Gemini 3 Flash Preview is a Google reasoning model for multimodal understanding, coding and agentic tasks. It accepts text, images, video, audio and PDF and returns text. A request can therefore join written instructions, source files, visual observations and conversation history around one problem. The result may be an explanation, a code proposal, extracted data or a plan grounded in those materials, rather than a generated image or spoken response.
The exact model card gives an input limit of 1,048,576 tokens and an output limit of 65,536 tokens. Plan the source and result separately: a long repository excerpt, document collection or recording can fit only when its processed representation and instructions fit the input budget, and the answer still needs its own allotted length. Label related sources and identify which material is authoritative. For a long prompt, the developer guide recommends placing the specific question after the data and tying it explicitly to the preceding information.
Thinking is dynamic, with high as the documented default for this model. The supported levels are minimal, low, medium and high. They are relative reasoning allowances rather than guaranteed token counts. Minimal can still involve some reasoning on a difficult coding problem. Choose a level according to the task: a short transformation and a multi-condition debugging problem need different treatment. Use direct, clear instructions instead of forcing elaborate reasoning rituals into the prompt; request the final artifact and the checks that make it usable.
The producer card lists structured outputs, function calling, code execution, computer use, file search, search grounding, Google Maps grounding, URL context and caching. Built-in tools can be combined with custom function calling in the documented Gemini 3 flow. An application defines the functions, checks their arguments, executes accepted actions and sends back their results. For a code assistant, a read-file or controlled test-runner tool can provide concrete evidence for the next step. A proposed action and an observed tool result should remain distinct in the final report.
For programming, supply the relevant files, language, expected behavior and an input that demonstrates the issue. Set the scope of the change and name the interface or behavior that must remain. Ask for a revised implementation and the cases that should be checked. For an analytical document task, define the question, required fields and source references. If structured output is used, provide a schema with clear field meanings and missing-value rules. Validate both its syntax and whether each value follows from the original material.
For multimodal analysis, identify what matters in each source. A screenshot can support an interface explanation, a PDF can supply a table or chart, and a recording can provide spoken or visible events. The developer guide discusses media-resolution controls because detail changes the processed representation and token use. The producer’s code-execution workflow can crop or zoom supplied images, run calculations from visual data and add annotations before the model prepares its answer. Readable small text may require a different setting from a broad scene description. Keep the relevant page, image or clip available so observations can be checked rather than treating a fluent summary as evidence that every detail was read correctly.
Conversation and tool state need to be retained in the chosen interface. Gemini 3 uses thought signatures to carry reasoning context between calls; the developer guide distinguishes managed stateful history from manually managed stateless history. Preserve the required context when continuing a tool task or revising a result. Google also recommends keeping its default temperature of 1.0 rather than importing a low-temperature recipe that can cause loops or degraded behavior on complex tasks. These are producer integration practices, not new claims about any particular application’s transport.
The text model does not advertise image or audio generation or the Live API. The guide also distinguishes visual understanding from pixel-level image segmentation, which is not a supported Gemini 3 Flash capability. Use an appropriate final result for the actual task: source-linked observations, a structured record, a code change or a decision with its assumptions stated. Check arithmetic, verify code in the intended environment and review returned tool information. When recent facts matter, use the configured grounding sources or supplied current data instead of assuming that model knowledge is a live database.
