parametertext_file_material | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |
Lifecycle: exact retained published method
Method shapes and IDs are exact; supplier capability is separate from admission.
POST /v1beta/models/{model}:generateContentAiloot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"contents": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["contents"]=[{"role":"user","parts":[{"text":"Summarize this material and quote supporting source passages.\\n\\n"+text}]}]\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1beta/models/gemini-3.5-flash-lite:generateContent \\\n -H "x-goog-api-key: $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(json.loads(Path("result.json").read_text(encoding="utf-8")))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"contents": [{"role": "user", "parts": [{"text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="image/png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "image/jpeg" if raw.startswith(b"\\xff\\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["contents"][0]["parts"].append({"inlineData":{"mimeType":mime,"data":b64}})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1beta/models/gemini-3.5-flash-lite:generateContent \\\n -H "x-goog-api-key: $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(json.loads(Path("result.json").read_text(encoding="utf-8")))\nPY_RESULT\nfrom google import genai\nfrom google.genai import types\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = genai.Client(\n api_key=os.environ["AILOOT_API_KEY"],\n http_options=types.HttpOptions(base_url="https://api.ailoot.ai"),\n)\nresp = client.models.generate_content(model="gemini-3.5-flash-lite", contents="Explain the difference between an observation and a hypothesis in three sentences.")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(resp.to_json_dict())\nimport { GoogleGenAI } from "@google/genai";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst ai = new GoogleGenAI({ apiKey: process.env.AILOOT_API_KEY, httpOptions: { baseUrl: "https://api.ailoot.ai" } });\nconst resp = await ai.models.generateContent({ model: "gemini-3.5-flash-lite", contents: "Explain the difference between an observation and a hypothesis in three sentences." });\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(resp);\nfrom google import genai\nfrom google.genai import types\nimport os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=genai.Client(api_key=os.environ["AILOOT_API_KEY"],http_options=types.HttpOptions(base_url="https://api.ailoot.ai"))\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\ncount=0\nwith Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for chunk in client.models.generate_content_stream(model='gemini-3.5-flash-lite',contents="Explain observations and hypotheses in three sentences."):\n payload=chunk.to_json_dict()\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n save_result(payload,"stream-chunk-"+str(count))\n count+=1\njson or supported streaming
Keep every complete returned response, file and content part.
Keep all candidates and parts, including function calls, thought signatures and usage; assemble stream chunks in order.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
FieldresponseId | Typestring |
FieldmodelVersion | Typestring |
Fieldcandidates[].content.parts[] | Typetext|inlineData|functionCall|other part |
Fieldcandidates[].finishReason | Typestring |
FieldusageMetadata | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot gemini-3.5-flash-lite, gemini-flash-lite, gemini-flash-lite-latest
Ailoot Ultra gemini-3.5-flash-lite, google/gemini-3.5-flash-lite
/chat/completions
google/gemini-3.5-flash-lite, gemini-flash-lite, gemini-flash-lite-latest, gemini-3.5-flash-lite, gemini-3.5-flash-lite
gemini-3.5-flash-liteGemini 3.5 Flash-Lite is Google’s multimodal model for focused subagent tasks, document parsing and repeated data extraction. Its default minimal reasoning suits bounded records; medium or high is documented for multi-step tool work. It returns text or structured results from text, images, audio, video and PDF.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 3.5 Flash-Lite is Google’s execution-focused multimodal text profile for repeated data work and focused subagent tasks. It builds on Gemini 3.1 Flash-Lite, improving document understanding, tool reliability and multi-turn instruction following. It accepts text, images, audio, video and PDF and returns text. A useful result is one extracted record, a classification, a short translation or a bounded tool-assisted analysis within a larger task.
For document parsing, define the fields that matter and the evidence each field must retain. Provide the relevant pages and specify how to represent absent or ambiguous information. For support-message extraction, extract a product code, mentioned issue and supporting sentence from a support message, keeping the message identifier in the answer. A document with multiple candidates for a field should not silently collapse them into one guessed value. Structured JSON can make the result usable for later processing when its schema matches the actual task.
The documented thinking levels are minimal, low, medium and high, with minimal as the default. The maker recommends it for high-volume extraction, routing and classification, while medium or high is appropriate for autonomous subagent work involving tool calls, code execution or several reasoning steps. The guide specifically advises increasing effort for those longer tasks to avoid premature tool termination. A one-field extraction and a document comparison with exceptions therefore benefit from different effort choices. Minimal is a supported setting of this edition rather than a general setting to transfer to every Flash model.
A focused subagent brief should contain one job, its source material, permitted tools and the required final form. For example, it can examine a table for a stated rule and return the affected rows with the relevant values. The maker also highlights tabular-data processing and frontend JavaScript work assisted by lightweight code execution. The surrounding application remains responsible for running a requested function and returning the real result. Keep a finished result distinguishable from an unexecuted suggestion or an unresolved input question.
The exact 3.5 Flash-Lite page lists function calling, code execution, file search, search grounding, Maps grounding and URL context, with Computer Use marked as preview. Structured output and thinking are supported. For a multi-turn persona or task, retain the actual instructions and tool observations so later replies follow the same assignment. The developer guide highlights stronger persona persistence than 3.1 Flash-Lite. Use a concise role and output contract rather than redefining the objective at every follow-up.
The guide also deprecates legacy sampling settings and prefilled final model turns for this edition. Control a bounded answer with explicit instructions or a schema rather than trying to start the answer inside a synthetic model-role turn. Preserve the Gemini 3 thought-signature context where the interface requires it, and match function results to their calls. These preparation rules support a continuation that still has the evidence needed to complete the same job.
The native card lists up to 1M context and 64K text output; the exact API page specifies 1,048,576 input tokens and 65,536 output tokens. Instructions, records, history and media all contribute to input preparation. Caching, batch, Flex and Priority options are listed for the producer profile. For repeated requests, use stable identifiers and a compact consistent answer format so each extraction can be compared with its source. Audio, image or video input produces a text interpretation or transcript in this profile, rather than generated speech or artwork.
