OpenAI o3-mini is a smaller o-series reasoning model focused on technical problem solving, including science, mathematics and coding. It accepts text and produces text, with extra internal reasoning before the visible answer. Use it for a clearly stated mathematical problem, algorithmic analysis, code revision or a technical comparison whose conclusion depends on several conditions. Reasoning effort can be configured for the base o3-mini edition; an o3-mini High preset selects high effort rather than separate model weights.
The maker documents low, medium and high reasoning effort. More effort can support a demanding problem and require more generation time, while the desired visible answer can still be concise. Give the model the task, constraints and output contract rather than prescribing a long chain of intermediate thoughts. For an algorithm problem, supply the input bounds, required behaviour and cases that determine correctness. For mathematics, define the variables, domains, notation and required result.
OpenAI lists a 200,000-token context window, a maximum output budget of 100,000 tokens and a knowledge cutoff of October 1, 2023. Reasoning tokens consume the available context and generated-output budget before the final response, so the maximum is not a promise of that many visible answer tokens. Leave room for both analysis and the requested result. A request can exhaust its generated-token allowance before returning useful visible text if the budget is too small for the problem.
The native input modality is text rather than vision. If a task originates in a diagram or screenshot, provide its relevant conditions in written form. The producer lists file uploads and file-search support in tool-assisted workflows, which can supply relevant textual material without changing the model’s native modality. Identify the source passages or file contents needed to answer the question instead of assuming that every attachment contributes useful evidence automatically.
The model supports Structured Outputs, function calling and streaming, and the producer model card lists Responses, Chat Completions, Assistants and Batch interfaces. In a structured task, specify the required fields and how missing information should be represented. In a tool workflow, the model proposes a function and arguments; the application executes the action and returns the actual observation. Keep a proposed operation distinct from one whose result has been received.
The current producer tool set also lists file search, code interpretation, MCP connections and image-generation tooling. Those configured tools have their own operations; they do not turn o3-mini’s direct text response into native image or audio output. For a coding task, supply the code, observed failure and requirements, then request a proposed change with an explanation of the cases it addresses. If execution results are available, provide them as evidence for the next revision rather than treating unexecuted code as a completed outcome.
A useful final artifact can be a formula, a justified comparison, a code proposal or a structured technical result that connects its conclusion to the original conditions. For a follow-up, name the new evidence and the part of the answer that needs revision. Preserve the relevant conversation and tool observations so the next response can work with actual results. The model’s smaller reasoning role is practical when the task needs analysis, clear constraints and a focused text artifact rather than unsupported assumptions about external actions.
", "aboutText": "OpenAI o3-mini is a smaller o-series reasoning model focused on technical problem solving, including science, mathematics and coding. It accepts text and produces text, with extra internal reasoning before the visible answer. Use it for a clearly stated mathematical problem, algorithmic analysis, code revision or a technical comparison whose conclusion depends on several conditions. Reasoning effort can be configured for the base o3-mini edition; an o3-mini High preset selects high effort rather than separate model weights.\n\nThe maker documents low, medium and high reasoning effort. More effort can support a demanding problem and require more generation time, while the desired visible answer can still be concise. Give the model the task, constraints and output contract rather than prescribing a long chain of intermediate thoughts. For an algorithm problem, supply the input bounds, required behaviour and cases that determine correctness. For mathematics, define the variables, domains, notation and required result.\n\nOpenAI lists a 200,000-token context window, a maximum output budget of 100,000 tokens and a knowledge cutoff of October 1, 2023. Reasoning tokens consume the available context and generated-output budget before the final response, so the maximum is not a promise of that many visible answer tokens. Leave room for both analysis and the requested result. A request can exhaust its generated-token allowance before returning useful visible text if the budget is too small for the problem.\n\nThe native input modality is text rather than vision. If a task originates in a diagram or screenshot, provide its relevant conditions in written form. The producer lists file uploads and file-search support in tool-assisted workflows, which can supply relevant textual material without changing the model’s native modality. Identify the source passages or file contents needed to answer the question instead of assuming that every attachment contributes useful evidence automatically.\n\nThe model supports Structured Outputs, function calling and streaming, and the producer model card lists Responses, Chat Completions, Assistants and Batch interfaces. In a structured task, specify the required fields and how missing information should be represented. In a tool workflow, the model proposes a function and arguments; the application executes the action and returns the actual observation. Keep a proposed operation distinct from one whose result has been received.