GPT-6 Luna is OpenAI’s focused model for repeated, high-volume tasks. It accepts text and images and produces text, making it useful for defined operations such as classification, extraction, rewriting, image-grounded questions and individual steps in an assistant workflow. Luna retains its own profile within GPT-6, separate from Sol’s complex coding role, Astra’s most demanding work and Luna’s Pro execution setting.
Give each task a clear result: a category, a small record, an explanation or a revised passage. For classification, supply the category meanings and a convention for items that fit none. For extraction, define the fields, units and handling of absent information. A useful brief is: “Identify the user’s main issue, choose one of these categories and return the sentence that supports the choice.”
For a support response, provide the question and the relevant approved source material, then identify the answer language and the details to retain. For an image, preserve visible labels and tell the model what the question concerns. Keep extracted wording separate from interpretation so the resulting record can be checked against the input.
The producer supports none, low, medium, high, xhigh and max reasoning effort; medium is the default. None allows tasks that do not need intermediate reasoning, while greater effort can develop analysis for a more involved question. Reasoning effort and standard or Pro execution mode are independent choices. A narrow output contract is still needed at every effort level.
Structured Outputs can constrain a defined record, and ordinary text can communicate a short answer or explanation. Specify field meanings and missing-value conventions. Format validity does not establish that an extracted value is present in the source, so review content as well as structure.
The model card lists a 1,050,000-token context, up to 922,000 input tokens and up to 128,000 output tokens. Its knowledge cutoff is May 18, 2026. Source material, conversation, reasoning and the visible answer need room together. For repeated work, retain the criteria and source labels that matter instead of allowing unrelated history to obscure the operation.
OpenAI documents Responses for built-in tools and function calling. Chat Completions supports function calling for this model only when reasoning effort is none. The producer tool list includes web and file search, image-generation tooling, a code interpreter, shell and patch tools, skills, computer use, MCP connections and tool search. Luna’s own output is text; tool-produced images or executed actions are separate results.
The application performs selected operations and returns the observation for the next model step. A product lookup can provide the missing field before the answer is composed; an extraction task can use an actual retrieved passage. The GPT-6 guide also describes asynchronous tool work, steering and context-management capabilities at the family level.
A useful final result is a focused answer or record linked to the supplied evidence. Check its values, preserve mandatory terminology and keep current-source questions tied to authoritative material or real tool observations. Luna’s role is completing the defined operation, not turning a large source collection into an unspecified task.
", "aboutText": "GPT-6 Luna is OpenAI’s focused model for repeated, high-volume tasks. It accepts text and images and produces text, making it useful for defined operations such as classification, extraction, rewriting, image-grounded questions and individual steps in an assistant workflow. Luna retains its own profile within GPT-6, separate from Sol’s complex coding role, Astra’s most demanding work and Luna’s Pro execution setting.\n\n### Define a repeatable operation\n\nGive each task a clear result: a category, a small record, an explanation or a revised passage. For classification, supply the category meanings and a convention for items that fit none. For extraction, define the fields, units and handling of absent information. A useful brief is: “Identify the user’s main issue, choose one of these categories and return the sentence that supports the choice.”\n\nFor a support response, provide the question and the relevant approved source material, then identify the answer language and the details to retain. For an image, preserve visible labels and tell the model what the question concerns. Keep extracted wording separate from interpretation so the resulting record can be checked against the input.\n\n### Effort and output format\n\nThe producer supports none, low, medium, high, xhigh and max reasoning effort; medium is the default. None allows tasks that do not need intermediate reasoning, while greater effort can develop analysis for a more involved question. Reasoning effort and standard or Pro execution mode are independent choices. A narrow output contract is still needed at every effort level.\n\nStructured Outputs can constrain a defined record, and ordinary text can communicate a short answer or explanation. Specify field meanings and missing-value conventions. Format validity does not establish that an extracted value is present in the source, so review content as well as structure.\n\n### Context and knowledge\n\nThe model card lists a 1,050,000-token context, up to 922,000 input tokens and up to 128,000 output tokens. Its knowledge cutoff is May 18, 2026. Source material, conversation, reasoning and the visible answer need room together. For repeated work, retain the criteria and source labels that matter instead of allowing unrelated history to obscure the operation.\n\n### Tools and application results\n\nOpenAI documents Responses for built-in tools and function calling. Chat Completions supports function calling for this model only when reasoning effort is none. The producer tool list includes web and file search, image-generation tooling, a code interpreter, shell and patch tools, skills, computer use, MCP connections and tool search. Luna’s own output is text; tool-produced images or executed actions are separate results.