Gemini 3.1 Pro Preview is Google’s reasoning-oriented text model for complex tasks that need software engineering, algorithmic development or synthesis of multimodal evidence. It builds on Gemini 3 Pro, emphasizing precise tool use, more efficient reasoning and reliable multi-step execution. Text, images, audio, video and PDF can contribute to a written answer, a code artifact or a structured result.
For a demanding coding assignment, provide the goal, relevant repository material, observed behaviour and the constraints to retain. Entire code repositories can supply context for the assignment. For a code-contract review, ask the model to compare two modules’ handling of a shared data contract, identify the mismatch and propose a focused correction with supporting code references. The useful output distinguishes the analysis, proposed revision and evidence from any validation performed by the connected application.
The launch material demonstrates code-based visual explanations and interactive projects, including animated SVG output from a text brief. These are code artifacts rather than raster-image generation. A clear brief can define what should be explained, how the visual should behave and the data it should represent. Review the resulting code and rendering against those requirements. For a data-synthesis task, supply the actual sources and ask for one view that preserves the relationships and qualifications found in them.
The documented thinking levels are low, medium and high, with high as the default for 3.1 Pro Preview. Thinking cannot be fully disabled in this Pro profile. Choose lower effort for a bounded answer and more reasoning for difficult multi-step work, while leaving sufficient output allowance for the final artifact. A small output cap can interrupt reasoning before a usable final answer appears. The thinking guide separates a summary of reasoning from the full internal process and explains why the conversation’s thought-signature context matters.
The exact Preview table lists function calling, code execution, search grounding, Maps grounding, URL context and structured outputs. It scopes File Search to AI Studio. Provide function purposes and parameter definitions and continue from the real returned result. The separate Custom Tools Preview profile is optimized to prioritize custom tools and bash; it is a distinct named producer endpoint, so that specialization should not be silently treated as a property of every 3.1 Pro request. Select a structured result schema when a task needs defined records instead of unrestricted prose.
For multimodal analysis, identify the relevant page, visual, recording interval or video event. For document analysis, compare a diagram with its written specification and return each discrepancy with its supporting passage. A spoken source can contribute a transcript or an interpretation in text. Preserve source references for the conclusions that need checking, and separate what is visible or stated from what is inferred. This profile’s output remains text, including code; native image or speech generation is not part of its exact capability table.
The native 3.1 Pro card specifies up to 1M context and 64K text output, and the exact Preview API table gives 1,048,576 input tokens and 65,536 output tokens. Include instructions, conversation history and media in the input budget. Caching and batch processing are documented, with Flex and Priority options also listed for the producer profile. For several independent items, define the required output and retain each source identifier rather than combining unrelated evidence into one untraceable answer.
The named Preview edition remains distinct from Pro’s Custom Tools profile and subsequent Flash or Pro releases. Its strengths concern complex reasoning, coding and evidence synthesis; the final artifact still needs checking against the source and the actual tool results. Retain unresolved ambiguity when the supplied information does not support a definite conclusion. A useful deliverable is the supported answer, code or record the task requested, with enough evidence to assess its practical limits.
", "aboutText": "Gemini 3.1 Pro Preview is Google’s reasoning-oriented text model for complex tasks that need software engineering, algorithmic development or synthesis of multimodal evidence. It builds on Gemini 3 Pro, emphasizing precise tool use, more efficient reasoning and reliable multi-step execution. Text, images, audio, video and PDF can contribute to a written answer, a code artifact or a structured result.\n\nFor a demanding coding assignment, provide the goal, relevant repository material, observed behaviour and the constraints to retain. Entire code repositories can supply context for the assignment. For a code-contract review, ask the model to compare two modules’ handling of a shared data contract, identify the mismatch and propose a focused correction with supporting code references. The useful output distinguishes the analysis, proposed revision and evidence from any validation performed by the connected application.\n\nThe launch material demonstrates code-based visual explanations and interactive projects, including animated SVG output from a text brief. These are code artifacts rather than raster-image generation. A clear brief can define what should be explained, how the visual should behave and the data it should represent. Review the resulting code and rendering against those requirements. For a data-synthesis task, supply the actual sources and ask for one view that preserves the relationships and qualifications found in them.\n\nThe documented thinking levels are low, medium and high, with high as the default for 3.1 Pro Preview. Thinking cannot be fully disabled in this Pro profile. Choose lower effort for a bounded answer and more reasoning for difficult multi-step work, while leaving sufficient output allowance for the final artifact. A small output cap can interrupt reasoning before a usable final answer appears. The thinking guide separates a summary of reasoning from the full internal process and explains why the conversation’s thought-signature context matters.\n\nThe exact Preview table lists function calling, code execution, search grounding, Maps grounding, URL context and structured outputs. It scopes File Search to AI Studio. Provide function purposes and parameter definitions and continue from the real returned result. The separate Custom Tools Preview profile is optimized to prioritize custom tools and bash; it is a distinct named producer endpoint, so that specialization should not be silently treated as a property of every 3.1 Pro request. Select a structured result schema when a task needs defined records instead of unrestricted prose.\n\nFor multimodal analysis, identify the relevant page, visual, recording interval or video event. For document analysis, compare a diagram with its written specification and return each discrepancy with its supporting passage. A spoken source can contribute a transcript or an interpretation in text. Preserve source references for the conclusions that need checking, and separate what is visible or stated from what is inferred. This profile’s output remains text, including code; native image or speech generation is not part of its exact capability table.