gpt-oss-120b is OpenAI’s larger open-weight language model for general-purpose reasoning, coding and agentic work. It receives and produces text. The maker publishes 117 billion total parameters with 5.1 billion active parameters per token in a mixture-of-experts architecture. This is the 120b edition of the family, separate from gpt-oss-20b and the specialized Safeguard models.
The release describes a mostly English, text-only training set focused on STEM, coding and general knowledge. An illustrative task is analyzing an algorithm from its code and stated conditions: explain the important relationships, compare possible approaches and produce a concrete implementation proposal. For a document decision, provide the material and criteria, then request a conclusion tied to the evidence you supplied.
OpenAI’s published architecture has 36 layers, 128 experts and four active experts per token. The original release uses MXFP4 for the mixture-of-experts weights and describes the model running within one 80 GB GPU. OpenAI releases the weights under Apache 2.0 and supports fine-tuning for specialized use cases. These are properties of the producer’s published model and format, rather than a description of an application’s particular deployment.
The model documentation lists a 131,072-token context window and a maximum generated output of 131,072 tokens, with a knowledge cutoff of June 1, 2024. Input, reasoning and output must fit the available context. The supported reasoning levels are low, medium and high, allowing a task to request a short dialogue response or deeper analysis. OpenAI requires the Harmony format, which separates internal analysis from the final response; the maker states that raw analysis is intended for developer use rather than direct display to end users.
The producer documents function calling, web browsing, Python code execution through tools and Structured Outputs. Its model card also lists streaming, with function, code-interpreter, MCP and search capabilities in the documented tool environment. Applications provide operations, execute their actions and return actual results. A calculation or lookup can then become evidence for another reasoning step, while a proposed tool request remains distinct from an operation that has run.
Prepare a clear goal, definitions and the useful final artifact: an explanation, code proposal, formula or structured set of findings. Identify which facts must survive a transformation and how missing information should be represented. A useful final response connects its conclusion to the supplied conditions and any actual tool results. For a follow-up, carry the significant evidence and the decision still to be made into the next request.
", "aboutText": "gpt-oss-120b is OpenAI’s larger open-weight language model for general-purpose reasoning, coding and agentic work. It receives and produces text. The maker publishes 117 billion total parameters with 5.1 billion active parameters per token in a mixture-of-experts architecture. This is the 120b edition of the family, separate from gpt-oss-20b and the specialized Safeguard models.\n\nThe release describes a mostly English, text-only training set focused on STEM, coding and general knowledge. An illustrative task is analyzing an algorithm from its code and stated conditions: explain the important relationships, compare possible approaches and produce a concrete implementation proposal. For a document decision, provide the material and criteria, then request a conclusion tied to the evidence you supplied.\n\nOpenAI’s published architecture has 36 layers, 128 experts and four active experts per token. The original release uses MXFP4 for the mixture-of-experts weights and describes the model running within one 80 GB GPU. OpenAI releases the weights under Apache 2.0 and supports fine-tuning for specialized use cases. These are properties of the producer’s published model and format, rather than a description of an application’s particular deployment.\n\nThe model documentation lists a 131,072-token context window and a maximum generated output of 131,072 tokens, with a knowledge cutoff of June 1, 2024. Input, reasoning and output must fit the available context. The supported reasoning levels are low, medium and high, allowing a task to request a short dialogue response or deeper analysis. OpenAI requires the Harmony format, which separates internal analysis from the final response; the maker states that raw analysis is intended for developer use rather than direct display to end users.\n\nThe producer documents function calling, web browsing, Python code execution through tools and Structured Outputs. Its model card also lists streaming, with function, code-interpreter, MCP and search capabilities in the documented tool environment. Applications provide operations, execute their actions and return actual results. A calculation or lookup can then become evidence for another reasoning step, while a proposed tool request remains distinct from an operation that has run.\n\nPrepare a clear goal, definitions and the useful final artifact: an explanation, code proposal, formula or structured set of findings. Identify which facts must survive a transformation and how missing information should be represented. A useful final response connects its conclusion to the supplied conditions and any actual tool results. For a follow-up, carry the significant evidence and the decision still to be made into the next request.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "bb570a52276656defb93e8f0e675f435c48d93e0c277d7417678ebae6f59472c", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "openai/gpt-oss-120b:batchOpenAI’s larger gpt-oss open-weight model uses mixture-of-experts reasoning for text, coding and agentic work. It supports low, medium and high reasoning effort, function calling and Structured Outputs in a tool-connected environment.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
gpt-oss-120b is OpenAI’s larger open-weight language model for general-purpose reasoning, coding and agentic work. It receives and produces text. The maker publishes 117 billion total parameters with 5.1 billion active parameters per token in a mixture-of-experts architecture. This is the 120b edition of the family, separate from gpt-oss-20b and the specialized Safeguard models.
The release describes a mostly English, text-only training set focused on STEM, coding and general knowledge. An illustrative task is analyzing an algorithm from its code and stated conditions: explain the important relationships, compare possible approaches and produce a concrete implementation proposal. For a document decision, provide the material and criteria, then request a conclusion tied to the evidence you supplied.
OpenAI’s published architecture has 36 layers, 128 experts and four active experts per token. The original release uses MXFP4 for the mixture-of-experts weights and describes the model running within one 80 GB GPU. OpenAI releases the weights under Apache 2.0 and supports fine-tuning for specialized use cases. These are properties of the producer’s published model and format, rather than a description of an application’s particular deployment.
The model documentation lists a 131,072-token context window and a maximum generated output of 131,072 tokens, with a knowledge cutoff of June 1, 2024. Input, reasoning and output must fit the available context. The supported reasoning levels are low, medium and high, allowing a task to request a short dialogue response or deeper analysis. OpenAI requires the Harmony format, which separates internal analysis from the final response; the maker states that raw analysis is intended for developer use rather than direct display to end users.
The producer documents function calling, web browsing, Python code execution through tools and Structured Outputs. Its model card also lists streaming, with function, code-interpreter, MCP and search capabilities in the documented tool environment. Applications provide operations, execute their actions and return actual results. A calculation or lookup can then become evidence for another reasoning step, while a proposed tool request remains distinct from an operation that has run.
Prepare a clear goal, definitions and the useful final artifact: an explanation, code proposal, formula or structured set of findings. Identify which facts must survive a transformation and how missing information should be represented. A useful final response connects its conclusion to the supplied conditions and any actual tool results. For a follow-up, carry the significant evidence and the decision still to be made into the next request.
POST /v1/batchestexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldendpoint | Typestring | RequirementRequired | Values & limits /v1/chat/completions | Default— |
Fieldmodel | Typestring | RequirementRequired | Values & limits openai/gpt-oss-120b: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/gpt-oss-120b:batch, openai/gpt-oss-120b | Default— |
Fieldprovider.only | Typestring[] | RequirementOptional | Values & limits deepinfra/bf16 | 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 $0.0000592 / 1K tokens Output · Output tokens $0.000272 / 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 includingNo upper bound | Charge Input · Input tokens $0.0000592 / 1K tokens Output · Output tokens $0.000272 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${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":"openai/gpt-oss-120b: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/gpt-oss-120b:batch', 'openai/gpt-oss-120b']: raise ValueError("body.model must be an exact documented caller or wire ID")\n return {"endpoint":"/v1/chat/completions", "model":"openai/gpt-oss-120b: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/gpt-oss-120b:batch
Use the method paths shown above.