", "aboutText": "Gemini 3 Flash Preview is a Google reasoning model for multimodal understanding, coding and agentic tasks. It accepts text, images, video, audio and PDF and returns text. A request can therefore join written instructions, source files, visual observations and conversation history around one problem. The result may be an explanation, a code proposal, extracted data or a plan grounded in those materials, rather than a generated image or spoken response.\n\nThe exact model card gives an input limit of 1,048,576 tokens and an output limit of 65,536 tokens. Plan the source and result separately: a long repository excerpt, document collection or recording can fit only when its processed representation and instructions fit the input budget, and the answer still needs its own allotted length. Label related sources and identify which material is authoritative. For a long prompt, the developer guide recommends placing the specific question after the data and tying it explicitly to the preceding information.\n\nThinking is dynamic, with high as the documented default for this model. The supported levels are minimal, low, medium and high. They are relative reasoning allowances rather than guaranteed token counts. Minimal can still involve some reasoning on a difficult coding problem. Choose a level according to the task: a short transformation and a multi-condition debugging problem need different treatment. Use direct, clear instructions instead of forcing elaborate reasoning rituals into the prompt; request the final artifact and the checks that make it usable.\n\nThe producer card lists structured outputs, function calling, code execution, computer use, file search, search grounding, Google Maps grounding, URL context and caching. Built-in tools can be combined with custom function calling in the documented Gemini 3 flow. An application defines the functions, checks their arguments, executes accepted actions and sends back their results. For a code assistant, a read-file or controlled test-runner tool can provide concrete evidence for the next step. A proposed action and an observed tool result should remain distinct in the final report.\n\nFor programming, supply the relevant files, language, expected behavior and an input that demonstrates the issue. Set the scope of the change and name the interface or behavior that must remain. Ask for a revised implementation and the cases that should be checked. For an analytical document task, define the question, required fields and source references. If structured output is used, provide a schema with clear field meanings and missing-value rules. Validate both its syntax and whether each value follows from the original material.\n\nFor multimodal analysis, identify what matters in each source. A screenshot can support an interface explanation, a PDF can supply a table or chart, and a recording can provide spoken or visible events. The developer guide discusses media-resolution controls because detail changes the processed representation and token use. The producer’s code-execution workflow can crop or zoom supplied images, run calculations from visual data and add annotations before the model prepares its answer. Readable small text may require a different setting from a broad scene description. Keep the relevant page, image or clip available so observations can be checked rather than treating a fluent summary as evidence that every detail was read correctly.\n\nConversation and tool state need to be retained in the chosen interface. Gemini 3 uses thought signatures to carry reasoning context between calls; the developer guide distinguishes managed stateful history from manually managed stateless history. Preserve the required context when continuing a tool task or revising a result. Google also recommends keeping its default temperature of 1.0 rather than importing a low-temperature recipe that can cause loops or degraded behavior on complex tasks. These are producer integration practices, not new claims about any particular application’s transport.\n\nThe text model does not advertise image or audio generation or the Live API. The guide also distinguishes visual understanding from pixel-level image segmentation, which is not a supported Gemini 3 Flash capability. Use an appropriate final result for the actual task: source-linked observations, a structured record, a code change or a decision with its assumptions stated. Check arithmetic, verify code in the intended environment and review returned tool information. When recent facts matter, use the configured grounding sources or supplied current data instead of assuming that model knowledge is a live database.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Keep a sorting helper immutable\n\nFix this JavaScript helper so it returns users sorted by name without changing the input array: function sortedUsers(users) { return users.sort((a,b) => a.name.localeCompare(b.name)); }. Preserve each user object. Return the revised function and tests for alphabetical order, an empty array and the unchanged original array.A revised function and three small test examples covering sorting and non-mutation.Check that the returned array is a different array and the original sequence is unchanged after the call.gemini-3-flash-previewGemini 3 Flash Preview combines multimodal understanding and reasoning with text output. It supports code, document and visual analysis, structured results and tool-oriented workflows, with four documented thinking levels for choosing the depth of analysis.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 3 Flash Preview is a Google reasoning model for multimodal understanding, coding and agentic tasks. It accepts text, images, video, audio and PDF and returns text. A request can therefore join written instructions, source files, visual observations and conversation history around one problem. The result may be an explanation, a code proposal, extracted data or a plan grounded in those materials, rather than a generated image or spoken response.
