{ "data": { "similar": [ { "grade": "B", "json": "https://www.anchorterminal.com/tools/convai-laya.json", "name": "Laya", "score": 69.2, "shared": [ "inference.decision" ], "slug": "convai-laya" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/jaredpalmer-kev.json", "name": "Kev", "score": 67.4, "shared": [ "inference.decision" ], "slug": "jaredpalmer-kev" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/vela.json", "name": "Vela 2.0", "score": 66.5, "shared": [ "inference.decision" ], "slug": "vela" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/cloudflare-clef.json", "name": "Clef", "score": 66.1, "shared": [ "inference.decision" ], "slug": "cloudflare-clef" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/typesafe-jev.json", "name": "Jev", "score": 62.1, "shared": [ "inference.decision" ], "slug": "typesafe-jev" }, { "grade": "C", "json": "https://www.anchorterminal.com/tools/strands-decider.json", "name": "Strands Decider 2B", "score": 61.3, "shared": [ "inference.decision" ], "slug": "strands-decider" } ], "tool": { "slug": "openai-decisions-api", "name": "OpenAI Decisions API", "vendor": "OpenAI", "vendorUrl": "https://developers.openai.com", "kind": "model", "category": "decision-models", "summary": "The Decisions API is an OpenAI endpoint, in public beta since 6 October 2026, that reads text and images and returns typed answers with probabilities, a predicate, a choice from a fixed set or a rubric score.", "url": "https://www.anchorterminal.com/tools/openai-decisions-api", "markdownUrl": "https://www.anchorterminal.com/tools/openai-decisions-api.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/openai-decisions-api.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/openai-decisions-api.json", "repo": "https://github.com/openai/openai-python", "license": "Proprietary service under OpenAI's services agreement. The official SDKs are Apache-2.0", "transports": [ "http" ], "remoteUrl": "https://api.openai.com/v1/decisions", "packages": [ { "registry": "pypi", "name": "openai" }, { "registry": "npm", "name": "openai" } ], "auth": "api-key", "authNotes": "`Authorization: Bearer` with an ordinary OpenAI project key, self-serve from the platform dashboard after sign-up. No waitlist or separate approval for the beta was found. Keys carry their own permissions under the access-control guide (https://developers.openai.com/api/docs/guides/rbac). We didn't confirm that a key can be restricted to `/v1/decisions` alone.", "pricing": "usage", "pricingNotes": "$0.10 per million input tokens on `gpt-6-luna`, with no output, cache-read or cache-write charge (https://developers.openai.com/api/docs/guides/decisions). Long-context input multipliers and regional processing premiums apply, which on GPT-6 Luna are 2x input over 272,000 tokens and 10 per cent. No sandbox. The rate-limits guide lists a Free tier capped at $100 a month, but GPT-6 Luna's limits start at the Build tier, reached with $5 of credit (https://developers.openai.com/api/docs/guides/rate-limits).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the Decisions guide, the API reference or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 31774, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://developers.openai.com/api/docs/guides/decisions", "llmsTxt": "https://developers.openai.com/llms.txt", "openapi": "https://github.com/openai/openai-openapi", "capabilities": [ "inference.decision" ], "tags": [ "official", "hosted", "model", "closed-source", "openapi", "llms-txt", "python", "typescript", "go", "java", "usage-priced", "status-page", "beta" ], "lastRelease": "2026-10-06", "graded": true, "anchor": { "graded": true, "score": 71.5, "grade": "BB", "agentReady": true, "rank": 102, "ranked": true, "rankOf": 629, "categoryRank": 1, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 87, "maintenance": 77, "payments": 30, "reliability": 53, "schema": 89, "security": 83, "transparency": 83 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "reliability", "name": "Reliability", "weight": 16, "effectiveWeight": 20, "score": 53, "points": 10.6, "reason": "Read as a hosted model API. status.openai.com has a Decisions component under APIs, reading 100 per cent on 8 October (20). The endpoint was released on 6 October, so its record is two days long. The incident feed, read back to 10 July, names Decisions in no incident. The platform under it had API-wide error incidents on 25 July, 17 September and 29 September (5 hours 22 minutes), all before the release, so 8 of 30 for a clean record too