o4-mini is OpenAI’s compact o-series reasoning model, optimized for fast, effective reasoning in coding and visual tasks. It accepts text and images and produces text. Its useful role is a defined technical problem that needs analysis before an answer: understanding a code failure, interpreting a diagram, connecting facts in supplied material or producing a structured result that a subsequent step can use.
For coding, give the model the relevant function or files, the expected behavior and the exact failing input or error. Include the language and environment details that affect the result. A focused request can ask for the likely cause, a minimal proposed correction and an explanation of how the change addresses the observed behavior. Define the boundary of the change, such as preserving the public interface or the meaning of existing data, so the result can be reviewed against the actual task.
For a visual problem, provide a legible screenshot, diagram or chart and identify the question it should answer. Keep meaningful labels, axes and units visible. An illustrative brief is to explain what a chart supports, identify the observations used, and separate a visible value from an inference. For a document task, label the source material and define the fields or relationships required in the answer. A compact model still benefits from complete problem information and a precise output request.
OpenAI specifies a 200,000-token context window, a maximum output of 100,000 tokens and a knowledge cutoff of June 1, 2024. Reasoning tokens consume both context and output capacity, so leave room for analysis and the final response rather than filling the entire allowance with input. Reaching a context or output limit can produce an incomplete response before any visible answer. A short final answer can still require internal reasoning; its visible length alone does not describe the full token budget.
The exact o4-mini model page lists Chat Completions, Responses, Batch and fine-tuning interfaces. Its documented features include streaming, Structured Outputs, function calling, file uploads, image input, file search, prompt caching and fine-tuning. The tool set lists web and file search, code interpretation and MCP connections. Give an application tool a clear purpose and input contract, return the actual result, and ask the model to use that result for the next decision. A requested function call is an action proposal, while a structured final answer organizes the information the task produces.
OpenAI’s o-series prompting guidance recommends a simple, direct goal with explicit constraints and clear delimiters around source material. Let the model work through the problem internally; request the final explanation, evidence or calculation you need instead of a transcript of hidden reasoning. Try a clear task brief first, then add examples when a required format or category boundary remains unclear. An example should demonstrate the same rules as the real task, including how to represent missing information.
For applications that need an optional explanation of the reasoning process, OpenAI’s reasoning guide explicitly documents detailed reasoning summaries for o4-mini. A summary must be requested and is distinct from the raw internal reasoning tokens, which are not exposed. The final answer still needs to contain the result the user asked for: for example, a proposed code change, a chart interpretation with relevant observations, or extracted fields tied to the supplied material. Supply recent facts when they matter, verify important claims against their source, and use a bounded task and completion criterion to keep the workflow focused.
", "aboutText": "o4-mini is OpenAI’s compact o-series reasoning model, optimized for fast, effective reasoning in coding and visual tasks. It accepts text and images and produces text. Its useful role is a defined technical problem that needs analysis before an answer: understanding a code failure, interpreting a diagram, connecting facts in supplied material or producing a structured result that a subsequent step can use.\n\nFor coding, give the model the relevant function or files, the expected behavior and the exact failing input or error. Include the language and environment details that affect the result. A focused request can ask for the likely cause, a minimal proposed correction and an explanation of how the change addresses the observed behavior. Define the boundary of the change, such as preserving the public interface or the meaning of existing data, so the result can be reviewed against the actual task.\n\nFor a visual problem, provide a legible screenshot, diagram or chart and identify the question it should answer. Keep meaningful labels, axes and units visible. An illustrative brief is to explain what a chart supports, identify the observations used, and separate a visible value from an inference. For a document task, label the source material and define the fields or relationships required in the answer. A compact model still benefits from complete problem information and a precise output request.\n\nOpenAI specifies a 200,000-token context window, a maximum output of 100,000 tokens and a knowledge cutoff of June 1, 2024. Reasoning tokens consume both context and output capacity, so leave room for analysis and the final response rather than filling the entire allowance with input. Reaching a context or output limit can produce an incomplete response before any visible answer. A short final answer can still require internal reasoning; its visible length alone does not describe the full token budget.\n\nThe exact o4-mini model page lists Chat Completions, Responses, Batch and fine-tuning interfaces. Its documented features include streaming, Structured Outputs, function calling, file uploads, image input, file search, prompt caching and fine-tuning. The tool set lists web and file search, code interpretation and MCP connections. Give an application tool a clear purpose and input contract, return the actual result, and ask the model to use that result for the next decision. A requested function call is an action proposal, while a structured final answer organizes the information the task produces.