The exact model card gives an input limit of 1,048,576 tokens and an output limit of 65,536 tokens. Plan the source and result separately: a long repository excerpt, document collection or recording can fit only when its processed representation and instructions fit the input budget, and the answer still needs its own allotted length. Label related sources and identify which material is authoritative. For a long prompt, the developer guide recommends placing the specific question after the data and tying it explicitly to the preceding information.
Thinking is dynamic, with high as the documented default for this model. The supported levels are minimal, low, medium and high. They are relative reasoning allowances rather than guaranteed token counts. Minimal can still involve some reasoning on a difficult coding problem. Choose a level according to the task: a short transformation and a multi-condition debugging problem need different treatment. Use direct, clear instructions instead of forcing elaborate reasoning rituals into the prompt; request the final artifact and the checks that make it usable.
The producer card lists structured outputs, function calling, code execution, computer use, file search, search grounding, Google Maps grounding, URL context and caching. Built-in tools can be combined with custom function calling in the documented Gemini 3 flow. An application defines the functions, checks their arguments, executes accepted actions and sends back their results. For a code assistant, a read-file or controlled test-runner tool can provide concrete evidence for the next step. A proposed action and an observed tool result should remain distinct in the final report.
For programming, supply the relevant files, language, expected behavior and an input that demonstrates the issue. Set the scope of the change and name the interface or behavior that must remain. Ask for a revised implementation and the cases that should be checked. For an analytical document task, define the question, required fields and source references. If structured output is used, provide a schema with clear field meanings and missing-value rules. Validate both its syntax and whether each value follows from the original material.
For multimodal analysis, identify what matters in each source. A screenshot can support an interface explanation, a PDF can supply a table or chart, and a recording can provide spoken or visible events. The developer guide discusses media-resolution controls because detail changes the processed representation and token use. The producer’s code-execution workflow can crop or zoom supplied images, run calculations from visual data and add annotations before the model prepares its answer. Readable small text may require a different setting from a broad scene description. Keep the relevant page, image or clip available so observations can be checked rather than treating a fluent summary as evidence that every detail was read correctly.
Conversation and tool state need to be retained in the chosen interface. Gemini 3 uses thought signatures to carry reasoning context between calls; the developer guide distinguishes managed stateful history from manually managed stateless history. Preserve the required context when continuing a tool task or revising a result. Google also recommends keeping its default temperature of 1.0 rather than importing a low-temperature recipe that can cause loops or degraded behavior on complex tasks. These are producer integration practices, not new claims about any particular application’s transport.
The text model does not advertise image or audio generation or the Live API. The guide also distinguishes visual understanding from pixel-level image segmentation, which is not a supported Gemini 3 Flash capability. Use an appropriate final result for the actual task: source-linked observations, a structured record, a code change or a decision with its assumptions stated. Check arithmetic, verify code in the intended environment and review returned tool information. When recent facts matter, use the configured grounding sources or supplied current data instead of assuming that model knowledge is a live database.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gemini-3-flash-preview | 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 $0.001 / 1K tokens Output · Output tokens $0.006 / 1K tokens Input · Cache read $0.0001 / 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 $0.001 / 1K tokens Output · Output tokens $0.006 / 1K tokens Input · Cache read $0.0001 / 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-flash-preview","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-flash-preview", 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 Ultra gemini-3-flash-preview, google/gemini-3-flash-preview
/chat/completions
gemini-3-flash-previewGemini 3 Flash Preview combines multimodal understanding and reasoning with text output. It supports code, document and visual analysis, structured results and tool-oriented workflows, with four documented thinking levels for choosing the depth of analysis.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 3 Flash Preview is a Google reasoning model for multimodal understanding, coding and agentic tasks. It accepts text, images, video, audio and PDF and returns text. A request can therefore join written instructions, source files, visual observations and conversation history around one problem. The result may be an explanation, a code proposal, extracted data or a plan grounded in those materials, rather than a generated image or spoken response.
