Gemini 3.1 Flash-Lite is Google’s stable lightweight multimodal text model for frequent, well-defined tasks. It is based on Gemini 3 Pro. Translation and classification are central workloads; other useful tasks include transcription, document summaries, entity extraction and model-choice classification. Text, images, audio, video and PDF can supply the source material, and the result is text. A useful brief asks for one operation and one final form, such as a translated message or a record of fields found in a document.
For translation, provide the source text, target language, audience and terminology that should remain intact. Google’s example uses instructions that return only the translation. For a support-message translation, preserve product names and order references while translating the rest naturally. Specify how ambiguity should be handled so the result does not add a date, promise or detail missing from the source. Keep the requested form appropriate to the destination, such as a short reply or a labelled translation record.
For transcription, supply the recording and define whether the answer should be spoken words, a readable edited transcript or a summary. These are different outputs. Identify the relevant interval when a long recording contains only one passage needed for the task. The maker’s developer example passes audio directly and requests a text transcript. Check names, numbers and unclear passages against the recording, retaining the original source for review. This general multimodal text profile does not itself imply an audio-output or dedicated speaker-diarization result.
For classification or extraction, define the categories, schema and missing-value rule. The developer guide shows structured JSON for analysing a customer review, with a supporting quotation and defined fields. A structured record can contain the mentioned product, issue category and sentence that justifies the choice. Include a representative case that should stay unknown rather than be forced into a category. A syntactically valid record still needs comparison with the actual source text.
Document processing can turn a PDF into a concise summary or a field record. State the question and preserve page or section references where the finding needs checking. A table review should specify the columns and rule that matter; a visual task should identify the label or region needed for the answer. Model routing is another documented use: the model classifies a request’s complexity and returns an allowed choice. The connected application, rather than the classification text itself, decides what to run next.
Thinking is supported, and the maker shows higher effort for tasks that benefit from more analysis. The exact stable page also lists function calling, code execution, file search, search grounding, Maps grounding, URL context and structured output. Computer Use is not supported in this stable 3.1 profile; the later 3.5 Flash-Lite profile has a different capability table. Define tool purposes and parameters clearly and continue from real returned results. A function suggestion does not establish that the operation has taken place.
The native model card lists up to 1M context and 64K text output; the stable API table specifies 1,048,576 input tokens and 65,536 output tokens. Include the instructions, conversation and source media in the input preparation, and request an output sized for the intended artifact. Caching, batch, Flex and Priority processing are documented for this producer profile. For repeated independent items, carry the input identifier into the result and retain a consistent schema so a missing answer can be identified.
This stable model identifier is distinct from Gemini 3.1 Flash-Lite Preview and later Flash-Lite editions. Preserve the exact edition when preparing repeated processing rather than treating a familiar family name as a fixed revision guarantee. Review translations for retained meaning and terms, transcripts against the audio and extracted fields against the document. The profile’s practical role is focused multimodal text processing with a clear result, leaving a broader task’s reasoning or external actions to the appropriate subsequent step.
", "aboutText": "Gemini 3.1 Flash-Lite is Google’s stable lightweight multimodal text model for frequent, well-defined tasks. It is based on Gemini 3 Pro. Translation and classification are central workloads; other useful tasks include transcription, document summaries, entity extraction and model-choice classification. Text, images, audio, video and PDF can supply the source material, and the result is text. A useful brief asks for one operation and one final form, such as a translated message or a record of fields found in a document.\n\nFor translation, provide the source text, target language, audience and terminology that should remain intact. Google’s example uses instructions that return only the translation. For a support-message translation, preserve product names and order references while translating the rest naturally. Specify how ambiguity should be handled so the result does not add a date, promise or detail missing from the source. Keep the requested form appropriate to the destination, such as a short reply or a labelled translation record.\n\nFor transcription, supply the recording and define whether the answer should be spoken words, a readable edited transcript or a summary. These are different outputs. Identify the relevant interval when a long recording contains only one passage needed for the task. The maker’s developer example passes audio directly and requests a text transcript. Check names, numbers and unclear passages against the recording, retaining the original source for review. This general multimodal text profile does not itself imply an audio-output or dedicated speaker-diarization result.