Gemini 3.1 Flash-Lite Preview is the preview edition of Google’s lightweight Gemini 3.1 Flash-Lite line. Its design focuses on high-frequency tasks with clear instructions: translation, transcription, classification, document summaries and simple data extraction. It accepts text, images, video, audio and PDF and returns text. A useful task specifies one operation and one final form, such as a translated message, a transcript or a record containing the fields an application needs.
The exact preview documentation lists an input limit of 1,048,576 tokens and an output limit of 65,536 tokens. These are separate producer limits. The source material, instructions and conversation history contribute to the input, while the required result must fit the output budget. For a large collection of messages or pages, retain identifiers and ask for a matching output identifier for every processed item. A large window does not replace a clear extraction rule or make an ambiguous field definition precise.
The model card includes thinking, structured outputs and function calling. It also lists code execution, file search, search grounding, Google Maps grounding, URL context and caching as producer capabilities. This is a text-output model; audio or image input does not imply generated speech or artwork. A calling application still selects the available tools, executes accepted function requests and returns their results. Keep a proposed action distinguishable from an action confirmed by the application.
For translation, provide the source message, target language, audience and terminology to preserve. The developer guide shows constraining the answer to translated text without extra commentary. A support-message workflow can keep product names and order references unchanged while producing a natural reply in the reader’s language. If the source is ambiguous, define whether to preserve that ambiguity or return a separate question for clarification instead of adding an invented detail to the translation.
For transcription, provide the audio together with the requested result: verbatim text, a cleaned transcript or a summary. These are different tasks. Identify the relevant interval if a long recording contains only a short exchange needed for the result. For a PDF, ask a definite question or define the fields to extract, preserving page or section references where the answer should be checked. For a visual source, indicate the object, label or region relevant to the request.
For classification and entity extraction, define the categories, required fields and handling of missing values. The maker’s guide demonstrates schema-constrained JSON for extracting review information. An original example is to classify a support ticket and return the mentioned product, issue category and source sentence that supports the choice. Give a small set of representative examples, including a case that should remain unknown. Validate the returned record and distinguish a syntactically valid value from one actually supported by the source.
The launch material describes adjustable thinking levels, letting the task use more analysis when its conditions require it. A short language conversion and a classification with several exceptions can use different reasoning settings. The developer guide also presents model routing as a classification task: the model identifies the complexity of a request and returns a selected category. The surrounding application, rather than the classifier itself, decides what to run next. Supply the actual routing criteria and the allowed choices so the output has an operational meaning.
For repeatable processing, retain this exact Preview identifier, the input version and the requested schema or output format. Check a pilot result on the same class of real material before processing a larger set. Compare extracted fields with the original message, review transcripts against the recording and confirm that translated terms remain intact. The practical advantage of this profile is focused multimodal text processing with a defined result; fluent text or a tool suggestion does not by itself establish factual correctness or completed external execution.
", "aboutText": "Gemini 3.1 Flash-Lite Preview is the preview edition of Google’s lightweight Gemini 3.1 Flash-Lite line. Its design focuses on high-frequency tasks with clear instructions: translation, transcription, classification, document summaries and simple data extraction. It accepts text, images, video, audio and PDF and returns text. A useful task specifies one operation and one final form, such as a translated message, a transcript or a record containing the fields an application needs.\n\nThe exact preview documentation lists an input limit of 1,048,576 tokens and an output limit of 65,536 tokens. These are separate producer limits. The source material, instructions and conversation history contribute to the input, while the required result must fit the output budget. For a large collection of messages or pages, retain identifiers and ask for a matching output identifier for every processed item. A large window does not replace a clear extraction rule or make an ambiguous field definition precise.\n\nThe model card includes thinking, structured outputs and function calling. It also lists code execution, file search, search grounding, Google Maps grounding, URL context and caching as producer capabilities. This is a text-output model; audio or image input does not imply generated speech or artwork. A calling application still selects the available tools, executes accepted function requests and returns their results. Keep a proposed action distinguishable from an action confirmed by the application.\n\nFor translation, provide the source message, target language, audience and terminology to preserve. The developer guide shows constraining the answer to translated text without extra commentary. A support-message workflow can keep product names and order references unchanged while producing a natural reply in the reader’s language. If the source is ambiguous, define whether to preserve that ambiguity or return a separate question for clarification instead of adding an invented detail to the translation.