The exact model card gives an input limit of 1,048,576 tokens and an output limit of 65,536 tokens. Plan the source and result separately: a long repository excerpt, document collection or recording can fit only when its processed representation and instructions fit the input budget, and the answer still needs its own allotted length. Label related sources and identify which material is authoritative. For a long prompt, the developer guide recommends placing the specific question after the data and tying it explicitly to the preceding information.
Thinking is dynamic, with high as the documented default for this model. The supported levels are minimal, low, medium and high. They are relative reasoning allowances rather than guaranteed token counts. Minimal can still involve some reasoning on a difficult coding problem. Choose a level according to the task: a short transformation and a multi-condition debugging problem need different treatment. Use direct, clear instructions instead of forcing elaborate reasoning rituals into the prompt; request the final artifact and the checks that make it usable.
The producer card lists structured outputs, function calling, code execution, computer use, file search, search grounding, Google Maps grounding, URL context and caching. Built-in tools can be combined with custom function calling in the documented Gemini 3 flow. An application defines the functions, checks their arguments, executes accepted actions and sends back their results. For a code assistant, a read-file or controlled test-runner tool can provide concrete evidence for the next step. A proposed action and an observed tool result should remain distinct in the final report.
For programming, supply the relevant files, language, expected behavior and an input that demonstrates the issue. Set the scope of the change and name the interface or behavior that must remain. Ask for a revised implementation and the cases that should be checked. For an analytical document task, define the question, required fields and source references. If structured output is used, provide a schema with clear field meanings and missing-value rules. Validate both its syntax and whether each value follows from the original material.
For multimodal analysis, identify what matters in each source. A screenshot can support an interface explanation, a PDF can supply a table or chart, and a recording can provide spoken or visible events. The developer guide discusses media-resolution controls because detail changes the processed representation and token use. The producer’s code-execution workflow can crop or zoom supplied images, run calculations from visual data and add annotations before the model prepares its answer. Readable small text may require a different setting from a broad scene description. Keep the relevant page, image or clip available so observations can be checked rather than treating a fluent summary as evidence that every detail was read correctly.
Conversation and tool state need to be retained in the chosen interface. Gemini 3 uses thought signatures to carry reasoning context between calls; the developer guide distinguishes managed stateful history from manually managed stateless history. Preserve the required context when continuing a tool task or revising a result. Google also recommends keeping its default temperature of 1.0 rather than importing a low-temperature recipe that can cause loops or degraded behavior on complex tasks. These are producer integration practices, not new claims about any particular application’s transport.
The text model does not advertise image or audio generation or the Live API. The guide also distinguishes visual understanding from pixel-level image segmentation, which is not a supported Gemini 3 Flash capability. Use an appropriate final result for the actual task: source-linked observations, a structured record, a code change or a decision with its assumptions stated. Check arithmetic, verify code in the intended environment and review returned tool information. When recent facts matter, use the configured grounding sources or supplied current data instead of assuming that model knowledge is a live database.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gemini-3-flash-preview | 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 $0.001 / 1K tokens Output · Output tokens $0.006 / 1K tokens Input · Cache read $0.0001 / 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 $0.001 / 1K tokens Output · Output tokens $0.006 / 1K tokens Input · Cache read $0.0001 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "gemini-3-flash-preview",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-flash-preview', '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-flash-preview', '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 Ultra gemini-3-flash-preview, google/gemini-3-flash-preview
/chat/completions
google/gemini-3-flash-previewGemini 3 Flash Preview combines multimodal understanding and reasoning with text output. It supports code, document and visual analysis, structured results and tool-oriented workflows, with four documented thinking levels for choosing the depth of analysis.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 3 Flash Preview is a Google reasoning model for multimodal understanding, coding and agentic tasks. It accepts text, images, video, audio and PDF and returns text. A request can therefore join written instructions, source files, visual observations and conversation history around one problem. The result may be an explanation, a code proposal, extracted data or a plan grounded in those materials, rather than a generated image or spoken response.