\n\nFor classification or extraction, define the categories, schema and missing-value rule. The developer guide shows structured JSON for analysing a customer review, with a supporting quotation and defined fields. A structured record can contain the mentioned product, issue category and sentence that justifies the choice. Include a representative case that should stay unknown rather than be forced into a category. A syntactically valid record still needs comparison with the actual source text.\n\nDocument processing can turn a PDF into a concise summary or a field record. State the question and preserve page or section references where the finding needs checking. A table review should specify the columns and rule that matter; a visual task should identify the label or region needed for the answer. Model routing is another documented use: the model classifies a request’s complexity and returns an allowed choice. The connected application, rather than the classification text itself, decides what to run next.\n\nThinking is supported, and the maker shows higher effort for tasks that benefit from more analysis. The exact stable page also lists function calling, code execution, file search, search grounding, Maps grounding, URL context and structured output. Computer Use is not supported in this stable 3.1 profile; the later 3.5 Flash-Lite profile has a different capability table. Define tool purposes and parameters clearly and continue from real returned results. A function suggestion does not establish that the operation has taken place.\n\nThe native model card lists up to 1M context and 64K text output; the stable API table specifies 1,048,576 input tokens and 65,536 output tokens. Include the instructions, conversation and source media in the input preparation, and request an output sized for the intended artifact. Caching, batch, Flex and Priority processing are documented for this producer profile. For repeated independent items, carry the input identifier into the result and retain a consistent schema so a missing answer can be identified.\n\nThis stable model identifier is distinct from Gemini 3.1 Flash-Lite Preview and later Flash-Lite editions. Preserve the exact edition when preparing repeated processing rather than treating a familiar family name as a fixed revision guarantee. Review translations for retained meaning and terms, transcripts against the audio and extracted fields against the document. The profile’s practical role is focused multimodal text processing with a clear result, leaving a broader task’s reasoning or external actions to the appropriate subsequent step.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "15fff4eeab95c140ff3efeebf8c2f0837263771ba84d483616de1179596d4765", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "google/gemini-3.1-flash-lite:batchGemini 3.1 Flash-Lite is Google’s stable multimodal model for translation, transcription, classification and simple extraction at scale. It accepts text, images, audio, video and PDF and returns text, with thinking, tools and structured output. Its exact input/output limits are 1,048,576/65,536 tokens.
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 is Google’s stable lightweight multimodal text model for frequent, well-defined tasks. It is based on Gemini 3 Pro. Translation and classification are central workloads; other useful tasks include transcription, document summaries, entity extraction and model-choice classification. Text, images, audio, video and PDF can supply the source material, and the result is text. A useful brief asks for one operation and one final form, such as a translated message or a record of fields found in a document.
For translation, provide the source text, target language, audience and terminology that should remain intact. Google’s example uses instructions that return only the translation. For a support-message translation, preserve product names and order references while translating the rest naturally. Specify how ambiguity should be handled so the result does not add a date, promise or detail missing from the source. Keep the requested form appropriate to the destination, such as a short reply or a labelled translation record.
For transcription, supply the recording and define whether the answer should be spoken words, a readable edited transcript or a summary. These are different outputs. Identify the relevant interval when a long recording contains only one passage needed for the task. The maker’s developer example passes audio directly and requests a text transcript. Check names, numbers and unclear passages against the recording, retaining the original source for review. This general multimodal text profile does not itself imply an audio-output or dedicated speaker-diarization result.
For classification or extraction, define the categories, schema and missing-value rule. The developer guide shows structured JSON for analysing a customer review, with a supporting quotation and defined fields. A structured record can contain the mentioned product, issue category and sentence that justifies the choice. Include a representative case that should stay unknown rather than be forced into a category. A syntactically valid record still needs comparison with the actual source text.
Document processing can turn a PDF into a concise summary or a field record. State the question and preserve page or section references where the finding needs checking. A table review should specify the columns and rule that matter; a visual task should identify the label or region needed for the answer. Model routing is another documented use: the model classifies a request’s complexity and returns an allowed choice. The connected application, rather than the classification text itself, decides what to run next.
Thinking is supported, and the maker shows higher effort for tasks that benefit from more analysis. The exact stable page also lists function calling, code execution, file search, search grounding, Maps grounding, URL context and structured output. Computer Use is not supported in this stable 3.1 profile; the later 3.5 Flash-Lite profile has a different capability table. Define tool purposes and parameters clearly and continue from real returned results. A function suggestion does not establish that the operation has taken place.