\n\nFor transcription, provide the audio together with the requested result: verbatim text, a cleaned transcript or a summary. These are different tasks. Identify the relevant interval if a long recording contains only a short exchange needed for the result. For a PDF, ask a definite question or define the fields to extract, preserving page or section references where the answer should be checked. For a visual source, indicate the object, label or region relevant to the request.\n\nFor classification and entity extraction, define the categories, required fields and handling of missing values. The maker’s guide demonstrates schema-constrained JSON for extracting review information. An original example is to classify a support ticket and return the mentioned product, issue category and source sentence that supports the choice. Give a small set of representative examples, including a case that should remain unknown. Validate the returned record and distinguish a syntactically valid value from one actually supported by the source.\n\nThe launch material describes adjustable thinking levels, letting the task use more analysis when its conditions require it. A short language conversion and a classification with several exceptions can use different reasoning settings. The developer guide also presents model routing as a classification task: the model identifies the complexity of a request and returns a selected category. The surrounding application, rather than the classifier itself, decides what to run next. Supply the actual routing criteria and the allowed choices so the output has an operational meaning.\n\nFor repeatable processing, retain this exact Preview identifier, the input version and the requested schema or output format. Check a pilot result on the same class of real material before processing a larger set. Compare extracted fields with the original message, review transcripts against the recording and confirm that translated terms remain intact. The practical advantage of this profile is focused multimodal text processing with a defined result; fluent text or a tool suggestion does not by itself establish factual correctness or completed external execution.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Translate a support message without additions\n\nTranslate this customer-service message into English for a customer. Preserve order reference K-204 and product name Orbit Mini exactly: 'Votre commande K-204 contenant Orbit Mini est prête à être retirée. Merci de présenter une pièce d’identité.' Return only the translation; do not add a collection address or deadline.Only the English translation, retaining the two exact identifiers and the identity-document requirement.K-204 and Orbit Mini remain unchanged, with no invented address, deadline or additional policy.gemini-3.1-flash-lite-previewGemini 3.1 Flash-Lite Preview is a multimodal text model for repeated, well-defined tasks such as translation, transcription, classification and data extraction. Thinking and structured-output capabilities help turn supplied material into a concise result that an application can use.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 3.1 Flash-Lite Preview is the preview edition of Google’s lightweight Gemini 3.1 Flash-Lite line. Its design focuses on high-frequency tasks with clear instructions: translation, transcription, classification, document summaries and simple data extraction. It accepts text, images, video, audio and PDF and returns text. A useful task specifies one operation and one final form, such as a translated message, a transcript or a record containing the fields an application needs.
The exact preview documentation lists an input limit of 1,048,576 tokens and an output limit of 65,536 tokens. These are separate producer limits. The source material, instructions and conversation history contribute to the input, while the required result must fit the output budget. For a large collection of messages or pages, retain identifiers and ask for a matching output identifier for every processed item. A large window does not replace a clear extraction rule or make an ambiguous field definition precise.
The model card includes thinking, structured outputs and function calling. It also lists code execution, file search, search grounding, Google Maps grounding, URL context and caching as producer capabilities. This is a text-output model; audio or image input does not imply generated speech or artwork. A calling application still selects the available tools, executes accepted function requests and returns their results. Keep a proposed action distinguishable from an action confirmed by the application.
For translation, provide the source message, target language, audience and terminology to preserve. The developer guide shows constraining the answer to translated text without extra commentary. A support-message workflow can keep product names and order references unchanged while producing a natural reply in the reader’s language. If the source is ambiguous, define whether to preserve that ambiguity or return a separate question for clarification instead of adding an invented detail to the translation.
For transcription, provide the audio together with the requested result: verbatim text, a cleaned transcript or a summary. These are different tasks. Identify the relevant interval if a long recording contains only a short exchange needed for the result. For a PDF, ask a definite question or define the fields to extract, preserving page or section references where the answer should be checked. For a visual source, indicate the object, label or region relevant to the request.
For classification and entity extraction, define the categories, required fields and handling of missing values. The maker’s guide demonstrates schema-constrained JSON for extracting review information. An original example is to classify a support ticket and return the mentioned product, issue category and source sentence that supports the choice. Give a small set of representative examples, including a case that should remain unknown. Validate the returned record and distinguish a syntactically valid value from one actually supported by the source.
