GPT-5.6 Luna is OpenAI’s focused model for high-volume workloads within the GPT-5.6 family. The maker relates its workload role to the smaller tier used in earlier GPT-5 families, while retaining Luna as its own model identity. It accepts text and images and generates text, including explanations, rewrites, classifications and structured records.
Give the model one defined operation and the criteria for a useful result. For extraction, name the fields, units and missing-value convention. For classification, supply the category meanings and identify what to do when none applies. An illustrative instruction is: “Extract the specification values from this passage, preserve their units and identify the sentence supporting each field.”
A support answer should use the supplied product or policy material and follow the user’s required language. For a visual question, identify the relevant image and visible detail. Keep the result concise enough for its downstream purpose without omitting a required source value or qualification.
The producer supports none, low, medium, high, xhigh and max effort, with medium as the default. Standard is the default reasoning mode, while Pro is a separate execution setting that adds model work. Effort and mode are independent; a routine direct task and a more involved comparison can therefore have different preparation needs while keeping the same named Luna profile.
The reasoning guide states that GPT-5.6 renders available reasoning from earlier turns by default, with a supported context setting that selects the behaviour. This affects the material retained across a multi-step task; it is not unlimited memory. Keep accepted facts, source labels and the required artifact clear through follow-ups.
OpenAI lists a 1,050,000-token context, a maximum input of 922,000 tokens and a maximum output of 128,000 tokens. The documented knowledge cutoff is February 16, 2026. Reasoning and the final response share the completion budget, and all task material needs space within the context. A request can end before a complete visible answer if those budgets are exhausted.
The model card lists Structured Outputs, streaming and function calling. The producer’s tool ecosystem includes web and file search, image-generation tooling, a code interpreter, shell and patch operations, skills, computer use, MCP connections and tool search. A structured record still needs values grounded in the actual input; JSON validity does not independently establish factual accuracy.
An application supplies functions, performs selected operations and returns observations. A lookup can supply a missing field before Luna composes the answer. Preserve the result with its source and operation, and distinguish a proposed action from work that has actually executed. The model’s own output is text, while a tool-generated image is a separate artifact.
Keep source-dependent claims tied to authoritative material and define when the operation is complete. A good deliverable is the requested record, explanation or revised passage with mandatory names and evidence intact. Luna’s focused role, supported effort range and standard-mode profile remain distinct from Terra, Sol, Pro execution and subsequent GPT-6 releases.
", "aboutText": "GPT-5.6 Luna is OpenAI’s focused model for high-volume workloads within the GPT-5.6 family. The maker relates its workload role to the smaller tier used in earlier GPT-5 families, while retaining Luna as its own model identity. It accepts text and images and generates text, including explanations, rewrites, classifications and structured records.\n\n### A precise repeated task\n\nGive the model one defined operation and the criteria for a useful result. For extraction, name the fields, units and missing-value convention. For classification, supply the category meanings and identify what to do when none applies. An illustrative instruction is: “Extract the specification values from this passage, preserve their units and identify the sentence supporting each field.”\n\nA support answer should use the supplied product or policy material and follow the user’s required language. For a visual question, identify the relevant image and visible detail. Keep the result concise enough for its downstream purpose without omitting a required source value or qualification.\n\n### Reasoning settings and retained context\n\nThe producer supports none, low, medium, high, xhigh and max effort, with medium as the default. Standard is the default reasoning mode, while Pro is a separate execution setting that adds model work. Effort and mode are independent; a routine direct task and a more involved comparison can therefore have different preparation needs while keeping the same named Luna profile.\n\nThe reasoning guide states that GPT-5.6 renders available reasoning from earlier turns by default, with a supported context setting that selects the behaviour. This affects the material retained across a multi-step task; it is not unlimited memory. Keep accepted facts, source labels and the required artifact clear through follow-ups.\n\n### Context and knowledge\n\nOpenAI lists a 1,050,000-token context, a maximum input of 922,000 tokens and a maximum output of 128,000 tokens. The documented knowledge cutoff is February 16, 2026. Reasoning and the final response share the completion budget, and all task material needs space within the context. A request can end before a complete visible answer if those budgets are exhausted.\n\n### Structured answers and tools\n\nThe model card lists Structured Outputs, streaming and function calling. The producer’s tool ecosystem includes web and file search, image-generation tooling, a code interpreter, shell and patch operations, skills, computer use, MCP connections and tool search. A structured record still needs values grounded in the actual input; JSON validity does not independently establish factual accuracy.