Possible limitations include hallucinations and occasional delays or timeouts. Its knowledge cutoff is March 2026, with some domains limited to January 2025. Source-dependent extraction should return what the supplied material supports; current-fact questions need current evidence. Compared with 3.1 Flash-Lite, this profile adds the documented execution and computer-use capabilities, while 3.6 Flash emphasizes more complex coding and spatial work. Review extracted fields, tool results and retained instructions before incorporating the answer into a larger workflow.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gemini-3.5-flash-lite | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Model-specific | Default— |
Fieldmessages[].content | Typestring | RequirementOptional | Values & limits Applies when: Text conversation | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream |
Parametercontrol_scope | ContractText conversation; stream is a boolean and defaults to false. |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Method aliases: /chat/completions
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model":"gemini-3.5-flash-lite","messages":[{"role":"user","content":"hello"}],"stream":false}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("choices",[]):\n if x.get("message",{}).get("content"): print(x["message"]["content"])\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.chat.completions.create(model="gemini-3.5-flash-lite", messages=[{"role":"user","content":"hello"}], stream=False)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(result.to_dict(mode="json"))\njson or SSE
Keep every complete returned response, file and content part.
Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldchoices[].index | Typeinteger |
Fieldchoices[].message.content | Typestring|null |
Fieldchoices[].message.tool_calls | Typetool_call[] |
Fieldchoices[].message.reasoning_content | Typestring |
Fieldchoices[].message.reasoning_details | Typeobject|array |
Fieldchoices[].finish_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot gemini-3.5-flash-lite, gemini-flash-lite, gemini-flash-lite-latest
Ailoot Ultra gemini-3.5-flash-lite, google/gemini-3.5-flash-lite
/chat/completions
google/gemini-3.5-flash-lite, gemini-flash-lite, gemini-flash-lite-latest, gemini-3.5-flash-lite, gemini-3.5-flash-lite
gemini-3.5-flash-liteGemini 3.5 Flash-Lite is Google’s multimodal model for focused subagent tasks, document parsing and repeated data extraction. Its default minimal reasoning suits bounded records; medium or high is documented for multi-step tool work. It returns text or structured results from text, images, audio, video and PDF.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 3.5 Flash-Lite is Google’s execution-focused multimodal text profile for repeated data work and focused subagent tasks. It builds on Gemini 3.1 Flash-Lite, improving document understanding, tool reliability and multi-turn instruction following. It accepts text, images, audio, video and PDF and returns text. A useful result is one extracted record, a classification, a short translation or a bounded tool-assisted analysis within a larger task.
For document parsing, define the fields that matter and the evidence each field must retain. Provide the relevant pages and specify how to represent absent or ambiguous information. For support-message extraction, extract a product code, mentioned issue and supporting sentence from a support message, keeping the message identifier in the answer. A document with multiple candidates for a field should not silently collapse them into one guessed value. Structured JSON can make the result usable for later processing when its schema matches the actual task.
The documented thinking levels are minimal, low, medium and high, with minimal as the default. The maker recommends it for high-volume extraction, routing and classification, while medium or high is appropriate for autonomous subagent work involving tool calls, code execution or several reasoning steps. The guide specifically advises increasing effort for those longer tasks to avoid premature tool termination. A one-field extraction and a document comparison with exceptions therefore benefit from different effort choices. Minimal is a supported setting of this edition rather than a general setting to transfer to every Flash model.
A focused subagent brief should contain one job, its source material, permitted tools and the required final form. For example, it can examine a table for a stated rule and return the affected rows with the relevant values. The maker also highlights tabular-data processing and frontend JavaScript work assisted by lightweight code execution. The surrounding application remains responsible for running a requested function and returning the real result. Keep a finished result distinguishable from an unexecuted suggestion or an unresolved input question.
The exact 3.5 Flash-Lite page lists function calling, code execution, file search, search grounding, Maps grounding and URL context, with Computer Use marked as preview. Structured output and thinking are supported. For a multi-turn persona or task, retain the actual instructions and tool observations so later replies follow the same assignment. The developer guide highlights stronger persona persistence than 3.1 Flash-Lite. Use a concise role and output contract rather than redefining the objective at every follow-up.
The guide also deprecates legacy sampling settings and prefilled final model turns for this edition. Control a bounded answer with explicit instructions or a schema rather than trying to start the answer inside a synthetic model-role turn. Preserve the Gemini 3 thought-signature context where the interface requires it, and match function results to their calls. These preparation rules support a continuation that still has the evidence needed to complete the same job.
The native card lists up to 1M context and 64K text output; the exact API page specifies 1,048,576 input tokens and 65,536 output tokens. Instructions, records, history and media all contribute to input preparation. Caching, batch, Flex and Priority options are listed for the producer profile. For repeated requests, use stable identifiers and a compact consistent answer format so each extraction can be compared with its source. Audio, image or video input produces a text interpretation or transcript in this profile, rather than generated speech or artwork.
Possible limitations include hallucinations and occasional delays or timeouts. Its knowledge cutoff is March 2026, with some domains limited to January 2025. Source-dependent extraction should return what the supplied material supports; current-fact questions need current evidence. Compared with 3.1 Flash-Lite, this profile adds the documented execution and computer-use capabilities, while 3.6 Flash emphasizes more complex coding and spatial work. Review extracted fields, tool results and retained instructions before incorporating the answer into a larger workflow.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gemini-3.5-flash-lite | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring | RequirementRequired | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF-8 text
messages[].content string
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractstream |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_or_streamed
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "gemini-3.5-flash-lite",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'gemini-3.5-flash-lite', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'gemini-3.5-flash-lite', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n with urlopen(request, timeout=120) as response:\n raw = response.read()\n Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n Path('result.json').write_bytes(error.read())\n Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nJSON or SSE
Keep every complete returned response, file and content part.
Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldmodel | Typestring |
Fieldcontent[] | Typetext|thinking|tool_use|other content block |
Fieldstop_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot gemini-3.5-flash-lite, gemini-flash-lite, gemini-flash-lite-latest
Ailoot Ultra gemini-3.5-flash-lite, google/gemini-3.5-flash-lite
/chat/completions
google/gemini-3.5-flash-lite, gemini-flash-lite, gemini-flash-lite-latest, gemini-3.5-flash-lite, gemini-3.5-flash-lite
gemini-flash-liteGemini 3.5 Flash-Lite is Google’s multimodal model for focused subagent tasks, document parsing and repeated data extraction. Its default minimal reasoning suits bounded records; medium or high is documented for multi-step tool work. It returns text or structured results from text, images, audio, video and PDF.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 3.5 Flash-Lite is Google’s execution-focused multimodal text profile for repeated data work and focused subagent tasks. It builds on Gemini 3.1 Flash-Lite, improving document understanding, tool reliability and multi-turn instruction following. It accepts text, images, audio, video and PDF and returns text. A useful result is one extracted record, a classification, a short translation or a bounded tool-assisted analysis within a larger task.