The launch material describes adjustable thinking levels, letting the task use more analysis when its conditions require it. A short language conversion and a classification with several exceptions can use different reasoning settings. The developer guide also presents model routing as a classification task: the model identifies the complexity of a request and returns a selected category. The surrounding application, rather than the classifier itself, decides what to run next. Supply the actual routing criteria and the allowed choices so the output has an operational meaning.
For repeatable processing, retain this exact Preview identifier, the input version and the requested schema or output format. Check a pilot result on the same class of real material before processing a larger set. Compare extracted fields with the original message, review transcripts against the recording and confirm that translated terms remain intact. The practical advantage of this profile is focused multimodal text processing with a defined result; fluent text or a tool suggestion does not by itself establish factual correctness or completed external execution.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gemini-3.1-flash-lite-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 $0.0005 / 1K tokens Output · Output tokens $0.003 / 1K tokens Input · Cache read $0.00005 / 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 $0.0005 / 1K tokens Output · Output tokens $0.003 / 1K tokens Input · Cache read $0.00005 / 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-3.1-flash-lite-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-3.1-flash-lite-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-3.1-flash-lite-preview, google/gemini-3.1-flash-lite-preview
/chat/completions
google/gemini-3.1-flash-lite-preview, gemini-3.1-flash-lite-preview
gemini-3.1-flash-lite-previewGemini 3.1 Flash-Lite Preview is a multimodal text model for repeated, well-defined tasks such as translation, transcription, classification and data extraction. Thinking and structured-output capabilities help turn supplied material into a concise result that an application can use.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 3.1 Flash-Lite Preview is the preview edition of Google’s lightweight Gemini 3.1 Flash-Lite line. Its design focuses on high-frequency tasks with clear instructions: translation, transcription, classification, document summaries and simple data extraction. It accepts text, images, video, audio and PDF and returns text. A useful task specifies one operation and one final form, such as a translated message, a transcript or a record containing the fields an application needs.
The exact preview documentation lists an input limit of 1,048,576 tokens and an output limit of 65,536 tokens. These are separate producer limits. The source material, instructions and conversation history contribute to the input, while the required result must fit the output budget. For a large collection of messages or pages, retain identifiers and ask for a matching output identifier for every processed item. A large window does not replace a clear extraction rule or make an ambiguous field definition precise.
The model card includes thinking, structured outputs and function calling. It also lists code execution, file search, search grounding, Google Maps grounding, URL context and caching as producer capabilities. This is a text-output model; audio or image input does not imply generated speech or artwork. A calling application still selects the available tools, executes accepted function requests and returns their results. Keep a proposed action distinguishable from an action confirmed by the application.
For translation, provide the source message, target language, audience and terminology to preserve. The developer guide shows constraining the answer to translated text without extra commentary. A support-message workflow can keep product names and order references unchanged while producing a natural reply in the reader’s language. If the source is ambiguous, define whether to preserve that ambiguity or return a separate question for clarification instead of adding an invented detail to the translation.
For transcription, provide the audio together with the requested result: verbatim text, a cleaned transcript or a summary. These are different tasks. Identify the relevant interval if a long recording contains only a short exchange needed for the result. For a PDF, ask a definite question or define the fields to extract, preserving page or section references where the answer should be checked. For a visual source, indicate the object, label or region relevant to the request.
For classification and entity extraction, define the categories, required fields and handling of missing values. The maker’s guide demonstrates schema-constrained JSON for extracting review information. An original example is to classify a support ticket and return the mentioned product, issue category and source sentence that supports the choice. Give a small set of representative examples, including a case that should remain unknown. Validate the returned record and distinguish a syntactically valid value from one actually supported by the source.
The launch material describes adjustable thinking levels, letting the task use more analysis when its conditions require it. A short language conversion and a classification with several exceptions can use different reasoning settings. The developer guide also presents model routing as a classification task: the model identifies the complexity of a request and returns a selected category. The surrounding application, rather than the classifier itself, decides what to run next. Supply the actual routing criteria and the allowed choices so the output has an operational meaning.
