Gemini 2.5 Pro is Google’s stable thinking profile for advanced coding, mathematics, STEM and long-context analysis. It can comprehend text, audio, images, video and entire code repositories, and its Gemini API profile also accepts PDF input. The output is text, including code, written analysis or a structured record. A useful assignment provides the evidence and asks for a result that can be checked, such as an explained solution, a codebase finding or a comparison across several documents.
For coding, supply the relevant files, observed behaviour and the change or question that matters. Long context can help the model relate modules rather than reason from one isolated snippet. For a code-path investigation, ask it to trace an identifier from an input form through processing and storage, identify where a contract changes and propose a focused correction. Preserve constraints and ask for supporting references. A proposed revision needs comparison with the actual code and any validation performed through the connected tools.
For mathematics or scientific analysis, state the problem, assumptions, units and required form of the answer. Supply data or figures that the calculation depends on. Ask for the supported result and the checks that make it assessable, such as boundary cases or a comparison with the original values. The model’s reasoning capability does not remove ambiguity in the problem statement. Keep an unknown quantity or unsupported assumption visible rather than replacing it with a convenient value.
Dynamic thinking is the documented default. The Gemini 2.5 GenerateContent guide supports an explicit reasoning budget from 128 to 32,768 tokens for Pro, or -1 for adaptive thinking. This edition cannot fully disable thinking. Those controls differ from Flash’s zero-budget option and from Gemini 3 thinking-level settings. The thinking budget guides reasoning rather than guaranteeing an exact number of internal tokens, and a response cap also needs to leave space for the final artifact.
For multimodal document work, identify the pages, chart, image region or recording event that should support the answer. A practical synthesis task can request the competing claims from several source documents, their supporting passages and the differences that matter to one decision. Ask the model to distinguish a stated fact from an inference. For video or audio, define whether the result should be a description, transcript, summary or comparison. The image and sound are evidence for a text result in this profile.
The exact API page documents function calling, code execution, file search, search grounding, Maps grounding, URL context and structured outputs. Define function purposes and parameter fields and preserve the real results in later turns. For a schema-constrained record, specify required fields and how missing information should be represented. The native architecture is a multimodal sparse mixture-of-experts transformer; that model design does not itself supply an external tool execution or a finished application beyond the text or code returned.
The native card lists a 1M input context and 64K text output; the API table specifies 1,048,576 input tokens and 65,536 output tokens. Instructions, source content and retained history contribute to input preparation. A maximum response allowance includes reasoning tokens, so an overly small cap can interrupt the final answer. Caching and batch processing are documented, together with Flex and Priority options. Retain each source identifier and the requested final form when preparing independent long-context tasks.
The stable identifier is distinct from the Experimental and Preview editions discussed separately in the shared Pro model card. Do not assign their version-specific results to this profile merely because they share the Pro name. The card identifies possible hallucinations and limitations in causal understanding, complex deduction and counterfactual reasoning, with a January 2025 knowledge cutoff. Supply current evidence when it matters and review source references, calculations and proposed modifications. The useful output is the supported text or code artifact the task requested.
", "aboutText": "Gemini 2.5 Pro is Google’s stable thinking profile for advanced coding, mathematics, STEM and long-context analysis. It can comprehend text, audio, images, video and entire code repositories, and its Gemini API profile also accepts PDF input. The output is text, including code, written analysis or a structured record. A useful assignment provides the evidence and asks for a result that can be checked, such as an explained solution, a codebase finding or a comparison across several documents.\n\nFor coding, supply the relevant files, observed behaviour and the change or question that matters. Long context can help the model relate modules rather than reason from one isolated snippet. For a code-path investigation, ask it to trace an identifier from an input form through processing and storage, identify where a contract changes and propose a focused correction. Preserve constraints and ask for supporting references. A proposed revision needs comparison with the actual code and any validation performed through the connected tools.\n\nFor mathematics or scientific analysis, state the problem, assumptions, units and required form of the answer. Supply data or figures that the calculation depends on. Ask for the supported result and the checks that make it assessable, such as boundary cases or a comparison with the original values. The model’s reasoning capability does not remove ambiguity in the problem statement. Keep an unknown quantity or unsupported assumption visible rather than replacing it with a convenient value.\n\nDynamic thinking is the documented default. The Gemini 2.5 GenerateContent guide supports an explicit reasoning budget from 128 to 32,768 tokens for Pro, or -1 for adaptive thinking. This edition cannot fully disable thinking. Those controls differ from Flash’s zero-budget option and from Gemini 3 thinking-level settings. The thinking budget guides reasoning rather than guaranteeing an exact number of internal tokens, and a response cap also needs to leave space for the final artifact.\n\nFor multimodal document work, identify the pages, chart, image region or recording event that should support the answer. A practical synthesis task can request the competing claims from several source documents, their supporting passages and the differences that matter to one decision. Ask the model to distinguish a stated fact from an inference. For video or audio, define whether the result should be a description, transcript, summary or comparison. The image and sound are evidence for a text result in this profile.\n\nThe exact API page documents function calling, code execution, file search, search grounding, Maps grounding, URL context and structured outputs. Define function purposes and parameter fields and preserve the real results in later turns. For a schema-constrained record, specify required fields and how missing information should be represented. The native architecture is a multimodal sparse mixture-of-experts transformer; that model design does not itself supply an external tool execution or a finished application beyond the text or code returned.