The native model card lists up to 1M context and 64K text output; the stable API table specifies 1,048,576 input tokens and 65,536 output tokens. Include the instructions, conversation and source media in the input preparation, and request an output sized for the intended artifact. Caching, batch, Flex and Priority processing are documented for this producer profile. For repeated independent items, carry the input identifier into the result and retain a consistent schema so a missing answer can be identified.
This stable model identifier is distinct from Gemini 3.1 Flash-Lite Preview and later Flash-Lite editions. Preserve the exact edition when preparing repeated processing rather than treating a familiar family name as a fixed revision guarantee. Review translations for retained meaning and terms, transcripts against the audio and extracted fields against the document. The profile’s practical role is focused multimodal text processing with a clear result, leaving a broader task’s reasoning or external actions to the appropriate subsequent step.
POST /v1/batchestexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldendpoint | Typestring | RequirementRequired | Values & limits /v1/chat/completions | Default— |
Fieldmodel | Typestring | RequirementRequired | Values & limits google/gemini-3.1-flash-lite:batch | Default— |
Fieldrequests | Typebatch_item[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldrequests[].custom_id | Typestring | RequirementRequired | Values & limits | Default— |
Fieldrequests[].body.messages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldcompletion_window | Typestring | RequirementOptional | Values & limits 24h | Default— |
Fieldprovider | Typeobject|null | RequirementOptional | Values & limits | Default— |
Fieldrequests[].body.model | Typestring | RequirementOptional | Values & limits google/gemini-3.1-flash-lite:batch, google/gemini-3.1-flash-lite | Default— |
Fieldprovider.only | Typestring[] | RequirementOptional | Values & limits google-vertex/global | Default— |
Fieldprovider.allow_fallbacks | Typeboolean|null | RequirementOptional | Values & limits false, null | Default— |
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractendpoint, model, requests |
Parametermaterial_types | Contracttext |
Parameterrepresentation | Contractinline requests[]; each item has custom_id and body |
Parameterrequest_endpoint_profile | Contract/v1/chat/completions |
Parameterfile_material | ContractCaller may read actual UTF-8 JSONL locally into requests[]. No upload purpose, input_file_id or file reference is used. Missing/empty customer material stops preparation before POST. |
Parameterserialization_order | Contractendpoint, model, provider (if supplied), completion_window (if supplied), requests last |
Parameteroptional_controls | Contractprovider.only, provider.allow_fallbacks, completion_window |
Parameterschema_scope | ContractText Chat Completions bodies in the documented inline Batch envelope. |
Lifecycle: asynchronous
GET /v1/batches/{operation_id} · actual original create response.id; same user/key/group
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 $0.00025 / 1K tokens Output · Output tokens $0.0015 / 1K tokens Input · Cache read $0.000025 / 1K tokens Input · Cache write — / 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 $0.00025 / 1K tokens Output · Output tokens $0.0015 / 1K tokens Input · Cache read $0.000025 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json\nfrom pathlib import Path\nbody=json.loads('{"endpoint":"/v1/chat/completions","model":"google/gemini-3.1-flash-lite:batch","requests":[{"custom_id":"req-0001","body":{"messages":[{"role":"user","content":"Hello!"}],"max_tokens":16}}]}')\nPath("batch-request.json").write_text(json.dumps(body,ensure_ascii=False),encoding="utf-8")\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/batches \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @batch-request.json -D batch-response-headers.txt -o batch-create-response.json\nimport json, os\nfrom pathlib import Path\nfrom urllib.request import Request, urlopen\n\ndef prepare_requests(customer_path):\n path = Path(customer_path)\n if not path.is_file(): raise ValueError("Customer JSONL file is missing")\n items = [json.loads(line) for line in path.read_text(encoding="utf-8").splitlines() if line.strip()]\n if not items: raise ValueError("Customer JSONL contains no requests")\n ids = set()\n for item in items:\n if set(item) != {"custom_id", "body"}: raise ValueError("Each item needs custom_id and body")\n cid = item["custom_id"]\n if not isinstance(cid, str) or not cid.strip() or cid in ids: raise ValueError("custom_id must be nonempty and unique")\n ids.add(cid)\n if not isinstance(item["body"], dict) or not item["body"].get("messages"): raise ValueError("Supply