For repeatable processing, retain this exact Preview identifier, the input version and the requested schema or output format. Check a pilot result on the same class of real material before processing a larger set. Compare extracted fields with the original message, review transcripts against the recording and confirm that translated terms remain intact. The practical advantage of this profile is focused multimodal text processing with a defined result; fluent text or a tool suggestion does not by itself establish factual correctness or completed external execution.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gemini-3.1-flash-lite-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 $0.0005 / 1K tokens Output · Output tokens $0.003 / 1K tokens Input · Cache read $0.00005 / 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 $0.0005 / 1K tokens Output · Output tokens $0.003 / 1K tokens Input · Cache read $0.00005 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "gemini-3.1-flash-lite-preview",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-3.1-flash-lite-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-3.1-flash-lite-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-3.1-flash-lite-preview, google/gemini-3.1-flash-lite-preview
/chat/completions
google/gemini-3.1-flash-lite-preview, gemini-3.1-flash-lite-preview
google/gemini-3.1-flash-lite-previewGemini 3.1 Flash-Lite Preview is a multimodal text model for repeated, well-defined tasks such as translation, transcription, classification and data extraction. Thinking and structured-output capabilities help turn supplied material into a concise result that an application can use.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 3.1 Flash-Lite Preview is the preview edition of Google’s lightweight Gemini 3.1 Flash-Lite line. Its design focuses on high-frequency tasks with clear instructions: translation, transcription, classification, document summaries and simple data extraction. It accepts text, images, video, audio and PDF and returns text. A useful task specifies one operation and one final form, such as a translated message, a transcript or a record containing the fields an application needs.
The exact preview documentation lists an input limit of 1,048,576 tokens and an output limit of 65,536 tokens. These are separate producer limits. The source material, instructions and conversation history contribute to the input, while the required result must fit the output budget. For a large collection of messages or pages, retain identifiers and ask for a matching output identifier for every processed item. A large window does not replace a clear extraction rule or make an ambiguous field definition precise.
The model card includes thinking, structured outputs and function calling. It also lists code execution, file search, search grounding, Google Maps grounding, URL context and caching as producer capabilities. This is a text-output model; audio or image input does not imply generated speech or artwork. A calling application still selects the available tools, executes accepted function requests and returns their results. Keep a proposed action distinguishable from an action confirmed by the application.
For translation, provide the source message, target language, audience and terminology to preserve. The developer guide shows constraining the answer to translated text without extra commentary. A support-message workflow can keep product names and order references unchanged while producing a natural reply in the reader’s language. If the source is ambiguous, define whether to preserve that ambiguity or return a separate question for clarification instead of adding an invented detail to the translation.
For transcription, provide the audio together with the requested result: verbatim text, a cleaned transcript or a summary. These are different tasks. Identify the relevant interval if a long recording contains only a short exchange needed for the result. For a PDF, ask a definite question or define the fields to extract, preserving page or section references where the answer should be checked. For a visual source, indicate the object, label or region relevant to the request.
For classification and entity extraction, define the categories, required fields and handling of missing values. The maker’s guide demonstrates schema-constrained JSON for extracting review information. An original example is to classify a support ticket and return the mentioned product, issue category and source sentence that supports the choice. Give a small set of representative examples, including a case that should remain unknown. Validate the returned record and distinguish a syntactically valid value from one actually supported by the source.
The launch material describes adjustable thinking levels, letting the task use more analysis when its conditions require it. A short language conversion and a classification with several exceptions can use different reasoning settings. The developer guide also presents model routing as a classification task: the model identifies the complexity of a request and returns a selected category. The surrounding application, rather than the classifier itself, decides what to run next. Supply the actual routing criteria and the allowed choices so the output has an operational meaning.
For repeatable processing, retain this exact Preview identifier, the input version and the requested schema or output format. Check a pilot result on the same class of real material before processing a larger set. Compare extracted fields with the original message, review transcripts against the recording and confirm that translated terms remain intact. The practical advantage of this profile is focused multimodal text processing with a defined result; fluent text or a tool suggestion does not by itself establish factual correctness or completed external execution.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits google/gemini-3.1-flash-lite-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 $0.0005 / 1K tokens Output · Output tokens $0.003 / 1K tokens Input · Cache read $0.00005 / 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 $0.0005 / 1K tokens Output · Output tokens $0.003 / 1K tokens Input · Cache read $0.00005 / 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-3.1-flash-lite-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-3.1-flash-lite-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-3.1-flash-lite-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-3.1-flash-lite-preview, google/gemini-3.1-flash-lite-preview
/chat/completions
google/gemini-3.1-flash-lite-preview, gemini-3.1-flash-lite-preview
google/gemini-3.1-flash-lite-previewGemini 3.1 Flash-Lite Preview is a multimodal text model for repeated, well-defined tasks such as translation, transcription, classification and data extraction. Thinking and structured-output capabilities help turn supplied material into a concise result that an application can use.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 3.1 Flash-Lite Preview is the preview edition of Google’s lightweight Gemini 3.1 Flash-Lite line. Its design focuses on high-frequency tasks with clear instructions: translation, transcription, classification, document summaries and simple data extraction. It accepts text, images, video, audio and PDF and returns text. A useful task specifies one operation and one final form, such as a translated message, a transcript or a record containing the fields an application needs.