\n\nAn application supplies functions, performs selected operations and returns observations. A lookup can supply a missing field before Luna composes the answer. Preserve the result with its source and operation, and distinguish a proposed action from work that has actually executed. The model’s own output is text, while a tool-generated image is a separate artifact.\n\n### A useful result\n\nKeep source-dependent claims tied to authoritative material and define when the operation is complete. A good deliverable is the requested record, explanation or revised passage with mandatory names and evidence intact. Luna’s focused role, supported effort range and standard-mode profile remain distinct from Terra, Sol, Pro execution and subsequent GPT-6 releases.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "ef720c2c745f6e2c7d234e3a120e2d33fad19ff9bfcc8072908f3a272ec44c5e", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "openai/gpt-5.6-luna:batchGPT-5.6 Luna is OpenAI’s focused model for repeated, high-volume workloads. It accepts text and images and returns answers or structured records, with optional reasoning, source-guided tools and a 1,050,000-token context kept separate from its Pro execution setting.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GPT-5.6 Luna is OpenAI’s focused model for high-volume workloads within the GPT-5.6 family. The maker relates its workload role to the smaller tier used in earlier GPT-5 families, while retaining Luna as its own model identity. It accepts text and images and generates text, including explanations, rewrites, classifications and structured records.
Give the model one defined operation and the criteria for a useful result. For extraction, name the fields, units and missing-value convention. For classification, supply the category meanings and identify what to do when none applies. An illustrative instruction is: “Extract the specification values from this passage, preserve their units and identify the sentence supporting each field.”
A support answer should use the supplied product or policy material and follow the user’s required language. For a visual question, identify the relevant image and visible detail. Keep the result concise enough for its downstream purpose without omitting a required source value or qualification.
The producer supports none, low, medium, high, xhigh and max effort, with medium as the default. Standard is the default reasoning mode, while Pro is a separate execution setting that adds model work. Effort and mode are independent; a routine direct task and a more involved comparison can therefore have different preparation needs while keeping the same named Luna profile.
The reasoning guide states that GPT-5.6 renders available reasoning from earlier turns by default, with a supported context setting that selects the behaviour. This affects the material retained across a multi-step task; it is not unlimited memory. Keep accepted facts, source labels and the required artifact clear through follow-ups.
OpenAI lists a 1,050,000-token context, a maximum input of 922,000 tokens and a maximum output of 128,000 tokens. The documented knowledge cutoff is February 16, 2026. Reasoning and the final response share the completion budget, and all task material needs space within the context. A request can end before a complete visible answer if those budgets are exhausted.
The model card lists Structured Outputs, streaming and function calling. The producer’s tool ecosystem includes web and file search, image-generation tooling, a code interpreter, shell and patch operations, skills, computer use, MCP connections and tool search. A structured record still needs values grounded in the actual input; JSON validity does not independently establish factual accuracy.
An application supplies functions, performs selected operations and returns observations. A lookup can supply a missing field before Luna composes the answer. Preserve the result with its source and operation, and distinguish a proposed action from work that has actually executed. The model’s own output is text, while a tool-generated image is a separate artifact.
Keep source-dependent claims tied to authoritative material and define when the operation is complete. A good deliverable is the requested record, explanation or revised passage with mandatory names and evidence intact. Luna’s focused role, supported effort range and standard-mode profile remain distinct from Terra, Sol, Pro execution and subsequent GPT-6 releases.
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-5.6-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-5.6-luna:batch, openai/gpt-5.6-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 $0.0002 / 1K tokens Output · Output tokens $0.0012 / 1K tokens Input · Cache read $0.00002 / 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 including272,000 | Charge Input · Input tokens $0.0002 / 1K tokens Output · Output tokens $0.0012 / 1K tokens Input · Cache read $0.00002 / 1K tokens Input · Cache write — / 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 $0.0004 / 1K tokens Output · Output tokens $0.0018 / 1K tokens Input · Cache read $0.00004 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${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-5.6-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-5.6-luna:batch', 'openai/gpt-5.6-luna']: raise ValueError("body.model must be an exact documented caller or wire ID")\n return {"endpoint":"/v1/chat/completions", "model":"openai/gpt-5.6-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-5.6-luna:batch
Use the method paths shown above.