\n\nThe application performs selected operations and returns the observation for the next model step. A product lookup can provide the missing field before the answer is composed; an extraction task can use an actual retrieved passage. The GPT-6 guide also describes asynchronous tool work, steering and context-management capabilities at the family level.\n\nA useful final result is a focused answer or record linked to the supplied evidence. Check its values, preserve mandatory terminology and keep current-source questions tied to authoritative material or real tool observations. Luna’s role is completing the defined operation, not turning a large source collection into an unspecified task.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "3c9ccbdf9126ed67d7811315eaf513fce22ff6f704ac0bc5cb8f3284d01f2180", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "openai/gpt-6-luna:batchGPT-6 Luna is OpenAI’s focused reasoning model for repeated, high-volume tasks. Text and images can support classification, extraction, assistance and tool-guided work, with a 1,050,000-token context, structured text output and an optional non-reasoning effort setting.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GPT-6 Luna is OpenAI’s focused model for repeated, high-volume tasks. It accepts text and images and produces text, making it useful for defined operations such as classification, extraction, rewriting, image-grounded questions and individual steps in an assistant workflow. Luna retains its own profile within GPT-6, separate from Sol’s complex coding role, Astra’s most demanding work and Luna’s Pro execution setting.
Give each task a clear result: a category, a small record, an explanation or a revised passage. For classification, supply the category meanings and a convention for items that fit none. For extraction, define the fields, units and handling of absent information. A useful brief is: “Identify the user’s main issue, choose one of these categories and return the sentence that supports the choice.”
For a support response, provide the question and the relevant approved source material, then identify the answer language and the details to retain. For an image, preserve visible labels and tell the model what the question concerns. Keep extracted wording separate from interpretation so the resulting record can be checked against the input.
The producer supports none, low, medium, high, xhigh and max reasoning effort; medium is the default. None allows tasks that do not need intermediate reasoning, while greater effort can develop analysis for a more involved question. Reasoning effort and standard or Pro execution mode are independent choices. A narrow output contract is still needed at every effort level.
Structured Outputs can constrain a defined record, and ordinary text can communicate a short answer or explanation. Specify field meanings and missing-value conventions. Format validity does not establish that an extracted value is present in the source, so review content as well as structure.
The model card lists a 1,050,000-token context, up to 922,000 input tokens and up to 128,000 output tokens. Its knowledge cutoff is May 18, 2026. Source material, conversation, reasoning and the visible answer need room together. For repeated work, retain the criteria and source labels that matter instead of allowing unrelated history to obscure the operation.
OpenAI documents Responses for built-in tools and function calling. Chat Completions supports function calling for this model only when reasoning effort is none. The producer tool list includes web and file search, image-generation tooling, a code interpreter, shell and patch tools, skills, computer use, MCP connections and tool search. Luna’s own output is text; tool-produced images or executed actions are separate results.
The application performs selected operations and returns the observation for the next model step. A product lookup can provide the missing field before the answer is composed; an extraction task can use an actual retrieved passage. The GPT-6 guide also describes asynchronous tool work, steering and context-management capabilities at the family level.
A useful final result is a focused answer or record linked to the supplied evidence. Check its values, preserve mandatory terminology and keep current-source questions tied to authoritative material or real tool observations. Luna’s role is completing the defined operation, not turning a large source collection into an unspecified task.
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-6-luna: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-6-luna:batch, openai/gpt-6-luna | 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 $0.0001 / 1K tokens Output · Output tokens $0.0005 / 1K tokens Input · Cache read $0.00001 / 1K tokens Input · Cache write $0.000125 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and including272,000 | Charge Input · Input tokens $0.0001 / 1K tokens Output · Output tokens $0.0005 / 1K tokens Input · Cache read $0.00001 / 1K tokens Input · Cache write $0.000125 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 2 | Rate schedule— | Context tokens, more than272,000 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0002 / 1K tokens Output · Output tokens $0.00075 / 1K tokens Input · Cache read $0.00002 / 1K tokens Input · Cache write $0.00025 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${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-6-luna: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-6-luna:batch', 'openai/gpt-6-luna']: raise ValueError("body.model must be an exact documented caller or wire ID")\n return {"endpoint":"/v1/chat/completions", "model":"openai/gpt-6-luna: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-6-luna:batch
Use the method paths shown above.