For document parsing, define the fields that matter and the evidence each field must retain. Provide the relevant pages and specify how to represent absent or ambiguous information. For support-message extraction, extract a product code, mentioned issue and supporting sentence from a support message, keeping the message identifier in the answer. A document with multiple candidates for a field should not silently collapse them into one guessed value. Structured JSON can make the result usable for later processing when its schema matches the actual task.
The documented thinking levels are minimal, low, medium and high, with minimal as the default. The maker recommends it for high-volume extraction, routing and classification, while medium or high is appropriate for autonomous subagent work involving tool calls, code execution or several reasoning steps. The guide specifically advises increasing effort for those longer tasks to avoid premature tool termination. A one-field extraction and a document comparison with exceptions therefore benefit from different effort choices. Minimal is a supported setting of this edition rather than a general setting to transfer to every Flash model.
A focused subagent brief should contain one job, its source material, permitted tools and the required final form. For example, it can examine a table for a stated rule and return the affected rows with the relevant values. The maker also highlights tabular-data processing and frontend JavaScript work assisted by lightweight code execution. The surrounding application remains responsible for running a requested function and returning the real result. Keep a finished result distinguishable from an unexecuted suggestion or an unresolved input question.
The exact 3.5 Flash-Lite page lists function calling, code execution, file search, search grounding, Maps grounding and URL context, with Computer Use marked as preview. Structured output and thinking are supported. For a multi-turn persona or task, retain the actual instructions and tool observations so later replies follow the same assignment. The developer guide highlights stronger persona persistence than 3.1 Flash-Lite. Use a concise role and output contract rather than redefining the objective at every follow-up.
The guide also deprecates legacy sampling settings and prefilled final model turns for this edition. Control a bounded answer with explicit instructions or a schema rather than trying to start the answer inside a synthetic model-role turn. Preserve the Gemini 3 thought-signature context where the interface requires it, and match function results to their calls. These preparation rules support a continuation that still has the evidence needed to complete the same job.
The native card lists up to 1M context and 64K text output; the exact API page specifies 1,048,576 input tokens and 65,536 output tokens. Instructions, records, history and media all contribute to input preparation. Caching, batch, Flex and Priority options are listed for the producer profile. For repeated requests, use stable identifiers and a compact consistent answer format so each extraction can be compared with its source. Audio, image or video input produces a text interpretation or transcript in this profile, rather than generated speech or artwork.
Possible limitations include hallucinations and occasional delays or timeouts. Its knowledge cutoff is March 2026, with some domains limited to January 2025. Source-dependent extraction should return what the supplied material supports; current-fact questions need current evidence. Compared with 3.1 Flash-Lite, this profile adds the documented execution and computer-use capabilities, while 3.6 Flash emphasizes more complex coding and spatial work. Review extracted fields, tool results and retained instructions before incorporating the answer into a larger workflow.
POST /v1/messagestext, imagetext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gemini-flash-lite | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring|content_block[] | RequirementRequired | Values & limits | Default— |
Fieldsystem | Typestring|content_block[] | RequirementOptional | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits Minimum: 1 Limit applies to: exact selected model/card ceiling | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstop_sequences | Typestring[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools | Typetool[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].name | Typestring | RequirementOptional | Values & limits Applies when: tool supplied | Default— |
Fieldtools[].description | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools[].input_schema | TypeJSON_schema | RequirementOptional | Values & limits | Default— |
Fieldtool_choice | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldthinking.type | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldthinking.budget_tokens | Typeinteger | RequirementOptional | Values & limits Model-specific | Default— |
Fieldoutput_config.effort | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmetadata | Typeobject | RequirementOptional | Values & limits | Default— |
Fieldcache_control | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Text · UTF8 text
messages[].content or type=text block
Text + image
{type:image,source:{type:base64,media_type,data}} or source type=url
| Parameter | Contract |
|---|---|
Parametermaterial_types | Contracttext, image |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractnull |
Parametercontent_type | Contractapplication/json |
Parametertext_file_material | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |
Lifecycle: exact retained published method
Method shapes and IDs are exact; supplier capability is separate from admission.
POST /v1/messagesAiloot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "gemini-flash-lite", "max_tokens": 1024, "messages": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\\n\\n"+text}]\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "gemini-flash-lite", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="image/png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "image/jpeg" if raw.startswith(b"\\xff\\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nimport anthropic\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nmsg = client.messages.create(\n model="gemini-flash-lite",\n max_tokens=1024,\n messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(msg.to_dict(mode="json"))\nimport Anthropic from "@anthropic-ai/sdk";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n model: "gemini-flash-lite",\n max_tokens: 1024,\n messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],\n});\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(msg);\nimport anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.messages.stream(model='gemini-flash-lite',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_message()\n save_result(final.to_dict(mode="json"),"stream-result")\njson or SSE
Keep every complete returned response, file and content part.
Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldmodel | Typestring |
Fieldcontent[] | Typetext|thinking|tool_use|other content block |
Fieldstop_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot gemini-3.5-flash-lite, gemini-flash-lite, gemini-flash-lite-latest
Ailoot Ultra gemini-3.5-flash-lite, google/gemini-3.5-flash-lite
/chat/completions
google/gemini-3.5-flash-lite, gemini-flash-lite, gemini-flash-lite-latest, gemini-3.5-flash-lite, gemini-3.5-flash-lite
gemini-flash-liteGemini 3.5 Flash-Lite is Google’s multimodal model for focused subagent tasks, document parsing and repeated data extraction. Its default minimal reasoning suits bounded records; medium or high is documented for multi-step tool work. It returns text or structured results from text, images, audio, video and PDF.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 3.5 Flash-Lite is Google’s execution-focused multimodal text profile for repeated data work and focused subagent tasks. It builds on Gemini 3.1 Flash-Lite, improving document understanding, tool reliability and multi-turn instruction following. It accepts text, images, audio, video and PDF and returns text. A useful result is one extracted record, a classification, a short translation or a bounded tool-assisted analysis within a larger task.
For document parsing, define the fields that matter and the evidence each field must retain. Provide the relevant pages and specify how to represent absent or ambiguous information. For support-message extraction, extract a product code, mentioned issue and supporting sentence from a support message, keeping the message identifier in the answer. A document with multiple candidates for a field should not silently collapse them into one guessed value. Structured JSON can make the result usable for later processing when its schema matches the actual task.
