Gemini 2.5 Flash-Lite Preview 06-17 is Google's June preview edition of Flash-Lite, designed for frequent, latency-sensitive tasks such as classifying messages and summarizing material at scale. It belongs to the Gemini 2.5 thinking family while keeping a direct-response path for straightforward work. The dated Preview designation identifies this release separately from stable Flash-Lite and the later September preview, whose instruction-following and multimodal improvements have their own edition identity.
The June launch places classification and summarization at the centre of its intended use. A useful classification input contains the message, the allowed labels and examples of their boundaries; the output can be a label, a short reason and the information needed for the next processing step. A summarization task can specify decisions, action items, named deadlines and unresolved questions to retain. These are practical applications of the declared purpose: they give a repetitive operation a clear input and a compact result instead of asking for an open-ended essay.
Thinking is available but off by default in this June Flash-Lite preview. Google describes a controllable thinking budget that lets the task use additional reasoning when its conditions require it. Keep the direct path for simple categorization or shortening; use a reasoned task for overlapping categories, exceptions or a question requiring several dependent conclusions. Specify which conditions are mandatory and what constitutes a correct answer. Thinking is a task-processing capability; a longer explanation is not itself evidence that the conclusion is correct.
Google's technical report explicitly names this June model and documents multimodal input support and a context length of one million tokens. Its result is text. The context provides room for source material, instructions and examples within the same task. Give each document or section a clear role, then identify what the model should extract or compare. For a document assistant, separate the question from the source text and request a result tied to the relevant passages. For an extraction step, define the fields and how to represent information absent from the material. This is a context capability, not a promise that unrelated content will become useful merely by being included.
The June announcement lists native tools for search grounding, code execution and URL context, together with function calling. Search grounding adds web information to a response; URL context uses the contents of supplied pages for tasks such as comparing documents or extracting details. Google's code-execution tool generates and runs Python for calculations or text processing and uses the execution result in the answer. Function calling has a different role: the model selects a declared function and its arguments, while the connected application executes it and returns the result. Define the function's purpose and permitted parameters so a tool-assisted task has an explicit next action.
For a recurring workflow, prepare a small set of representative inputs before applying the same instruction to a larger collection. Include an ordinary case, an ambiguous case and a missing-information case. A customer-support example might ask for a topic, the customer's actual question and a reply grounded only in an accompanying reference passage. A correspondence example can request a list of tasks with an action, the person assigning it and a deadline only when it is stated. Keep these requested fields separate from any explanatory prose so the resulting text can be checked against the original item.
The manufacturer's Flash-Lite family card identifies possible factual invention and difficulties with causal understanding, complex logical deduction and counterfactual reasoning. It also notes that adherence to a thinking budget may be inconsistent. Treat those as concrete review points: compare extracted facts with the source, check dependent calculations and distinguish an observed statement from an inferred explanation. The useful finished artifact is a compact classification, summary, extraction or answer whose required facts and missing information can be inspected. This June edition is a separate text-processing choice; later preview specifications do not redefine its documented identity.
", "aboutText": "Gemini 2.5 Flash-Lite Preview 06-17 is Google's June preview edition of Flash-Lite, designed for frequent, latency-sensitive tasks such as classifying messages and summarizing material at scale. It belongs to the Gemini 2.5 thinking family while keeping a direct-response path for straightforward work. The dated Preview designation identifies this release separately from stable Flash-Lite and the later September preview, whose instruction-following and multimodal improvements have their own edition identity.\n\nThe June launch places classification and summarization at the centre of its intended use. A useful classification input contains the message, the allowed labels and examples of their boundaries; the output can be a label, a short reason and the information needed for the next processing step. A summarization task can specify decisions, action items, named deadlines and unresolved questions to retain. These are practical applications of the declared purpose: they give a repetitive operation a clear input and a compact result instead of asking for an open-ended essay.\n\nThinking is available but off by default in this June Flash-Lite preview. Google describes a controllable thinking budget that lets the task use additional reasoning when its conditions require it. Keep the direct path for simple categorization or shortening; use a reasoned task for overlapping categories, exceptions or a question requiring several dependent conclusions. Specify which conditions are mandatory and what constitutes a correct answer. Thinking is a task-processing capability; a longer explanation is not itself evidence that the conclusion is correct.\n\nGoogle's technical report explicitly names this June model and documents multimodal input support and a context length of one million tokens. Its result is text. The context provides room for source material, instructions and examples within the same task. Give each document or section a clear role, then identify what the model should extract or compare. For a document assistant, separate the question from the source text and request a result tied to the relevant passages. For an extraction step, define the fields and how to represent information absent from the material. This is a context capability, not a promise that unrelated content will become useful merely by being included.