GPT-5.6 Sol is OpenAI’s flagship model within the GPT-5.6 family for complex professional work. It corresponds to the main model tier used in earlier GPT-5 families, while remaining its own named edition. It accepts text and images and generates text, including analysis, code, documents and structured findings. Its standard profile is distinct from Sol’s Pro reasoning execution.
Define the outcome, relevant sources and the conditions that a result must satisfy. For software work, provide the relevant files or excerpts, observed behaviour, expected behaviour and constraints. For professional analysis, identify the decision, comparison criteria and evidence. An illustrative instruction is: “Compare these approaches with the specification, identify the dependencies and produce a recommendation with the source condition supporting each finding.”
If images contain evidence, label them and specify the chart, diagram or interface element to analyse. Ask the answer to separate the observed detail from interpretation. For writing or editing, give the intended reader and facts to retain, then name the final artifact and its required structure.
The producer supports none, low, medium, high, xhigh and max effort, with medium as the default. Standard reasoning mode is the default; Pro adds model work for difficult tasks. These are independent controls, so effort does not itself change the named model or make Pro a new base edition.
The GPT-5.6 reasoning profile defaults to rendering available reasoning from previous turns into the next step, with a context setting for supported workflows. Keep accepted requirements and observations clear through the conversation, and preserve the distinction between an intermediate idea and a final finding. Retained material still consumes context.
Sol’s card lists a 1,050,000-token context, up to 922,000 input tokens and up to 128,000 output tokens, with a February 16, 2026 knowledge cutoff. Reasoning consumes response space even when it is not displayed as the final answer. Leave room for tool results and the completed artifact, and inspect a response that reaches its budget before using it.
Organise long documents and code around the actual question. Keep source labels and relevant boundaries so a conclusion can identify the material on which it depends. For current facts, provide authoritative passages or suitable lookup tools rather than relying on the cutoff-era training knowledge.
OpenAI lists Structured Outputs, streaming and function calling. The documented tools include web and file search, image generation, a code interpreter, shell and patch operations, skills, computer use, MCP connections and tool search. The application supplies and executes its operations, returning observations for the next model step. The model’s own output remains text, while tool-produced media or actions have their own results.
Give functions specific purposes and schemas. For a data record, define field meanings and missing-value conventions. Check values against sources and code against the requested behaviour. A useful handoff presents the result, evidence and unresolved conditions clearly; a proposed operation or validation command is distinct from actual executed work.
GPT-5.6 Sol is distinct from Terra, Luna and subsequent GPT-6 models; OpenAI’s gpt-5.6 alias points to Sol. Preserve that profile when the task depends on its knowledge cutoff, reasoning controls or context limits.
", "aboutText": "GPT-5.6 Sol is OpenAI’s flagship model within the GPT-5.6 family for complex professional work. It corresponds to the main model tier used in earlier GPT-5 families, while remaining its own named edition. It accepts text and images and generates text, including analysis, code, documents and structured findings. Its standard profile is distinct from Sol’s Pro reasoning execution.\n\n### Prepare demanding work\n\nDefine the outcome, relevant sources and the conditions that a result must satisfy. For software work, provide the relevant files or excerpts, observed behaviour, expected behaviour and constraints. For professional analysis, identify the decision, comparison criteria and evidence. An illustrative instruction is: “Compare these approaches with the specification, identify the dependencies and produce a recommendation with the source condition supporting each finding.”\n\nIf images contain evidence, label them and specify the chart, diagram or interface element to analyse. Ask the answer to separate the observed detail from interpretation. For writing or editing, give the intended reader and facts to retain, then name the final artifact and its required structure.\n\n### Effort, execution and continuing context\n\nThe producer supports none, low, medium, high, xhigh and max effort, with medium as the default. Standard reasoning mode is the default; Pro adds model work for difficult tasks. These are independent controls, so effort does not itself change the named model or make Pro a new base edition.\n\nThe GPT-5.6 reasoning profile defaults to rendering available reasoning from previous turns into the next step, with a context setting for supported workflows. Keep accepted requirements and observations clear through the conversation, and preserve the distinction between an intermediate idea and a final finding. Retained material still consumes context.\n\n### Limits and source preparation\n\nSol’s card lists a 1,050,000-token context, up to 922,000 input tokens and up to 128,000 output tokens, with a February 16, 2026 knowledge cutoff. Reasoning consumes response space even when it is not displayed as the final answer. Leave room for tool results and the completed artifact, and inspect a response that reaches its budget before using it.\n\nOrganise long documents and code around the actual question. Keep source labels and relevant boundaries so a conclusion can identify the material on which it depends. For current facts, provide authoritative passages or suitable lookup tools rather than relying on the cutoff-era training knowledge.