The documented thinking levels are minimal, low, medium and high, with minimal as the default. The maker recommends it for high-volume extraction, routing and classification, while medium or high is appropriate for autonomous subagent work involving tool calls, code execution or several reasoning steps. The guide specifically advises increasing effort for those longer tasks to avoid premature tool termination. A one-field extraction and a document comparison with exceptions therefore benefit from different effort choices. Minimal is a supported setting of this edition rather than a general setting to transfer to every Flash model.
A focused subagent brief should contain one job, its source material, permitted tools and the required final form. For example, it can examine a table for a stated rule and return the affected rows with the relevant values. The maker also highlights tabular-data processing and frontend JavaScript work assisted by lightweight code execution. The surrounding application remains responsible for running a requested function and returning the real result. Keep a finished result distinguishable from an unexecuted suggestion or an unresolved input question.
The exact 3.5 Flash-Lite page lists function calling, code execution, file search, search grounding, Maps grounding and URL context, with Computer Use marked as preview. Structured output and thinking are supported. For a multi-turn persona or task, retain the actual instructions and tool observations so later replies follow the same assignment. The developer guide highlights stronger persona persistence than 3.1 Flash-Lite. Use a concise role and output contract rather than redefining the objective at every follow-up.
The guide also deprecates legacy sampling settings and prefilled final model turns for this edition. Control a bounded answer with explicit instructions or a schema rather than trying to start the answer inside a synthetic model-role turn. Preserve the Gemini 3 thought-signature context where the interface requires it, and match function results to their calls. These preparation rules support a continuation that still has the evidence needed to complete the same job.
The native card lists up to 1M context and 64K text output; the exact API page specifies 1,048,576 input tokens and 65,536 output tokens. Instructions, records, history and media all contribute to input preparation. Caching, batch, Flex and Priority options are listed for the producer profile. For repeated requests, use stable identifiers and a compact consistent answer format so each extraction can be compared with its source. Audio, image or video input produces a text interpretation or transcript in this profile, rather than generated speech or artwork.
Possible limitations include hallucinations and occasional delays or timeouts. Its knowledge cutoff is March 2026, with some domains limited to January 2025. Source-dependent extraction should return what the supplied material supports; current-fact questions need current evidence. Compared with 3.1 Flash-Lite, this profile adds the documented execution and computer-use capabilities, while 3.6 Flash emphasizes more complex coding and spatial work. Review extracted fields, tool results and retained instructions before incorporating the answer into a larger workflow.
POST /v1beta/models/{model}:generateContenttext, imagetext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldpath.model | Typestring | RequirementRequired | Values & limits gemini-flash-lite | Default— |
Fieldcontents | Typecontent[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldcontents[].role | Typestring | RequirementOptional | Values & limits user, model | Default— |
Fieldcontents[].parts | Typepart[] | RequirementRequired | Values & limits | Default— |
FieldsystemInstruction | Typecontent | RequirementOptional | Values & limits | Default— |
FieldgenerationConfig.maxOutputTokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
FieldgenerationConfig.temperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
FieldgenerationConfig.topP | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
FieldgenerationConfig.topK | Typeinteger | RequirementOptional | Values & limits Model-specific | Default— |
FieldgenerationConfig.stopSequences | Typestring[] | RequirementOptional | Values & limits Model-specific | Default— |
FieldgenerationConfig.thinkingConfig.includeThoughts | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
FieldgenerationConfig.thinkingConfig.thinkingBudget | Typeinteger | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].functionDeclarations | Typefunction_declaration[] | RequirementOptional | Values & limits Model-specific | Default— |
FieldtoolConfig.functionCallingConfig.mode | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
FieldsafetySettings | Typeobject[] | RequirementOptional | Values & limits Model-specific | Default— |
FieldsessionId | Typestring | RequirementOptional | Values & limits | Default— |
Text · UTF8 text
contents[].parts[].text
Text + image
parts[].inlineData={mimeType,data}
| Parameter | Contract |
|---|---|
Parametermaterial_types | Contracttext, image |
Parameterrequired | Contractcontents |
Parameteroptional_controls | Contractnull |
Parametercontent_type | Contractapplication/json |
Parametertext_file_material | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |
Lifecycle: exact retained published method
Method shapes and IDs are exact; supplier capability is separate from admission.
POST /v1beta/models/{model}:generateContentAiloot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"contents": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["contents"]=[{"role":"user","parts":[{"text":"Summarize this material and quote supporting source passages.\\n\\n"+text}]}]\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1beta/models/gemini-flash-lite:generateContent \\\n -H "x-goog-api-key: $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(json.loads(Path("result.json").read_text(encoding="utf-8")))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"contents": [{"role": "user", "parts": [{"text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="image/png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "image/jpeg" if raw.startswith(b"\\xff\\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["contents"][0]["parts"].append({"inlineData":{"mimeType":mime,"data":b64}})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1beta/models/gemini-flash-lite:generateContent \\\n -H "x-goog-api-key: $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(json.loads(Path("result.json").read_text(encoding="utf-8")))\nPY_RESULT\nfrom google import genai\nfrom google.genai import types\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = genai.Client(\n api_key=os.environ["AILOOT_API_KEY"],\n http_options=types.HttpOptions(base_url="https://api.ailoot.ai"),\n)\nresp = client.models.generate_content(model="gemini-flash-lite", contents="Explain the difference between an observation and a hypothesis in three sentences.")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(resp.to_json_dict())\nimport { GoogleGenAI } from "@google/genai";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst ai = new GoogleGenAI({ apiKey: process.env.AILOOT_API_KEY, httpOptions: { baseUrl: "https://api.ailoot.ai" } });\nconst resp = await ai.models.generateContent({ model: "gemini-flash-lite", contents: "Explain the difference between an observation and a hypothesis in three sentences." });\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(resp);\nfrom google import genai\nfrom google.genai import types\nimport os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=genai.Client(api_key=os.environ["AILOOT_API_KEY"],http_options=types.HttpOptions(base_url="https://api.ailoot.ai"))\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\ncount=0\nwith Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for chunk in client.models.generate_content_stream(model='gemini-flash-lite',contents="Explain observations and hypotheses in three sentences."):\n payload=chunk.to_json_dict()\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n save_result(payload,"stream-chunk-"+str(count))\n count+=1\njson or supported streaming
Keep every complete returned response, file and content part.