short to count, the reading given to Clef on its first day. The GPT-6 Luna page lists 5,000 requests and 2,000,000 tokens a minute on the Build tier, 10,000 and 10,000,000 on Launch and 30,000 and 180,000,000 on Grow, but its endpoint table doesn't list Decisions and the guide gives no limits of its own (10 of 15). The rate-limits guide covers `Retry-After` on 429 and 503, backoff with jitter and SDK retries, and a decision has no side effects, so a retry is safe (15). No SLA covering a beta endpoint was found. The Scale Tier page answered 403 on 8 October (0). Public beta (0)." }, { "key": "performance", "name": "Performance", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes." }, { "key": "schema", "name": "Schema \u0026 documentation", "weight": 13, "effectiveWeight": 16.25, "score": 89, "points": 14.46, "reason": "OpenAI's OpenAPI 3.1 document (version 2.3.0, committed 8 October) has `POST /decisions` with `DecisionRequest` and `DecisionResponse` schemas (25). llms.txt indexes the guide, and the guide and the reference page each have a Markdown twin (10). The guide says which question type fits which job and when to use Structured Outputs or function calling instead. No page of known limits for the model on this endpoint was found (16 of 20). Questions are a union discriminated on `type`, with 1 to 200 questions, 2 to 255 choices and 2 to 10 levels set in the schema and no extra properties allowed (15). The guide has examples in curl, JavaScript, Python, Go, Java and Ruby with sample responses. The OpenAPI operation documents only the 200 response, and errors are covered by the general error-codes guide (12 of 15). A dated changelog carries the release on 6 October. The only model ID is the alias `gpt-6-luna` with no dated snapshot, and the beta has no version of its own (11 of 15)." }, { "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "effectiveWeight": 16.25, "score": 87, "points": 14.14, "reason": "Read as an API an agent calls for a decision, the reading used for Jev. Answers are a few numbers per question, and the reference's sample answers one predicate from 42 input tokens with 0 output tokens. Up to 128 inline images a request. The usage object reports cached tokens and the guide says cache reads and writes aren't charged. `/v1/decisions` isn't among the endpoints the Batch guide lists, and the guide states no context limit for the endpoint (20 of 25). The caller sets the whole output shape, with up to 200 independent questions about one input in a call (18 of 20). The error-codes guide gives types, codes and recovery steps for 400, 401, 403, 429, 500 and 503, and a question the model declines comes back as a typed `refusal` answer beside the others. Errors particular to the endpoint aren't documented (16 of 20). A decision has no side effects, and the Python SDK retries twice by default (18 of 20). Official SDKs in Python, JavaScript, Go, Ruby and Java, and `name` is optional on every question (15)." }, { "key": "security", "name": "Security \u0026 auth", "weight": 14, "effectiveWeight": 17.5, "score": 83, "points": 14.53, "reason": "Read for a model API, on the lines used for Jev. Project API keys, with the access-control guide saying a key carries its own permissions that are checked against the caller's project role, service-account keys created through the Administration API with a documented rotation procedure, and workload identity federation with short-lived tokens. We didn't confirm that a restricted key can be limited to `/v1/decisions`, since the help centre article answered 403 (27 of 30). The data-controls guide lists `/v1/decisions` as not used for training, with abuse-monitoring logs kept up to 30 days and Zero Data Retention for eligible customers. An image flagged by the CSAM classifier is kept for review under any setting, and the Private Retention column reads pending confirmation (18 of 20). The endpoint judges text and images that often come from users. Neither the guide nor the reference mentions adversarial or injected content. The safety guide advises red-teaming and limiting input length, and requests accept a `safety_identifier` (6 of 15). Each response reports token usage, and the Admin APIs guide documents audit-log retrieval. We didn't confirm how Decisions calls appear in usage views (12 of 15). security.txt is PGP-signed and names a Bugcrowd bounty and a coordinated disclosure policy, though it has no Expires field, and trust.openai.com names SOC 2 Type 2 and ISO/IEC 27001, 27017, 27018, 27701 and 42001 (20)." }, { "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "effectiveWeight": 12.5, "score": 30, "points": 3.75, "reason": "No x402, MPP or L402 in the guide, the reference or the pricing page (0). Per-token price published without a login, $0.10 per million input tokens with no output or cache charge (20). The rate-limits guide lists a Free tier capped at $100 a month in allowed countries, but the GPT-6 Luna page's rate-limit table starts at Build, which needs $5 of credit, and the Decisions guide doesn't mention a free allowance, so half, as for the OpenAI API listing (10). A person signs up in a browser and creates a key (0)." }, { "key": "tasks", "name": "Task success", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored." }, { "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7, "effectiveWeight": 8.75, "score": 77, "points": 6.74, "reason": "Read for a closed model, on the lines used for Jev. Released in beta on 6 October 2026 (30). OpenAI publishes minimum notice of 6 months for generally available models and 3 months for specialised variants, and says preview models can go with 2 weeks. Nothing states what a beta endpoint gets (6 of 12). Two days old with one model alias and no dated snapshot, too short to show churn (4 of 8). A dated changelog with several entries a month, including this release. The help centre answered 403 and issue replies weren't sampled (12 of 15). Official SDKs gained Decisions on release day, Python 3.26.0 and JavaScript 7.30.0 on 6 October, with 3.26.1 and 7.30.1 on 8 October, and the guide names Go 3.73.0, Ruby 0.101.0 and Java 4.78.0 (15). The Python SDK states Python 3.10 or later, the JavaScript SDK Node 22 or later, and the Python repository carries CI and breaking-change workflows (10)." }, { "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "effectiveWeight": 8.75, "score": 83, "points": 7.26, "note": "editorial 71, provenance 94", "reason": "Closed service with Apache-2.0 SDKs and an MIT OpenAPI repository. The services agreement answered 403 on 8 October, so its terms stand per the OpenAI API listing's earlier check (15). The data-controls guide, read on 8 October, gives `/v1/decisions` its own row and section covering training, 30-day abuse logs, Zero Data Retention, the 24-hour prompt cache and HIPAA eligibility. One column reads pending confirmation, and the DPA wasn't re-read (403), per the 4 October check on the OpenAI API listing (26 of 30). The deprecations page gives dated notices and minimum notice periods for models. It says nothing about beta endpoints, and the guide gives no date for general availability (14 of 20). The guide lists ten data-residency regions with Decisions in each, and regional processing for it in the United States and Europe. The subprocessor list answered 403 on 8 October, per the 4 October check (16 of 20)." } ], "assessment": { "date": "2026-10-08", "basis": "public evidence", "confidence": "medium", "notes": { "ergonomics": "Read as an API an agent calls for a decision, the reading used for Jev. Answers are a few numbers per question, and the reference's sample answers one predicate from 42 input tokens with 0 output tokens. Up to 128 inline images a request. The usage object reports cached tokens and the guide says cache reads and writes aren't charged. `/v1/decisions` isn't among the endpoints the Batch guide lists, and the guide states no context limit for the endpoint (20 of 25). The caller sets the whole output shape, with up to 200 independent questions about one input in a call (18 of 20). The error-codes guide gives types, codes and recovery steps for 400, 401, 403, 429, 500 and 503, and a question the model declines comes back as a typed `refusal` answer beside the others. Errors particular to the endpoint aren't documented (16 of 20). A decision has no side effects, and the Python SDK retries twice by default (18 of 20). Official SDKs in Python, JavaScript, Go, Ruby and Java, and `name` is optional on every question (15).", "maintenance": "Read for a closed model, on the lines used for Jev. Released in beta on 6 October 2026 (30). OpenAI publishes minimum notice of 6 months for generally available models and 3 months for specialised variants, and says preview models can go with 2 weeks. Nothing states what a beta endpoint gets (6 of 12). Two days old with one model alias and no dated snapshot, too short to show churn (4 of 8). A dated changelog with several entries a month, including this release. The help centre answered 403 and issue replies weren't sampled (12 of 15). Official