\n\nThe native card lists a 1M input context and 64K text output; the API table specifies 1,048,576 input tokens and 65,536 output tokens. Instructions, source content and retained history contribute to input preparation. A maximum response allowance includes reasoning tokens, so an overly small cap can interrupt the final answer. Caching and batch processing are documented, together with Flex and Priority options. Retain each source identifier and the requested final form when preparing independent long-context tasks.\n\nThe stable identifier is distinct from the Experimental and Preview editions discussed separately in the shared Pro model card. Do not assign their version-specific results to this profile merely because they share the Pro name. The card identifies possible hallucinations and limitations in causal understanding, complex deduction and counterfactual reasoning, with a January 2025 knowledge cutoff. Supply current evidence when it matters and review source references, calculations and proposed modifications. The useful output is the supported text or code artifact the task requested.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "43e9e4ef0dc60b2b6667255132eaa80739a75df8ae47743ef36bbd46176d5fb9", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "google/gemini-2.5-pro:batchGemini 2.5 Pro is Google’s stable thinking model for complex code, mathematics, STEM and long-context analysis. It accepts text, images, audio, video and PDF and returns text, with tools and structured output. Its dynamic reasoning budget supports 128–32,768 tokens and cannot be fully disabled.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 2.5 Pro is Google’s stable thinking profile for advanced coding, mathematics, STEM and long-context analysis. It can comprehend text, audio, images, video and entire code repositories, and its Gemini API profile also accepts PDF input. The output is text, including code, written analysis or a structured record. A useful assignment provides the evidence and asks for a result that can be checked, such as an explained solution, a codebase finding or a comparison across several documents.
For coding, supply the relevant files, observed behaviour and the change or question that matters. Long context can help the model relate modules rather than reason from one isolated snippet. For a code-path investigation, ask it to trace an identifier from an input form through processing and storage, identify where a contract changes and propose a focused correction. Preserve constraints and ask for supporting references. A proposed revision needs comparison with the actual code and any validation performed through the connected tools.
For mathematics or scientific analysis, state the problem, assumptions, units and required form of the answer. Supply data or figures that the calculation depends on. Ask for the supported result and the checks that make it assessable, such as boundary cases or a comparison with the original values. The model’s reasoning capability does not remove ambiguity in the problem statement. Keep an unknown quantity or unsupported assumption visible rather than replacing it with a convenient value.
Dynamic thinking is the documented default. The Gemini 2.5 GenerateContent guide supports an explicit reasoning budget from 128 to 32,768 tokens for Pro, or -1 for adaptive thinking. This edition cannot fully disable thinking. Those controls differ from Flash’s zero-budget option and from Gemini 3 thinking-level settings. The thinking budget guides reasoning rather than guaranteeing an exact number of internal tokens, and a response cap also needs to leave space for the final artifact.
For multimodal document work, identify the pages, chart, image region or recording event that should support the answer. A practical synthesis task can request the competing claims from several source documents, their supporting passages and the differences that matter to one decision. Ask the model to distinguish a stated fact from an inference. For video or audio, define whether the result should be a description, transcript, summary or comparison. The image and sound are evidence for a text result in this profile.
The exact API page documents function calling, code execution, file search, search grounding, Maps grounding, URL context and structured outputs. Define function purposes and parameter fields and preserve the real results in later turns. For a schema-constrained record, specify required fields and how missing information should be represented. The native architecture is a multimodal sparse mixture-of-experts transformer; that model design does not itself supply an external tool execution or a finished application beyond the text or code returned.
The native card lists a 1M input context and 64K text output; the API table specifies 1,048,576 input tokens and 65,536 output tokens. Instructions, source content and retained history contribute to input preparation. A maximum response allowance includes reasoning tokens, so an overly small cap can interrupt the final answer. Caching and batch processing are documented, together with Flex and Priority options. Retain each source identifier and the requested final form when preparing independent long-context tasks.
The stable identifier is distinct from the Experimental and Preview editions discussed separately in the shared Pro model card. Do not assign their version-specific results to this profile merely because they share the Pro name. The card identifies possible hallucinations and limitations in causal understanding, complex deduction and counterfactual reasoning, with a January 2025 knowledge cutoff. Supply current evidence when it matters and review source references, calculations and proposed modifications. The useful output is the supported text or code artifact the task requested.
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-2.5-pro: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-2.5-pro:batch, google/gemini-2.5-pro | 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 $0.00125 / 1K tokens Output · Output tokens $0.01 / 1K tokens Input · Cache read $0.00025 / 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 $0.00125 / 1K tokens Output · Output tokens $0.01 / 1K tokens Input · Cache read $0.00025 / 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 $0.0025 / 1K tokens Output · Output tokens $0.015 / 1K tokens Input · Cache read $0.0005 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${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-2.5-pro: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-2.5-pro:batch', 'google/gemini-2.5-pro']: raise ValueError("body.model must be an exact documented caller or wire ID")\n return {"endpoint":"/v1/chat/completions", "model":"google/gemini-2.5-pro: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-2.5-pro:batch
Use the method paths shown above.