Keep all candidates and parts, including function calls, thought signatures and usage; assemble stream chunks in order.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
FieldresponseId | Typestring |
FieldmodelVersion | Typestring |
Fieldcandidates[].content.parts[] | Typetext|inlineData|functionCall|other part |
Fieldcandidates[].finishReason | Typestring |
FieldusageMetadata | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot gemini-3.5-flash-lite, gemini-flash-lite, gemini-flash-lite-latest
Ailoot Ultra gemini-3.5-flash-lite, google/gemini-3.5-flash-lite
/chat/completions
google/gemini-3.5-flash-lite, gemini-flash-lite, gemini-flash-lite-latest, gemini-3.5-flash-lite, gemini-3.5-flash-lite
gemini-flash-lite-latestGemini 3.5 Flash-Lite is Google’s multimodal model for focused subagent tasks, document parsing and repeated data extraction. Its default minimal reasoning suits bounded records; medium or high is documented for multi-step tool work. It returns text or structured results from text, images, audio, video and PDF.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 3.5 Flash-Lite is Google’s execution-focused multimodal text profile for repeated data work and focused subagent tasks. It builds on Gemini 3.1 Flash-Lite, improving document understanding, tool reliability and multi-turn instruction following. It accepts text, images, audio, video and PDF and returns text. A useful result is one extracted record, a classification, a short translation or a bounded tool-assisted analysis within a larger task.
For document parsing, define the fields that matter and the evidence each field must retain. Provide the relevant pages and specify how to represent absent or ambiguous information. For support-message extraction, extract a product code, mentioned issue and supporting sentence from a support message, keeping the message identifier in the answer. A document with multiple candidates for a field should not silently collapse them into one guessed value. Structured JSON can make the result usable for later processing when its schema matches the actual task.
The documented thinking levels are minimal, low, medium and high, with minimal as the default. The maker recommends it for high-volume extraction, routing and classification, while medium or high is appropriate for autonomous subagent work involving tool calls, code execution or several reasoning steps. The guide specifically advises increasing effort for those longer tasks to avoid premature tool termination. A one-field extraction and a document comparison with exceptions therefore benefit from different effort choices. Minimal is a supported setting of this edition rather than a general setting to transfer to every Flash model.
A focused subagent brief should contain one job, its source material, permitted tools and the required final form. For example, it can examine a table for a stated rule and return the affected rows with the relevant values. The maker also highlights tabular-data processing and frontend JavaScript work assisted by lightweight code execution. The surrounding application remains responsible for running a requested function and returning the real result. Keep a finished result distinguishable from an unexecuted suggestion or an unresolved input question.
The exact 3.5 Flash-Lite page lists function calling, code execution, file search, search grounding, Maps grounding and URL context, with Computer Use marked as preview. Structured output and thinking are supported. For a multi-turn persona or task, retain the actual instructions and tool observations so later replies follow the same assignment. The developer guide highlights stronger persona persistence than 3.1 Flash-Lite. Use a concise role and output contract rather than redefining the objective at every follow-up.
The guide also deprecates legacy sampling settings and prefilled final model turns for this edition. Control a bounded answer with explicit instructions or a schema rather than trying to start the answer inside a synthetic model-role turn. Preserve the Gemini 3 thought-signature context where the interface requires it, and match function results to their calls. These preparation rules support a continuation that still has the evidence needed to complete the same job.
The native card lists up to 1M context and 64K text output; the exact API page specifies 1,048,576 input tokens and 65,536 output tokens. Instructions, records, history and media all contribute to input preparation. Caching, batch, Flex and Priority options are listed for the producer profile. For repeated requests, use stable identifiers and a compact consistent answer format so each extraction can be compared with its source. Audio, image or video input produces a text interpretation or transcript in this profile, rather than generated speech or artwork.
Possible limitations include hallucinations and occasional delays or timeouts. Its knowledge cutoff is March 2026, with some domains limited to January 2025. Source-dependent extraction should return what the supplied material supports; current-fact questions need current evidence. Compared with 3.1 Flash-Lite, this profile adds the documented execution and computer-use capabilities, while 3.6 Flash emphasizes more complex coding and spatial work. Review extracted fields, tool results and retained instructions before incorporating the answer into a larger workflow.
POST /v1/messagestext, imagetext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gemini-flash-lite-latest | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring|content_block[] | RequirementRequired | Values & limits | Default— |
Fieldsystem | Typestring|content_block[] | RequirementOptional | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits Minimum: 1 Limit applies to: exact selected model/card ceiling | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstop_sequences | Typestring[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools | Typetool[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].name | Typestring | RequirementOptional | Values & limits Applies when: tool supplied | Default— |
Fieldtools[].description | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools[].input_schema | TypeJSON_schema | RequirementOptional | Values & limits | Default— |
Fieldtool_choice | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldthinking.type | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldthinking.budget_tokens | Typeinteger | RequirementOptional | Values & limits Model-specific | Default— |
Fieldoutput_config.effort | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmetadata | Typeobject | RequirementOptional | Values & limits | Default— |
Fieldcache_control | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Text · UTF8 text
messages[].content or type=text block
Text + image
{type:image,source:{type:base64,media_type,data}} or source type=url
| Parameter | Contract |
|---|---|
Parametermaterial_types | Contracttext, image |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractnull |
Parametercontent_type | Contractapplication/json |
Parametertext_file_material | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |
Lifecycle: exact retained published method
Method shapes and IDs are exact; supplier capability is separate from admission.
POST /v1/messagesAiloot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "gemini-flash-lite-latest", "max_tokens": 1024, "messages": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\\n\\n"+text}]\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "gemini-flash-lite-latest", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="image/png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "image/jpeg" if raw.startswith(b"\\xff\\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nimport anthropic\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nmsg = client.messages.create(\n model="gemini-flash-lite-latest",\n max_tokens=1024,\n messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(msg.to_dict(mode="json"))\nimport Anthropic from "@anthropic-ai/sdk";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n model: "gemini-flash-lite-latest",\n max_tokens: 1024,\n messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],\n});\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(msg);\nimport anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.messages.stream(model='gemini-flash-lite-latest',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_message()\n save_result(final.to_dict(mode="json"),"stream-result")\njson or SSE
Keep every complete returned response, file and content part.
Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldmodel | Typestring |
Fieldcontent[] | Typetext|thinking|tool_use|other content block |
Fieldstop_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot gemini-3.5-flash-lite, gemini-flash-lite, gemini-flash-lite-latest
Ailoot Ultra gemini-3.5-flash-lite, google/gemini-3.5-flash-lite
/chat/completions
google/gemini-3.5-flash-lite, gemini-flash-lite, gemini-flash-lite-latest, gemini-3.5-flash-lite, gemini-3.5-flash-lite
gemini-flash-lite-latestGemini 3.5 Flash-Lite is Google’s multimodal model for focused subagent tasks, document parsing and repeated data extraction. Its default minimal reasoning suits bounded records; medium or high is documented for multi-step tool work. It returns text or structured results from text, images, audio, video and PDF.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 3.5 Flash-Lite is Google’s execution-focused multimodal text profile for repeated data work and focused subagent tasks. It builds on Gemini 3.1 Flash-Lite, improving document understanding, tool reliability and multi-turn instruction following. It accepts text, images, audio, video and PDF and returns text. A useful result is one extracted record, a classification, a short translation or a bounded tool-assisted analysis within a larger task.
For document parsing, define the fields that matter and the evidence each field must retain. Provide the relevant pages and specify how to represent absent or ambiguous information. For support-message extraction, extract a product code, mentioned issue and supporting sentence from a support message, keeping the message identifier in the answer. A document with multiple candidates for a field should not silently collapse them into one guessed value. Structured JSON can make the result usable for later processing when its schema matches the actual task.
The documented thinking levels are minimal, low, medium and high, with minimal as the default. The maker recommends it for high-volume extraction, routing and classification, while medium or high is appropriate for autonomous subagent work involving tool calls, code execution or several reasoning steps. The guide specifically advises increasing effort for those longer tasks to avoid premature tool termination. A one-field extraction and a document comparison with exceptions therefore benefit from different effort choices. Minimal is a supported setting of this edition rather than a general setting to transfer to every Flash model.
A focused subagent brief should contain one job, its source material, permitted tools and the required final form. For example, it can examine a table for a stated rule and return the affected rows with the relevant values. The maker also highlights tabular-data processing and frontend JavaScript work assisted by lightweight code execution. The surrounding application remains responsible for running a requested function and returning the real result. Keep a finished result distinguishable from an unexecuted suggestion or an unresolved input question.
The exact 3.5 Flash-Lite page lists function calling, code execution, file search, search grounding, Maps grounding and URL context, with Computer Use marked as preview. Structured output and thinking are supported. For a multi-turn persona or task, retain the actual instructions and tool observations so later replies follow the same assignment. The developer guide highlights stronger persona persistence than 3.1 Flash-Lite. Use a concise role and output contract rather than redefining the objective at every follow-up.
The guide also deprecates legacy sampling settings and prefilled final model turns for this edition. Control a bounded answer with explicit instructions or a schema rather than trying to start the answer inside a synthetic model-role turn. Preserve the Gemini 3 thought-signature context where the interface requires it, and match function results to their calls. These preparation rules support a continuation that still has the evidence needed to complete the same job.
The native card lists up to 1M context and 64K text output; the exact API page specifies 1,048,576 input tokens and 65,536 output tokens. Instructions, records, history and media all contribute to input preparation. Caching, batch, Flex and Priority options are listed for the producer profile. For repeated requests, use stable identifiers and a compact consistent answer format so each extraction can be compared with its source. Audio, image or video input produces a text interpretation or transcript in this profile, rather than generated speech or artwork.
Possible limitations include hallucinations and occasional delays or timeouts. Its knowledge cutoff is March 2026, with some domains limited to January 2025. Source-dependent extraction should return what the supplied material supports; current-fact questions need current evidence. Compared with 3.1 Flash-Lite, this profile adds the documented execution and computer-use capabilities, while 3.6 Flash emphasizes more complex coding and spatial work. Review extracted fields, tool results and retained instructions before incorporating the answer into a larger workflow.
POST /v1beta/models/{model}:generateContenttext, imagetext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldpath.model | Typestring | RequirementRequired | Values & limits gemini-flash-lite-latest | Default— |
Fieldcontents | Typecontent[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldcontents[].role | Typestring | RequirementOptional | Values & limits user, model | Default— |
Fieldcontents[].parts | Typepart[] | RequirementRequired | Values & limits | Default— |
FieldsystemInstruction | Typecontent | RequirementOptional | Values & limits | Default— |
FieldgenerationConfig.maxOutputTokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
FieldgenerationConfig.temperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
FieldgenerationConfig.topP | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
FieldgenerationConfig.topK | Typeinteger | RequirementOptional | Values & limits Model-specific | Default— |
FieldgenerationConfig.stopSequences | Typestring[] | RequirementOptional | Values & limits Model-specific | Default— |
FieldgenerationConfig.thinkingConfig.includeThoughts | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
FieldgenerationConfig.thinkingConfig.thinkingBudget | Typeinteger | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].functionDeclarations | Typefunction_declaration[] | RequirementOptional | Values & limits Model-specific | Default— |
FieldtoolConfig.functionCallingConfig.mode | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
FieldsafetySettings | Typeobject[] | RequirementOptional | Values & limits Model-specific | Default— |
FieldsessionId | Typestring | RequirementOptional | Values & limits | Default— |
Text · UTF8 text
contents[].parts[].text
Text + image
parts[].inlineData={mimeType,data}
| Parameter | Contract |
|---|---|
Parametermaterial_types | Contracttext, image |
Parameterrequired | Contractcontents |
Parameteroptional_controls | Contractnull |
Parametercontent_type | Contractapplication/json |
Parametertext_file_material | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |
Lifecycle: exact retained published method
Method shapes and IDs are exact; supplier capability is separate from admission.