\n\nOpenAI’s o-series prompting guidance recommends a simple, direct goal with explicit constraints and clear delimiters around source material. Let the model work through the problem internally; request the final explanation, evidence or calculation you need instead of a transcript of hidden reasoning. Try a clear task brief first, then add examples when a required format or category boundary remains unclear. An example should demonstrate the same rules as the real task, including how to represent missing information.\n\nFor applications that need an optional explanation of the reasoning process, OpenAI’s reasoning guide explicitly documents detailed reasoning summaries for o4-mini. A summary must be requested and is distinct from the raw internal reasoning tokens, which are not exposed. The final answer still needs to contain the result the user asked for: for example, a proposed code change, a chart interpretation with relevant observations, or extracted fields tied to the supplied material. Supply recent facts when they matter, verify important claims against their source, and use a bounded task and completion criterion to keep the workflow focused.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "bce3c1eb68a69689ec6d5d013e9b229603c9ae0284e84989d6b54757d25bbdd4", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "openai/o4-mini:batchOpenAI o4-mini is a compact reasoning model focused on efficient coding and visual tasks. It accepts text and images, returns text, and supports structured answers and tools for solving a bounded technical problem or extracting a useful conclusion from supplied material.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
o4-mini is OpenAI’s compact o-series reasoning model, optimized for fast, effective reasoning in coding and visual tasks. It accepts text and images and produces text. Its useful role is a defined technical problem that needs analysis before an answer: understanding a code failure, interpreting a diagram, connecting facts in supplied material or producing a structured result that a subsequent step can use.
For coding, give the model the relevant function or files, the expected behavior and the exact failing input or error. Include the language and environment details that affect the result. A focused request can ask for the likely cause, a minimal proposed correction and an explanation of how the change addresses the observed behavior. Define the boundary of the change, such as preserving the public interface or the meaning of existing data, so the result can be reviewed against the actual task.
For a visual problem, provide a legible screenshot, diagram or chart and identify the question it should answer. Keep meaningful labels, axes and units visible. An illustrative brief is to explain what a chart supports, identify the observations used, and separate a visible value from an inference. For a document task, label the source material and define the fields or relationships required in the answer. A compact model still benefits from complete problem information and a precise output request.
OpenAI specifies a 200,000-token context window, a maximum output of 100,000 tokens and a knowledge cutoff of June 1, 2024. Reasoning tokens consume both context and output capacity, so leave room for analysis and the final response rather than filling the entire allowance with input. Reaching a context or output limit can produce an incomplete response before any visible answer. A short final answer can still require internal reasoning; its visible length alone does not describe the full token budget.
The exact o4-mini model page lists Chat Completions, Responses, Batch and fine-tuning interfaces. Its documented features include streaming, Structured Outputs, function calling, file uploads, image input, file search, prompt caching and fine-tuning. The tool set lists web and file search, code interpretation and MCP connections. Give an application tool a clear purpose and input contract, return the actual result, and ask the model to use that result for the next decision. A requested function call is an action proposal, while a structured final answer organizes the information the task produces.
OpenAI’s o-series prompting guidance recommends a simple, direct goal with explicit constraints and clear delimiters around source material. Let the model work through the problem internally; request the final explanation, evidence or calculation you need instead of a transcript of hidden reasoning. Try a clear task brief first, then add examples when a required format or category boundary remains unclear. An example should demonstrate the same rules as the real task, including how to represent missing information.
For applications that need an optional explanation of the reasoning process, OpenAI’s reasoning guide explicitly documents detailed reasoning summaries for o4-mini. A summary must be requested and is distinct from the raw internal reasoning tokens, which are not exposed. The final answer still needs to contain the result the user asked for: for example, a proposed code change, a chart interpretation with relevant observations, or extracted fields tied to the supplied material. Supply recent facts when they matter, verify important claims against their source, and use a bounded task and completion criterion to keep the workflow focused.
POST /v1/batchestexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldendpoint | Typestring | RequirementRequired | Values & limits /v1/chat/completions | Default— |
Fieldmodel | Typestring | RequirementRequired | Values & limits openai/o4-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/o4-mini:batch, openai/o4-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 $0.000275 / 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 $0.000275 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${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/o4-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/o4-mini:batch', 'openai/o4-mini']: raise ValueError("body.model must be an exact documented caller or wire ID")\n return {"endpoint":"/v1/chat/completions", "model":"openai/o4-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/o4-mini:batch
Use the method paths shown above.