\n\nThe June announcement lists native tools for search grounding, code execution and URL context, together with function calling. Search grounding adds web information to a response; URL context uses the contents of supplied pages for tasks such as comparing documents or extracting details. Google's code-execution tool generates and runs Python for calculations or text processing and uses the execution result in the answer. Function calling has a different role: the model selects a declared function and its arguments, while the connected application executes it and returns the result. Define the function's purpose and permitted parameters so a tool-assisted task has an explicit next action.\n\nFor a recurring workflow, prepare a small set of representative inputs before applying the same instruction to a larger collection. Include an ordinary case, an ambiguous case and a missing-information case. A customer-support example might ask for a topic, the customer's actual question and a reply grounded only in an accompanying reference passage. A correspondence example can request a list of tasks with an action, the person assigning it and a deadline only when it is stated. Keep these requested fields separate from any explanatory prose so the resulting text can be checked against the original item.\n\nThe manufacturer's Flash-Lite family card identifies possible factual invention and difficulties with causal understanding, complex logical deduction and counterfactual reasoning. It also notes that adherence to a thinking budget may be inconsistent. Treat those as concrete review points: compare extracted facts with the source, check dependent calculations and distinguish an observed statement from an inferred explanation. The useful finished artifact is a compact classification, summary, extraction or answer whose required facts and missing information can be inspected. This June edition is a separate text-processing choice; later preview specifications do not redefine its documented identity.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Extract actions from a meeting note\n\nExtract only explicit action items from this note: 'Mira will send the revised price sheet by Friday. Jonas suggested checking packaging later, but nobody accepted that task. Noor will confirm the delivery address; no deadline was set.' Return a table with action, owner and deadline. Use 'not stated' for an absent deadline and exclude unassigned suggestions.A compact action table containing explicit commitments and source-grounded deadline values.The unassigned packaging suggestion is excluded, and Noor's deadline is not invented.gemini-2.5-flash-lite-preview-06-17Gemini 2.5 Flash-Lite Preview 06-17 is Google’s June edition for high-throughput classification, summarization and repeatable text processing. It combines a million-token context, optional thinking and documented search, code, URL-context and function-calling tools.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 2.5 Flash-Lite Preview 06-17 is Google's June preview edition of Flash-Lite, designed for frequent, latency-sensitive tasks such as classifying messages and summarizing material at scale. It belongs to the Gemini 2.5 thinking family while keeping a direct-response path for straightforward work. The dated Preview designation identifies this release separately from stable Flash-Lite and the later September preview, whose instruction-following and multimodal improvements have their own edition identity.
The June launch places classification and summarization at the centre of its intended use. A useful classification input contains the message, the allowed labels and examples of their boundaries; the output can be a label, a short reason and the information needed for the next processing step. A summarization task can specify decisions, action items, named deadlines and unresolved questions to retain. These are practical applications of the declared purpose: they give a repetitive operation a clear input and a compact result instead of asking for an open-ended essay.
Thinking is available but off by default in this June Flash-Lite preview. Google describes a controllable thinking budget that lets the task use additional reasoning when its conditions require it. Keep the direct path for simple categorization or shortening; use a reasoned task for overlapping categories, exceptions or a question requiring several dependent conclusions. Specify which conditions are mandatory and what constitutes a correct answer. Thinking is a task-processing capability; a longer explanation is not itself evidence that the conclusion is correct.
Google's technical report explicitly names this June model and documents multimodal input support and a context length of one million tokens. Its result is text. The context provides room for source material, instructions and examples within the same task. Give each document or section a clear role, then identify what the model should extract or compare. For a document assistant, separate the question from the source text and request a result tied to the relevant passages. For an extraction step, define the fields and how to represent information absent from the material. This is a context capability, not a promise that unrelated content will become useful merely by being included.
The June announcement lists native tools for search grounding, code execution and URL context, together with function calling. Search grounding adds web information to a response; URL context uses the contents of supplied pages for tasks such as comparing documents or extracting details. Google's code-execution tool generates and runs Python for calculations or text processing and uses the execution result in the answer. Function calling has a different role: the model selects a declared function and its arguments, while the connected application executes it and returns the result. Define the function's purpose and permitted parameters so a tool-assisted task has an explicit next action.
For a recurring workflow, prepare a small set of representative inputs before applying the same instruction to a larger collection. Include an ordinary case, an ambiguous case and a missing-information case. A customer-support example might ask for a topic, the customer's actual question and a reply grounded only in an accompanying reference passage. A correspondence example can request a list of tasks with an action, the person assigning it and a deadline only when it is stated. Keep these requested fields separate from any explanatory prose so the resulting text can be checked against the original item.