The exact preview documentation lists an input limit of 1,048,576 tokens and an output limit of 65,536 tokens. These are separate producer limits. The source material, instructions and conversation history contribute to the input, while the required result must fit the output budget. For a large collection of messages or pages, retain identifiers and ask for a matching output identifier for every processed item. A large window does not replace a clear extraction rule or make an ambiguous field definition precise.
The model card includes thinking, structured outputs and function calling. It also lists code execution, file search, search grounding, Google Maps grounding, URL context and caching as producer capabilities. This is a text-output model; audio or image input does not imply generated speech or artwork. A calling application still selects the available tools, executes accepted function requests and returns their results. Keep a proposed action distinguishable from an action confirmed by the application.
For translation, provide the source message, target language, audience and terminology to preserve. The developer guide shows constraining the answer to translated text without extra commentary. A support-message workflow can keep product names and order references unchanged while producing a natural reply in the reader’s language. If the source is ambiguous, define whether to preserve that ambiguity or return a separate question for clarification instead of adding an invented detail to the translation.
For transcription, provide the audio together with the requested result: verbatim text, a cleaned transcript or a summary. These are different tasks. Identify the relevant interval if a long recording contains only a short exchange needed for the result. For a PDF, ask a definite question or define the fields to extract, preserving page or section references where the answer should be checked. For a visual source, indicate the object, label or region relevant to the request.
For classification and entity extraction, define the categories, required fields and handling of missing values. The maker’s guide demonstrates schema-constrained JSON for extracting review information. An original example is to classify a support ticket and return the mentioned product, issue category and source sentence that supports the choice. Give a small set of representative examples, including a case that should remain unknown. Validate the returned record and distinguish a syntactically valid value from one actually supported by the source.
The launch material describes adjustable thinking levels, letting the task use more analysis when its conditions require it. A short language conversion and a classification with several exceptions can use different reasoning settings. The developer guide also presents model routing as a classification task: the model identifies the complexity of a request and returns a selected category. The surrounding application, rather than the classifier itself, decides what to run next. Supply the actual routing criteria and the allowed choices so the output has an operational meaning.
For repeatable processing, retain this exact Preview identifier, the input version and the requested schema or output format. Check a pilot result on the same class of real material before processing a larger set. Compare extracted fields with the original message, review transcripts against the recording and confirm that translated terms remain intact. The practical advantage of this profile is focused multimodal text processing with a defined result; fluent text or a tool suggestion does not by itself establish factual correctness or completed external execution.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits google/gemini-3.1-flash-lite-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 $0.0005 / 1K tokens Output · Output tokens $0.003 / 1K tokens Input · Cache read $0.00005 / 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 $0.0005 / 1K tokens Output · Output tokens $0.003 / 1K tokens Input · Cache read $0.00005 / 1K tokens Input · Cache write $0.0001666666666666666 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "google/gemini-3.1-flash-lite-preview",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-3.1-flash-lite-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-3.1-flash-lite-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-3.1-flash-lite-preview, google/gemini-3.1-flash-lite-preview
/chat/completions
google/gemini-3.1-flash-lite-preview, gemini-3.1-flash-lite-preview
Technical example in English
Translate a support message without additions\n\nTranslate this customer-service message into English for a customer. Preserve order reference K-204 and product name Orbit Mini exactly: 'Votre commande K-204 contenant Orbit Mini est prête à être retirée. Merci de présenter une pièce d’identité.' Return only the translation; do not add a collection address or deadline.Only the English translation, retaining the two exact identifiers and the identity-document requirement.K-204 and Orbit Mini remain unchanged, with no invented address, deadline or additional policy.