\n\n### Tools and outputs\n\nOpenAI lists Structured Outputs, streaming and function calling. The documented tools include web and file search, image generation, a code interpreter, shell and patch operations, skills, computer use, MCP connections and tool search. The application supplies and executes its operations, returning observations for the next model step. The model’s own output remains text, while tool-produced media or actions have their own results.\n\nGive functions specific purposes and schemas. For a data record, define field meanings and missing-value conventions. Check values against sources and code against the requested behaviour. A useful handoff presents the result, evidence and unresolved conditions clearly; a proposed operation or validation command is distinct from actual executed work.\n\nGPT-5.6 Sol is distinct from Terra, Luna and subsequent GPT-6 models; OpenAI’s gpt-5.6 alias points to Sol. Preserve that profile when the task depends on its knowledge cutoff, reasoning controls or context limits.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "4f2b9deb1ba4d12ae2e172fbb035aa85e34bdefc74059aa6addc17e5252c76f2", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "openai/gpt-5.6-sol:batchGPT-5.6 Sol is OpenAI’s flagship GPT-5.6 model for complex professional work. It combines text and image understanding, configurable reasoning and tools with a 1,050,000-token context to produce code, analysis and source-backed documents.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GPT-5.6 Sol is OpenAI’s flagship model within the GPT-5.6 family for complex professional work. It corresponds to the main model tier used in earlier GPT-5 families, while remaining its own named edition. It accepts text and images and generates text, including analysis, code, documents and structured findings. Its standard profile is distinct from Sol’s Pro reasoning execution.
Define the outcome, relevant sources and the conditions that a result must satisfy. For software work, provide the relevant files or excerpts, observed behaviour, expected behaviour and constraints. For professional analysis, identify the decision, comparison criteria and evidence. An illustrative instruction is: “Compare these approaches with the specification, identify the dependencies and produce a recommendation with the source condition supporting each finding.”
If images contain evidence, label them and specify the chart, diagram or interface element to analyse. Ask the answer to separate the observed detail from interpretation. For writing or editing, give the intended reader and facts to retain, then name the final artifact and its required structure.
The producer supports none, low, medium, high, xhigh and max effort, with medium as the default. Standard reasoning mode is the default; Pro adds model work for difficult tasks. These are independent controls, so effort does not itself change the named model or make Pro a new base edition.
The GPT-5.6 reasoning profile defaults to rendering available reasoning from previous turns into the next step, with a context setting for supported workflows. Keep accepted requirements and observations clear through the conversation, and preserve the distinction between an intermediate idea and a final finding. Retained material still consumes context.
Sol’s card lists a 1,050,000-token context, up to 922,000 input tokens and up to 128,000 output tokens, with a February 16, 2026 knowledge cutoff. Reasoning consumes response space even when it is not displayed as the final answer. Leave room for tool results and the completed artifact, and inspect a response that reaches its budget before using it.
Organise long documents and code around the actual question. Keep source labels and relevant boundaries so a conclusion can identify the material on which it depends. For current facts, provide authoritative passages or suitable lookup tools rather than relying on the cutoff-era training knowledge.
OpenAI lists Structured Outputs, streaming and function calling. The documented tools include web and file search, image generation, a code interpreter, shell and patch operations, skills, computer use, MCP connections and tool search. The application supplies and executes its operations, returning observations for the next model step. The model’s own output remains text, while tool-produced media or actions have their own results.
Give functions specific purposes and schemas. For a data record, define field meanings and missing-value conventions. Check values against sources and code against the requested behaviour. A useful handoff presents the result, evidence and unresolved conditions clearly; a proposed operation or validation command is distinct from actual executed work.
GPT-5.6 Sol is distinct from Terra, Luna and subsequent GPT-6 models; OpenAI’s gpt-5.6 alias points to Sol. Preserve that profile when the task depends on its knowledge cutoff, reasoning controls or context limits.
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-sol: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-sol:batch, openai/gpt-5.6-sol | 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 $0.002 / 1K tokens Output · Output tokens $0.01 / 1K tokens Input · Cache read $0.0002 / 1K tokens Input · Cache write $0.0025 / 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 $0.002 / 1K tokens Output · Output tokens $0.01 / 1K tokens Input · Cache read $0.0002 / 1K tokens Input · Cache write $0.0025 / 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 $0.004 / 1K tokens Output · Output tokens $0.015 / 1K tokens Input · Cache read $0.0004 / 1K tokens Input · Cache write $0.005 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${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-sol: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-sol:batch', 'openai/gpt-5.6-sol']: raise ValueError("body.model must be an exact documented caller or wire ID")\n return {"endpoint":"/v1/chat/completions", "model":"openai/gpt-5.6-sol: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-sol:batch
Use the method paths shown above.