\n\nThe native 3.1 Pro card specifies up to 1M context and 64K text output, and the exact Preview API table gives 1,048,576 input tokens and 65,536 output tokens. Include instructions, conversation history and media in the input budget. Caching and batch processing are documented, with Flex and Priority options also listed for the producer profile. For several independent items, define the required output and retain each source identifier rather than combining unrelated evidence into one untraceable answer.\n\nThe named Preview edition remains distinct from Pro’s Custom Tools profile and subsequent Flash or Pro releases. Its strengths concern complex reasoning, coding and evidence synthesis; the final artifact still needs checking against the source and the actual tool results. Retain unresolved ambiguity when the supplied information does not support a definite conclusion. A useful deliverable is the supported answer, code or record the task requested, with enough evidence to assess its practical limits.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "ebda6b420fb1f8814680402b8ca3c1820f3bbb6fae8c91840badc396bc5c06a4", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "google/gemini-3.1-pro-preview:batchGemini 3.1 Pro Preview is Google’s multimodal reasoning model for complex software, algorithm and knowledge tasks. It accepts text, images, audio, video and PDF and returns text or code, with tools and structured output. Low, medium and high reasoning levels guide effort; high is the documented default.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 3.1 Pro Preview is Google’s reasoning-oriented text model for complex tasks that need software engineering, algorithmic development or synthesis of multimodal evidence. It builds on Gemini 3 Pro, emphasizing precise tool use, more efficient reasoning and reliable multi-step execution. Text, images, audio, video and PDF can contribute to a written answer, a code artifact or a structured result.
For a demanding coding assignment, provide the goal, relevant repository material, observed behaviour and the constraints to retain. Entire code repositories can supply context for the assignment. For a code-contract review, ask the model to compare two modules’ handling of a shared data contract, identify the mismatch and propose a focused correction with supporting code references. The useful output distinguishes the analysis, proposed revision and evidence from any validation performed by the connected application.
The launch material demonstrates code-based visual explanations and interactive projects, including animated SVG output from a text brief. These are code artifacts rather than raster-image generation. A clear brief can define what should be explained, how the visual should behave and the data it should represent. Review the resulting code and rendering against those requirements. For a data-synthesis task, supply the actual sources and ask for one view that preserves the relationships and qualifications found in them.
The documented thinking levels are low, medium and high, with high as the default for 3.1 Pro Preview. Thinking cannot be fully disabled in this Pro profile. Choose lower effort for a bounded answer and more reasoning for difficult multi-step work, while leaving sufficient output allowance for the final artifact. A small output cap can interrupt reasoning before a usable final answer appears. The thinking guide separates a summary of reasoning from the full internal process and explains why the conversation’s thought-signature context matters.
The exact Preview table lists function calling, code execution, search grounding, Maps grounding, URL context and structured outputs. It scopes File Search to AI Studio. Provide function purposes and parameter definitions and continue from the real returned result. The separate Custom Tools Preview profile is optimized to prioritize custom tools and bash; it is a distinct named producer endpoint, so that specialization should not be silently treated as a property of every 3.1 Pro request. Select a structured result schema when a task needs defined records instead of unrestricted prose.
For multimodal analysis, identify the relevant page, visual, recording interval or video event. For document analysis, compare a diagram with its written specification and return each discrepancy with its supporting passage. A spoken source can contribute a transcript or an interpretation in text. Preserve source references for the conclusions that need checking, and separate what is visible or stated from what is inferred. This profile’s output remains text, including code; native image or speech generation is not part of its exact capability table.
The native 3.1 Pro card specifies up to 1M context and 64K text output, and the exact Preview API table gives 1,048,576 input tokens and 65,536 output tokens. Include instructions, conversation history and media in the input budget. Caching and batch processing are documented, with Flex and Priority options also listed for the producer profile. For several independent items, define the required output and retain each source identifier rather than combining unrelated evidence into one untraceable answer.
The named Preview edition remains distinct from Pro’s Custom Tools profile and subsequent Flash or Pro releases. Its strengths concern complex reasoning, coding and evidence synthesis; the final artifact still needs checking against the source and the actual tool results. Retain unresolved ambiguity when the supplied information does not support a definite conclusion. A useful deliverable is the supported answer, code or record the task requested, with enough evidence to assess its practical limits.
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-pro-preview: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-pro-preview:batch, google/gemini-3.1-pro-preview | 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 $0.002 / 1K tokens Output · Output tokens $0.012 / 1K tokens Input · Cache read — / 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 including200,000 | Charge Input · Input tokens $0.002 / 1K tokens Output · Output tokens $0.012 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 2 | Rate schedule— | Context tokens, more than200,000 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.004 / 1K tokens Output · Output tokens $0.018 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${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-pro-preview: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-pro-preview:batch', 'google/gemini-3.1-pro-preview']: raise ValueError("body.model must be an exact documented caller or wire ID")\n return {"endpoint":"/v1/chat/completions", "model":"google/gemini-3.1-pro-preview: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-pro-preview:batch
Use the method paths shown above.