SDKs gained Decisions on release day, Python 3.26.0 and JavaScript 7.30.0 on 6 October, with 3.26.1 and 7.30.1 on 8 October, and the guide names Go 3.73.0, Ruby 0.101.0 and Java 4.78.0 (15). The Python SDK states Python 3.10 or later, the JavaScript SDK Node 22 or later, and the Python repository carries CI and breaking-change workflows (10).", "payments": "No x402, MPP or L402 in the guide, the reference or the pricing page (0). Per-token price published without a login, $0.10 per million input tokens with no output or cache charge (20). The rate-limits guide lists a Free tier capped at $100 a month in allowed countries, but the GPT-6 Luna page's rate-limit table starts at Build, which needs $5 of credit, and the Decisions guide doesn't mention a free allowance, so half, as for the OpenAI API listing (10). A person signs up in a browser and creates a key (0).", "reliability": "Read as a hosted model API. status.openai.com has a Decisions component under APIs, reading 100 per cent on 8 October (20). The endpoint was released on 6 October, so its record is two days long. The incident feed, read back to 10 July, names Decisions in no incident. The platform under it had API-wide error incidents on 25 July, 17 September and 29 September (5 hours 22 minutes), all before the release, so 8 of 30 for a clean record too short to count, the reading given to Clef on its first day. The GPT-6 Luna page lists 5,000 requests and 2,000,000 tokens a minute on the Build tier, 10,000 and 10,000,000 on Launch and 30,000 and 180,000,000 on Grow, but its endpoint table doesn't list Decisions and the guide gives no limits of its own (10 of 15). The rate-limits guide covers `Retry-After` on 429 and 503, backoff with jitter and SDK retries, and a decision has no side effects, so a retry is safe (15). No SLA covering a beta endpoint was found. The Scale Tier page answered 403 on 8 October (0). Public beta (0).", "schema": "OpenAI's OpenAPI 3.1 document (version 2.3.0, committed 8 October) has `POST /decisions` with `DecisionRequest` and `DecisionResponse` schemas (25). llms.txt indexes the guide, and the guide and the reference page each have a Markdown twin (10). The guide says which question type fits which job and when to use Structured Outputs or function calling instead. No page of known limits for the model on this endpoint was found (16 of 20). Questions are a union discriminated on `type`, with 1 to 200 questions, 2 to 255 choices and 2 to 10 levels set in the schema and no extra properties allowed (15). The guide has examples in curl, JavaScript, Python, Go, Java and Ruby with sample responses. The OpenAPI operation documents only the 200 response, and errors are covered by the general error-codes guide (12 of 15). A dated changelog carries the release on 6 October. The only model ID is the alias `gpt-6-luna` with no dated snapshot, and the beta has no version of its own (11 of 15).", "security": "Read for a model API, on the lines used for Jev. Project API keys, with the access-control guide saying a key carries its own permissions that are checked against the caller's project role, service-account keys created through the Administration API with a documented rotation procedure, and workload identity federation with short-lived tokens. We didn't confirm that a restricted key can be limited to `/v1/decisions`, since the help centre article answered 403 (27 of 30). The data-controls guide lists `/v1/decisions` as not used for training, with abuse-monitoring logs kept up to 30 days and Zero Data Retention for eligible customers. An image flagged by the CSAM classifier is kept for review under any setting, and the Private Retention column reads pending confirmation (18 of 20). The endpoint judges text and images that often come from users. Neither the guide nor the reference mentions adversarial or injected content. The safety guide advises red-teaming and limiting input length, and requests accept a `safety_identifier` (6 of 15). Each response reports token usage, and the Admin APIs guide documents audit-log retrieval. We didn't confirm how Decisions calls appear in usage views (12 of 15). security.txt is PGP-signed and names a Bugcrowd bounty and a coordinated disclosure policy, though it has no Expires field, and trust.openai.com names SOC 2 Type 2 and ISO/IEC 27001, 27017, 27018, 27701 and 42001 (20).", "transparency": "Closed service with Apache-2.0 SDKs and an MIT OpenAPI repository. The services agreement answered 403 on 8 October, so its terms stand per the OpenAI API listing's earlier