The exact model card gives an input limit of 1,048,576 tokens and an output limit of 65,536 tokens. Plan the source and result separately: a long repository excerpt, document collection or recording can fit only when its processed representation and instructions fit the input budget, and the answer still needs its own allotted length. Label related sources and identify which material is authoritative. For a long prompt, the developer guide recommends placing the specific question after the data and tying it explicitly to the preceding information.
Thinking is dynamic, with high as the documented default for this model. The supported levels are minimal, low, medium and high. They are relative reasoning allowances rather than guaranteed token counts. Minimal can still involve some reasoning on a difficult coding problem. Choose a level according to the task: a short transformation and a multi-condition debugging problem need different treatment. Use direct, clear instructions instead of forcing elaborate reasoning rituals into the prompt; request the final artifact and the checks that make it usable.
The producer card lists structured outputs, function calling, code execution, computer use, file search, search grounding, Google Maps grounding, URL context and caching. Built-in tools can be combined with custom function calling in the documented Gemini 3 flow. An application defines the functions, checks their arguments, executes accepted actions and sends back their results. For a code assistant, a read-file or controlled test-runner tool can provide concrete evidence for the next step. A proposed action and an observed tool result should remain distinct in the final report.
For programming, supply the relevant files, language, expected behavior and an input that demonstrates the issue. Set the scope of the change and name the interface or behavior that must remain. Ask for a revised implementation and the cases that should be checked. For an analytical document task, define the question, required fields and source references. If structured output is used, provide a schema with clear field meanings and missing-value rules. Validate both its syntax and whether each value follows from the original material.
For multimodal analysis, identify what matters in each source. A screenshot can support an interface explanation, a PDF can supply a table or chart, and a recording can provide spoken or visible events. The developer guide discusses media-resolution controls because detail changes the processed representation and token use. The producer’s code-execution workflow can crop or zoom supplied images, run calculations from visual data and add annotations before the model prepares its answer. Readable small text may require a different setting from a broad scene description. Keep the relevant page, image or clip available so observations can be checked rather than treating a fluent summary as evidence that every detail was read correctly.
Conversation and tool state need to be retained in the chosen interface. Gemini 3 uses thought signatures to carry reasoning context between calls; the developer guide distinguishes managed stateful history from manually managed stateless history. Preserve the required context when continuing a tool task or revising a result. Google also recommends keeping its default temperature of 1.0 rather than importing a low-temperature recipe that can cause loops or degraded behavior on complex tasks. These are producer integration practices, not new claims about any particular application’s transport.
The text model does not advertise image or audio generation or the Live API. The guide also distinguishes visual understanding from pixel-level image segmentation, which is not a supported Gemini 3 Flash capability. Use an appropriate final result for the actual task: source-linked observations, a structured record, a code change or a decision with its assumptions stated. Check arithmetic, verify code in the intended environment and review returned tool information. When recent facts matter, use the configured grounding sources or supplied current data instead of assuming that model knowledge is a live database.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits google/gemini-3-flash-preview | 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 $0.001 / 1K tokens Output · Output tokens $0.006 / 1K tokens Input · Cache read $0.0001 / 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 $0.001 / 1K tokens Output · Output tokens $0.006 / 1K tokens Input · Cache read $0.0001 / 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-flash-preview", "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-flash-preview',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-flash-preview',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 Ultra gemini-3-flash-preview, google/gemini-3-flash-preview
/chat/completions
google/gemini-3-flash-previewGemini 3 Flash Preview combines multimodal understanding and reasoning with text output. It supports code, document and visual analysis, structured results and tool-oriented workflows, with four documented thinking levels for choosing the depth of analysis.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 3 Flash Preview is a Google reasoning model for multimodal understanding, coding and agentic tasks. It accepts text, images, video, audio and PDF and returns text. A request can therefore join written instructions, source files, visual observations and conversation history around one problem. The result may be an explanation, a code proposal, extracted data or a plan grounded in those materials, rather than a generated image or spoken response.