\n\nThe current producer tool set also lists file search, code interpretation, MCP connections and image-generation tooling. Those configured tools have their own operations; they do not turn o3-mini’s direct text response into native image or audio output. For a coding task, supply the code, observed failure and requirements, then request a proposed change with an explanation of the cases it addresses. If execution results are available, provide them as evidence for the next revision rather than treating unexecuted code as a completed outcome.\n\nA useful final artifact can be a formula, a justified comparison, a code proposal or a structured technical result that connects its conclusion to the original conditions. For a follow-up, name the new evidence and the part of the answer that needs revision. Preserve the relevant conversation and tool observations so the next response can work with actual results. The model’s smaller reasoning role is practical when the task needs analysis, clear constraints and a focused text artifact rather than unsupported assumptions about external actions.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "5a0c273fa7340060be90937871c74c2f4ce959da0bb5f685f960f8d93605e954", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "openai/o3-mini:batchOpenAI o3-mini is a text reasoning model for science, mathematics and coding. It offers low, medium and high reasoning effort, a 200K context, structured outputs and tool-assisted workflows, with a maximum generated output budget of 100K tokens.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
OpenAI o3-mini is a smaller o-series reasoning model focused on technical problem solving, including science, mathematics and coding. It accepts text and produces text, with extra internal reasoning before the visible answer. Use it for a clearly stated mathematical problem, algorithmic analysis, code revision or a technical comparison whose conclusion depends on several conditions. Reasoning effort can be configured for the base o3-mini edition; an o3-mini High preset selects high effort rather than separate model weights.
The maker documents low, medium and high reasoning effort. More effort can support a demanding problem and require more generation time, while the desired visible answer can still be concise. Give the model the task, constraints and output contract rather than prescribing a long chain of intermediate thoughts. For an algorithm problem, supply the input bounds, required behaviour and cases that determine correctness. For mathematics, define the variables, domains, notation and required result.
OpenAI lists a 200,000-token context window, a maximum output budget of 100,000 tokens and a knowledge cutoff of October 1, 2023. Reasoning tokens consume the available context and generated-output budget before the final response, so the maximum is not a promise of that many visible answer tokens. Leave room for both analysis and the requested result. A request can exhaust its generated-token allowance before returning useful visible text if the budget is too small for the problem.
The native input modality is text rather than vision. If a task originates in a diagram or screenshot, provide its relevant conditions in written form. The producer lists file uploads and file-search support in tool-assisted workflows, which can supply relevant textual material without changing the model’s native modality. Identify the source passages or file contents needed to answer the question instead of assuming that every attachment contributes useful evidence automatically.
The model supports Structured Outputs, function calling and streaming, and the producer model card lists Responses, Chat Completions, Assistants and Batch interfaces. In a structured task, specify the required fields and how missing information should be represented. In a tool workflow, the model proposes a function and arguments; the application executes the action and returns the actual observation. Keep a proposed operation distinct from one whose result has been received.
The current producer tool set also lists file search, code interpretation, MCP connections and image-generation tooling. Those configured tools have their own operations; they do not turn o3-mini’s direct text response into native image or audio output. For a coding task, supply the code, observed failure and requirements, then request a proposed change with an explanation of the cases it addresses. If execution results are available, provide them as evidence for the next revision rather than treating unexecuted code as a completed outcome.
A useful final artifact can be a formula, a justified comparison, a code proposal or a structured technical result that connects its conclusion to the original conditions. For a follow-up, name the new evidence and the part of the answer that needs revision. Preserve the relevant conversation and tool observations so the next response can work with actual results. The model’s smaller reasoning role is practical when the task needs analysis, clear constraints and a focused text artifact rather than unsupported assumptions about external actions.
POST /v1/batchestexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldendpoint | Typestring | RequirementRequired | Values & limits /v1/chat/completions | Default— |
Fieldmodel | Typestring | RequirementRequired | Values & limits openai/o3-mini: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 openai/o3-mini:batch, openai/o3-mini | Default— |
Fieldprovider.only | Typestring[] | RequirementOptional | Values & limits openai | 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 $0.0011 / 1K tokens Output · Output tokens $0.0044 / 1K tokens Input · Cache read $0.00055 / 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 $0.0011 / 1K tokens Output · Output tokens $0.0044 / 1K tokens Input · Cache read $0.00055 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${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":"openai/o3-mini: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 ['openai/o3-mini:batch', 'openai/o3-mini']: raise ValueError("body.model must be an exact documented caller or wire ID")\n return {"endpoint":"/v1/chat/completions", "model":"openai/o3-mini: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 openai/o3-mini:batch
Use the method paths shown above.