POST /v1beta/models/{model}:generateContentAiloot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"contents": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["contents"]=[{"role":"user","parts":[{"text":"Summarize this material and quote supporting source passages.\\n\\n"+text}]}]\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1beta/models/gemini-flash-lite-latest:generateContent \\\n -H "x-goog-api-key: $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(json.loads(Path("result.json").read_text(encoding="utf-8")))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"contents": [{"role": "user", "parts": [{"text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="image/png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "image/jpeg" if raw.startswith(b"\\xff\\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["contents"][0]["parts"].append({"inlineData":{"mimeType":mime,"data":b64}})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1beta/models/gemini-flash-lite-latest:generateContent \\\n -H "x-goog-api-key: $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(json.loads(Path("result.json").read_text(encoding="utf-8")))\nPY_RESULT\nfrom google import genai\nfrom google.genai import types\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = genai.Client(\n api_key=os.environ["AILOOT_API_KEY"],\n http_options=types.HttpOptions(base_url="https://api.ailoot.ai"),\n)\nresp = client.models.generate_content(model="gemini-flash-lite-latest", contents="Explain the difference between an observation and a hypothesis in three sentences.")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(resp.to_json_dict())\nimport { GoogleGenAI } from "@google/genai";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst ai = new GoogleGenAI({ apiKey: process.env.AILOOT_API_KEY, httpOptions: { baseUrl: "https://api.ailoot.ai" } });\nconst resp = await ai.models.generateContent({ model: "gemini-flash-lite-latest", contents: "Explain the difference between an observation and a hypothesis in three sentences." });\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(resp);\nfrom google import genai\nfrom google.genai import types\nimport os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=genai.Client(api_key=os.environ["AILOOT_API_KEY"],http_options=types.HttpOptions(base_url="https://api.ailoot.ai"))\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\ncount=0\nwith Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for chunk in client.models.generate_content_stream(model='gemini-flash-lite-latest',contents="Explain observations and hypotheses in three sentences."):\n payload=chunk.to_json_dict()\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n save_result(payload,"stream-chunk-"+str(count))\n count+=1\njson or supported streaming
Keep every complete returned response, file and content part.
Keep all candidates and parts, including function calls, thought signatures and usage; assemble stream chunks in order.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
FieldresponseId | Typestring |
FieldmodelVersion | Typestring |
Fieldcandidates[].content.parts[] | Typetext|inlineData|functionCall|other part |
Fieldcandidates[].finishReason | Typestring |
FieldusageMetadata | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot gemini-3.5-flash-lite, gemini-flash-lite, gemini-flash-lite-latest
Ailoot Ultra gemini-3.5-flash-lite, google/gemini-3.5-flash-lite
/chat/completions
google/gemini-3.5-flash-lite, gemini-flash-lite, gemini-flash-lite-latest, gemini-3.5-flash-lite, gemini-3.5-flash-lite
google/gemini-3.5-flash-liteGemini 3.5 Flash-Lite is Google’s multimodal model for focused subagent tasks, document parsing and repeated data extraction. Its default minimal reasoning suits bounded records; medium or high is documented for multi-step tool work. It returns text or structured results from text, images, audio, video and PDF.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 3.5 Flash-Lite is Google’s execution-focused multimodal text profile for repeated data work and focused subagent tasks. It builds on Gemini 3.1 Flash-Lite, improving document understanding, tool reliability and multi-turn instruction following. It accepts text, images, audio, video and PDF and returns text. A useful result is one extracted record, a classification, a short translation or a bounded tool-assisted analysis within a larger task.
For document parsing, define the fields that matter and the evidence each field must retain. Provide the relevant pages and specify how to represent absent or ambiguous information. For support-message extraction, extract a product code, mentioned issue and supporting sentence from a support message, keeping the message identifier in the answer. A document with multiple candidates for a field should not silently collapse them into one guessed value. Structured JSON can make the result usable for later processing when its schema matches the actual task.
The documented thinking levels are minimal, low, medium and high, with minimal as the default. The maker recommends it for high-volume extraction, routing and classification, while medium or high is appropriate for autonomous subagent work involving tool calls, code execution or several reasoning steps. The guide specifically advises increasing effort for those longer tasks to avoid premature tool termination. A one-field extraction and a document comparison with exceptions therefore benefit from different effort choices. Minimal is a supported setting of this edition rather than a general setting to transfer to every Flash model.
A focused subagent brief should contain one job, its source material, permitted tools and the required final form. For example, it can examine a table for a stated rule and return the affected rows with the relevant values. The maker also highlights tabular-data processing and frontend JavaScript work assisted by lightweight code execution. The surrounding application remains responsible for running a requested function and returning the real result. Keep a finished result distinguishable from an unexecuted suggestion or an unresolved input question.
The exact 3.5 Flash-Lite page lists function calling, code execution, file search, search grounding, Maps grounding and URL context, with Computer Use marked as preview. Structured output and thinking are supported. For a multi-turn persona or task, retain the actual instructions and tool observations so later replies follow the same assignment. The developer guide highlights stronger persona persistence than 3.1 Flash-Lite. Use a concise role and output contract rather than redefining the objective at every follow-up.
The guide also deprecates legacy sampling settings and prefilled final model turns for this edition. Control a bounded answer with explicit instructions or a schema rather than trying to start the answer inside a synthetic model-role turn. Preserve the Gemini 3 thought-signature context where the interface requires it, and match function results to their calls. These preparation rules support a continuation that still has the evidence needed to complete the same job.
The native card lists up to 1M context and 64K text output; the exact API page specifies 1,048,576 input tokens and 65,536 output tokens. Instructions, records, history and media all contribute to input preparation. Caching, batch, Flex and Priority options are listed for the producer profile. For repeated requests, use stable identifiers and a compact consistent answer format so each extraction can be compared with its source. Audio, image or video input produces a text interpretation or transcript in this profile, rather than generated speech or artwork.
Possible limitations include hallucinations and occasional delays or timeouts. Its knowledge cutoff is March 2026, with some domains limited to January 2025. Source-dependent extraction should return what the supplied material supports; current-fact questions need current evidence. Compared with 3.1 Flash-Lite, this profile adds the documented execution and computer-use capabilities, while 3.6 Flash emphasizes more complex coding and spatial work. Review extracted fields, tool results and retained instructions before incorporating the answer into a larger workflow.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits google/gemini-3.5-flash-lite | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
Fieldmessages[].content | Typestring|content_part[]|null | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_calls | Typetool_call[] | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_call_id | Typestring | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
Fieldmessages[].name | Typestring | RequirementOptional | Values & limits | Default— |
Fieldmessages[].reasoning_content | Typestring | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
Fieldmessages[].reasoning_details | Typeobject|array | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmax_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldmax_completion_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldstream_options.include_usage | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstop | Typestring|string[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools | Typefunction_tool[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].type | Typestring | RequirementOptional | Values & limits function Model-specific | Default— |
Fieldtools[].function.name | Typestring | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
Fieldtools[].function.description | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools[].function.parameters | TypeJSON_schema | RequirementOptional | Values & limits | Default— |
Fieldtool_choice | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldparallel_tool_calls | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldresponse_format | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning_effort | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldservice_tier | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldinstructions | Typestring | RequirementOptional | Values & limits Compatibility field | Default— |
Fieldfunctions | Typefunction[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldfunction_call | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldprompt_cache_options | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmodalities | Typestring[] | RequirementOptional | Values & limits text | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— |
Fieldcache_control.ttl | Typestring | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice |
Parametercontrol_scope | Contractmodel-specific; user function tools differ from hosted tools |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "google/gemini-3.5-flash-lite", "messages": [{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}]}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("choices",[]):\n if x.get("message",{}).get("content"): print(x["message"]["content"])\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.chat.completions.create(model='google/gemini-3.5-flash-lite',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}])\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(result.to_dict(mode="json"))\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.chat.completions.stream(model='google/gemini-3.5-flash-lite',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_completion()\n save_result(final.to_dict(mode="json"),"stream-result")\njson or SSE
Keep every complete returned response, file and content part.
Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldchoices[].index | Typeinteger |
Fieldchoices[].message.content | Typestring|null |
Fieldchoices[].message.tool_calls | Typetool_call[] |
Fieldchoices[].message.reasoning_content | Typestring |
Fieldchoices[].message.reasoning_details | Typeobject|array |
Fieldchoices[].finish_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot gemini-3.5-flash-lite, gemini-flash-lite, gemini-flash-lite-latest
Ailoot Ultra gemini-3.5-flash-lite, google/gemini-3.5-flash-lite
/chat/completions
google/gemini-3.5-flash-lite, gemini-flash-lite, gemini-flash-lite-latest, gemini-3.5-flash-lite, gemini-3.5-flash-lite
google/gemini-3.5-flash-liteGemini 3.5 Flash-Lite is Google’s multimodal model for focused subagent tasks, document parsing and repeated data extraction. Its default minimal reasoning suits bounded records; medium or high is documented for multi-step tool work. It returns text or structured results from text, images, audio, video and PDF.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 3.5 Flash-Lite is Google’s execution-focused multimodal text profile for repeated data work and focused subagent tasks. It builds on Gemini 3.1 Flash-Lite, improving document understanding, tool reliability and multi-turn instruction following. It accepts text, images, audio, video and PDF and returns text. A useful result is one extracted record, a classification, a short translation or a bounded tool-assisted analysis within a larger task.
For document parsing, define the fields that matter and the evidence each field must retain. Provide the relevant pages and specify how to represent absent or ambiguous information. For support-message extraction, extract a product code, mentioned issue and supporting sentence from a support message, keeping the message identifier in the answer. A document with multiple candidates for a field should not silently collapse them into one guessed value. Structured JSON can make the result usable for later processing when its schema matches the actual task.
The documented thinking levels are minimal, low, medium and high, with minimal as the default. The maker recommends it for high-volume extraction, routing and classification, while medium or high is appropriate for autonomous subagent work involving tool calls, code execution or several reasoning steps. The guide specifically advises increasing effort for those longer tasks to avoid premature tool termination. A one-field extraction and a document comparison with exceptions therefore benefit from different effort choices. Minimal is a supported setting of this edition rather than a general setting to transfer to every Flash model.
A focused subagent brief should contain one job, its source material, permitted tools and the required final form. For example, it can examine a table for a stated rule and return the affected rows with the relevant values. The maker also highlights tabular-data processing and frontend JavaScript work assisted by lightweight code execution. The surrounding application remains responsible for running a requested function and returning the real result. Keep a finished result distinguishable from an unexecuted suggestion or an unresolved input question.
The exact 3.5 Flash-Lite page lists function calling, code execution, file search, search grounding, Maps grounding and URL context, with Computer Use marked as preview. Structured output and thinking are supported. For a multi-turn persona or task, retain the actual instructions and tool observations so later replies follow the same assignment. The developer guide highlights stronger persona persistence than 3.1 Flash-Lite. Use a concise role and output contract rather than redefining the objective at every follow-up.
The guide also deprecates legacy sampling settings and prefilled final model turns for this edition. Control a bounded answer with explicit instructions or a schema rather than trying to start the answer inside a synthetic model-role turn. Preserve the Gemini 3 thought-signature context where the interface requires it, and match function results to their calls. These preparation rules support a continuation that still has the evidence needed to complete the same job.
The native card lists up to 1M context and 64K text output; the exact API page specifies 1,048,576 input tokens and 65,536 output tokens. Instructions, records, history and media all contribute to input preparation. Caching, batch, Flex and Priority options are listed for the producer profile. For repeated requests, use stable identifiers and a compact consistent answer format so each extraction can be compared with its source. Audio, image or video input produces a text interpretation or transcript in this profile, rather than generated speech or artwork.
Possible limitations include hallucinations and occasional delays or timeouts. Its knowledge cutoff is March 2026, with some domains limited to January 2025. Source-dependent extraction should return what the supplied material supports; current-fact questions need current evidence. Compared with 3.1 Flash-Lite, this profile adds the documented execution and computer-use capabilities, while 3.6 Flash emphasizes more complex coding and spatial work. Review extracted fields, tool results and retained instructions before incorporating the answer into a larger workflow.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits google/gemini-3.5-flash-lite | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring | RequirementRequired | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF-8 text
messages[].content string
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractstream |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_or_streamed
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0006 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "google/gemini-3.5-flash-lite",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'google/gemini-3.5-flash-lite', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'google/gemini-3.5-flash-lite', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n with urlopen(request, timeout=120) as response:\n raw = response.read()\n Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n Path('result.json').write_bytes(error.read())\n Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nJSON or SSE
Keep every complete returned response, file and content part.
Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldmodel | Typestring |
Fieldcontent[] | Typetext|thinking|tool_use|other content block |
Fieldstop_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot gemini-3.5-flash-lite, gemini-flash-lite, gemini-flash-lite-latest
Ailoot Ultra gemini-3.5-flash-lite, google/gemini-3.5-flash-lite
/chat/completions
google/gemini-3.5-flash-lite, gemini-flash-lite, gemini-flash-lite-latest, gemini-3.5-flash-lite, gemini-3.5-flash-lite
Technical example in English
Extract a support message record\n\nExtract fields from message S-91: "The pump P-28 stopped after ten minutes. I bought two, but only one has this issue. Please arrange a replacement." Return message ID, product code, issue, purchased quantity and affected quantity in a small table. Include the exact supporting phrase for each extracted value.A field/value/evidence table retaining S-91 and separating purchased from affected quantity.Check that two purchased pumps do not become two defective pumps.