The exact model card gives an input limit of 1,048,576 tokens and an output limit of 65,536 tokens. Plan the source and result separately: a long repository excerpt, document collection or recording can fit only when its processed representation and instructions fit the input budget, and the answer still needs its own allotted length. Label related sources and identify which material is authoritative. For a long prompt, the developer guide recommends placing the specific question after the data and tying it explicitly to the preceding information.
Thinking is dynamic, with high as the documented default for this model. The supported levels are minimal, low, medium and high. They are relative reasoning allowances rather than guaranteed token counts. Minimal can still involve some reasoning on a difficult coding problem. Choose a level according to the task: a short transformation and a multi-condition debugging problem need different treatment. Use direct, clear instructions instead of forcing elaborate reasoning rituals into the prompt; request the final artifact and the checks that make it usable.
The producer card lists structured outputs, function calling, code execution, computer use, file search, search grounding, Google Maps grounding, URL context and caching. Built-in tools can be combined with custom function calling in the documented Gemini 3 flow. An application defines the functions, checks their arguments, executes accepted actions and sends back their results. For a code assistant, a read-file or controlled test-runner tool can provide concrete evidence for the next step. A proposed action and an observed tool result should remain distinct in the final report.
For programming, supply the relevant files, language, expected behavior and an input that demonstrates the issue. Set the scope of the change and name the interface or behavior that must remain. Ask for a revised implementation and the cases that should be checked. For an analytical document task, define the question, required fields and source references. If structured output is used, provide a schema with clear field meanings and missing-value rules. Validate both its syntax and whether each value follows from the original material.
For multimodal analysis, identify what matters in each source. A screenshot can support an interface explanation, a PDF can supply a table or chart, and a recording can provide spoken or visible events. The developer guide discusses media-resolution controls because detail changes the processed representation and token use. The producer’s code-execution workflow can crop or zoom supplied images, run calculations from visual data and add annotations before the model prepares its answer. Readable small text may require a different setting from a broad scene description. Keep the relevant page, image or clip available so observations can be checked rather than treating a fluent summary as evidence that every detail was read correctly.
Conversation and tool state need to be retained in the chosen interface. Gemini 3 uses thought signatures to carry reasoning context between calls; the developer guide distinguishes managed stateful history from manually managed stateless history. Preserve the required context when continuing a tool task or revising a result. Google also recommends keeping its default temperature of 1.0 rather than importing a low-temperature recipe that can cause loops or degraded behavior on complex tasks. These are producer integration practices, not new claims about any particular application’s transport.
The text model does not advertise image or audio generation or the Live API. The guide also distinguishes visual understanding from pixel-level image segmentation, which is not a supported Gemini 3 Flash capability. Use an appropriate final result for the actual task: source-linked observations, a structured record, a code change or a decision with its assumptions stated. Check arithmetic, verify code in the intended environment and review returned tool information. When recent facts matter, use the configured grounding sources or supplied current data instead of assuming that model knowledge is a live database.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits google/gemini-3-flash-preview | 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 $0.001 / 1K tokens Output · Output tokens $0.006 / 1K tokens Input · Cache read $0.0001 / 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 $0.001 / 1K tokens Output · Output tokens $0.006 / 1K tokens Input · Cache read $0.0001 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "google/gemini-3-flash-preview",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-flash-preview', '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-flash-preview', '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 Ultra gemini-3-flash-preview, google/gemini-3-flash-preview
/chat/completions
Technical example in English
Keep a sorting helper immutable\n\nFix this JavaScript helper so it returns users sorted by name without changing the input array: function sortedUsers(users) { return users.sort((a,b) => a.name.localeCompare(b.name)); }. Preserve each user object. Return the revised function and tests for alphabetical order, an empty array and the unchanged original array.A revised function and three small test examples covering sorting and non-mutation.Check that the returned array is a different array and the original sequence is unchanged after the call.