The manufacturer's Flash-Lite family card identifies possible factual invention and difficulties with causal understanding, complex logical deduction and counterfactual reasoning. It also notes that adherence to a thinking budget may be inconsistent. Treat those as concrete review points: compare extracted facts with the source, check dependent calculations and distinguish an observed statement from an inferred explanation. The useful finished artifact is a compact classification, summary, extraction or answer whose required facts and missing information can be inspected. This June edition is a separate text-processing choice; later preview specifications do not redefine its documented identity.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gemini-2.5-flash-lite-preview-06-17 | 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.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.0002 / 1K tokens Output · Output tokens $0.0008 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "gemini-2.5-flash-lite-preview-06-17", "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='gemini-2.5-flash-lite-preview-06-17',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='gemini-2.5-flash-lite-preview-06-17',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-2.5-flash-lite-preview-06-17
Use the method paths shown above.
gemini-2.5-flash-lite-preview-06-17Gemini 2.5 Flash-Lite Preview 06-17 is Google’s June edition for high-throughput classification, summarization and repeatable text processing. It combines a million-token context, optional thinking and documented search, code, URL-context and function-calling tools.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 2.5 Flash-Lite Preview 06-17 is Google's June preview edition of Flash-Lite, designed for frequent, latency-sensitive tasks such as classifying messages and summarizing material at scale. It belongs to the Gemini 2.5 thinking family while keeping a direct-response path for straightforward work. The dated Preview designation identifies this release separately from stable Flash-Lite and the later September preview, whose instruction-following and multimodal improvements have their own edition identity.
The June launch places classification and summarization at the centre of its intended use. A useful classification input contains the message, the allowed labels and examples of their boundaries; the output can be a label, a short reason and the information needed for the next processing step. A summarization task can specify decisions, action items, named deadlines and unresolved questions to retain. These are practical applications of the declared purpose: they give a repetitive operation a clear input and a compact result instead of asking for an open-ended essay.
Thinking is available but off by default in this June Flash-Lite preview. Google describes a controllable thinking budget that lets the task use additional reasoning when its conditions require it. Keep the direct path for simple categorization or shortening; use a reasoned task for overlapping categories, exceptions or a question requiring several dependent conclusions. Specify which conditions are mandatory and what constitutes a correct answer. Thinking is a task-processing capability; a longer explanation is not itself evidence that the conclusion is correct.
Google's technical report explicitly names this June model and documents multimodal input support and a context length of one million tokens. Its result is text. The context provides room for source material, instructions and examples within the same task. Give each document or section a clear role, then identify what the model should extract or compare. For a document assistant, separate the question from the source text and request a result tied to the relevant passages. For an extraction step, define the fields and how to represent information absent from the material. This is a context capability, not a promise that unrelated content will become useful merely by being included.
The June announcement lists native tools for search grounding, code execution and URL context, together with function calling. Search grounding adds web information to a response; URL context uses the contents of supplied pages for tasks such as comparing documents or extracting details. Google's code-execution tool generates and runs Python for calculations or text processing and uses the execution result in the answer. Function calling has a different role: the model selects a declared function and its arguments, while the connected application executes it and returns the result. Define the function's purpose and permitted parameters so a tool-assisted task has an explicit next action.
For a recurring workflow, prepare a small set of representative inputs before applying the same instruction to a larger collection. Include an ordinary case, an ambiguous case and a missing-information case. A customer-support example might ask for a topic, the customer's actual question and a reply grounded only in an accompanying reference passage. A correspondence example can request a list of tasks with an action, the person assigning it and a deadline only when it is stated. Keep these requested fields separate from any explanatory prose so the resulting text can be checked against the original item.
The manufacturer's Flash-Lite family card identifies possible factual invention and difficulties with causal understanding, complex logical deduction and counterfactual reasoning. It also notes that adherence to a thinking budget may be inconsistent. Treat those as concrete review points: compare extracted facts with the source, check dependent calculations and distinguish an observed statement from an inferred explanation. The useful finished artifact is a compact classification, summary, extraction or answer whose required facts and missing information can be inspected. This June edition is a separate text-processing choice; later preview specifications do not redefine its documented identity.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gemini-2.5-flash-lite-preview-06-17 | 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.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.0002 / 1K tokens Output · Output tokens $0.0008 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "gemini-2.5-flash-lite-preview-06-17",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-2.5-flash-lite-preview-06-17', '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-2.5-flash-lite-preview-06-17', '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-2.5-flash-lite-preview-06-17
Use the method paths shown above.
Technical example in English
Extract actions from a meeting note\n\nExtract only explicit action items from this note: 'Mira will send the revised price sheet by Friday. Jonas suggested checking packaging later, but nobody accepted that task. Noor will confirm the delivery address; no deadline was set.' Return a table with action, owner and deadline. Use 'not stated' for an absent deadline and exclude unassigned suggestions.A compact action table containing explicit commitments and source-grounded deadline values.The unassigned packaging suggestion is excluded, and Noor's deadline is not invented.