actual text messages")\n supplied_model = item["body"].get("model")\n if supplied_model is not None and supplied_model not in ['google/gemini-3.1-flash-lite:batch', 'google/gemini-3.1-flash-lite']: raise ValueError("body.model must be an exact documented caller or wire ID")\n return {"endpoint":"/v1/chat/completions", "model":"google/gemini-3.1-flash-lite:batch", "requests":items}\n\nif __name__ == "__main__":\n material = os.environ.get("AILOOT_BATCH_REQUESTS_JSONL", "")\n if not material: raise SystemExit("Set AILOOT_BATCH_REQUESTS_JSONL to your actual customer file")\n body = prepare_requests(material)\n key = os.environ.get("AILOOT_API_KEY", "")\n if not key: raise SystemExit("Set AILOOT_API_KEY")\n request = Request("https://api.ailoot.ai/v1/batches", data=json.dumps(body, ensure_ascii=False).encode("utf-8"), headers={"Authorization":"Bearer " + key, "Content-Type":"application/json"}, method="POST")\n with urlopen(request) as response:\n raw = response.read()\n Path("batch-create-response.json").write_bytes(raw)\n print(raw.decode("utf-8"))\nimport json\nfrom pathlib import Path\nraw = Path("batch-status-response.json").read_bytes()\nresponse = json.loads(raw)\nif response.get("status") != "completed":\n raise SystemExit("Keep the original operation; read its status without resubmitting")\nresults = response.get("results")\nif not isinstance(results, list) or not results:\n raise SystemExit("Preserve the original response; completed results are missing")\nPath("batch-results.jsonl").write_text("".join(json.dumps(item, ensure_ascii=False) + "\\n" for item in results), encoding="utf-8")\n# Preserve batch-status-response.json with aggregate usage and every result/error.\ninline results[].response.body JSON
GET /v1/batches/{operation_id}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nBATCH_OPERATION_ID="$(python3 - <<'PY_ID'\nimport json\nfrom pathlib import Path\nfrom urllib.parse import quote\nresponse = json.loads(Path("batch-create-response.json").read_text(encoding="utf-8"))\noperation = response.get("id")\nif not isinstance(operation, str) or not operation: raise SystemExit("No actual original operation ID; preserve the response and do not resubmit")\nprint(quote(operation, safe=""))\nPY_ID\n)"\ncurl --fail-with-body --silent --show-error "https://api.ailoot.ai/v1/batches/$BATCH_OPERATION_ID" \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o batch-status-response.json\nKeep every complete returned response, file and content part.
Preserve the full original status JSON, every result/custom_id and complete response or error body. Save completed results[] as JSONL without filtering.
Preserve the original operation ID. 503 result_pending_check has X-Should-Retry:false; never resubmit an unknown original batch.
| Field | Type |
|---|---|
Fieldresults[].custom_id | Typestring |
Fieldresults[].response.body.choices[].message.content | Typestring|null |
Fieldresults[].error | Typeobject|null |
Fieldusage | Typeobject|null |
Fieldid | Typestring |
Fieldmodel | Typestring |
Fieldendpoint | Typestring |
Fieldstatus | Typestring |
Fieldrequest_counts | Typeobject |
Fieldresults[].id | Typestring |
Fieldresults[].response.status_code | Typeinteger |
Fieldresults[].response.request_id | Typestring |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid documented inline envelope, duplicate keys, item identity, or configured model capabilities conflict. | Next stepCorrect the indicated fields before any new submission. |
Response401 · authentication_error | ConditionInvalid API key. | Next stepUse the authorized Ailoot key. |
Response403 · permission_error | ConditionBatch group unavailable. | Next stepCheck key/group entitlement. |
Response422 · invalid_request_error | ConditionBatch uses balance billing; subscription creation is rejected. | Next stepUse the authorized balance-billed group. |
Response422 · price_unavailable | ConditionBatch input cannot be quoted. | Next stepPreserve response; use documented family input. |
Response402 · billing_error | ConditionBatch reserve unavailable. | Next stepResolve admission before a new request. |
Response503 · price_unavailable | ConditionBatch method price/native rates unavailable. | Next stepPreserve response; do not substitute prices. |
Response503 · api_error | ConditionExact supplier route unavailable. | Next stepPreserve response for route repair. |
Response503 · result_pending_check | ConditionOriginal result requires checking; X-Should-Retry:false. | Next stepKeep original operation_id/id and read its status; never repeat original POST. |
Response404 · not_found | ConditionBatch status operation absent or owned by another identity. | Next stepUse exact original id and same user/key/group. |
Ailoot Ultra google/gemini-3.1-flash-lite:batch
Use the method paths shown above.