check (15). The data-controls guide, read on 8 October, gives `/v1/decisions` its own row and section covering training, 30-day abuse logs, Zero Data Retention, the 24-hour prompt cache and HIPAA eligibility. One column reads pending confirmation, and the DPA wasn't re-read (403), per the 4 October check on the OpenAI API listing (26 of 30). The deprecations page gives dated notices and minimum notice periods for models. It says nothing about beta endpoints, and the guide gives no date for general availability (14 of 20). The guide lists ten data-residency regions with Decisions in each, and regional processing for it in the United States and Europe. The subprocessor list answered 403 on 8 October, per the 4 October check (16 of 20)." }, "sources": [ { "what": "Decisions guide", "url": "https://developers.openai.com/api/docs/guides/decisions.md", "seen": "2026-10-08" }, { "what": "Decisions API reference, create a decision", "url": "https://developers.openai.com/api/reference/resources/decisions/methods/create", "seen": "2026-10-08" }, { "what": "voice with Decisions guide", "url": "https://developers.openai.com/api/docs/guides/decisions-voice.md", "seen": "2026-10-08" }, { "what": "changelog, release entry of 6 October", "url": "https://developers.openai.com/api/docs/changelog.md", "seen": "2026-10-08" }, { "what": "GPT-6 Luna model page, limits and endpoints", "url": "https://developers.openai.com/api/docs/models/gpt-6-luna.md", "seen": "2026-10-08" }, { "what": "pricing", "url": "https://developers.openai.com/api/docs/pricing.md", "seen": "2026-10-08" }, { "what": "data controls, /v1/decisions row and residency", "url": "https://developers.openai.com/api/docs/guides/your-data.md", "seen": "2026-10-08" }, { "what": "rate limits, usage tiers and retry guidance", "url": "https://developers.openai.com/api/docs/guides/rate-limits.md", "seen": "2026-10-08" }, { "what": "error codes", "url": "https://developers.openai.com/api/docs/guides/error-codes.md", "seen": "2026-10-08" }, { "what": "Batch guide, supported endpoints", "url": "https://developers.openai.com/api/docs/guides/batch.md", "seen": "2026-10-08" }, { "what": "deprecations and notice periods", "url": "https://developers.openai.com/api/docs/deprecations.md", "seen": "2026-10-08" }, { "what": "access control guide", "url": "https://developers.openai.com/api/docs/guides/rbac.md", "seen": "2026-10-08" }, { "what": "Admin APIs guide, audit logs", "url": "https://developers.openai.com/api/docs/guides/admin-apis.md", "seen": "2026-10-08" }, { "what": "service accounts and key rotation", "url": "https://developers.openai.com/api/docs/guides/terraform/service-accounts.md", "seen": "2026-10-08" }, { "what": "safety best practices", "url": "https://developers.openai.com/api/docs/guides/safety-best-practices.md", "seen": "2026-10-08" }, { "what": "llms.txt for the API docs", "url": "https://developers.openai.com/api/docs/llms.txt", "seen": "2026-10-08" }, { "what": "OpenAPI repository, openapi.json", "url": "https://github.com/openai/openai-openapi", "seen": "2026-10-08" }, { "what": "openai-python changelog and source", "url": "https://github.com/openai/openai-python", "seen": "2026-10-08" }, { "what": "openai on PyPI (JSON)", "url": "https://pypi.org/pypi/openai/json", "seen": "2026-10-08" }, { "what": "npm openai", "url": "https://registry.npmjs.org/openai", "seen": "2026-10-08" }, { "what": "status page, Decisions component", "url": "https://status.openai.com/", "seen": "2026-10-08" }, { "what": "status incident feed", "url": "https://status.openai.com/history.rss", "seen": "2026-10-08" }, { "what": "incident of 29 September", "url": "https://status.openai.com/incidents/01M3Q4RK1SM4EMK445GGPG7C0N", "seen": "2026-10-08" }, { "what": "security.txt", "url": "https://openai.com/.well-known/security.txt", "seen": "2026-10-08" }, { "what": "trust portal, certifications", "url": "https://trust.openai.com/", "seen": "2026-10-08" }, { "what": "RDAP for openai.com", "url": "https://rdap.verisign.com/com/v1/domain/openai.com", "seen": "2026-10-08" } ], "openQuestions": [ "The scout gave the launch as unconfirmed, with press naming 29 September. The API changelog dates the beta release 6 October 2026, and openai-python added Decisions in 3.26.0 the same day. Whether a limited preview ran earlier wasn't established", "Which rate limits apply to `/v1/decisions`. The GPT-6 Luna page gives the model's limits and its endpoint table doesn't list Decisions", "The context limit on this endpoint. The guide gives none, and GPT-6 Luna's page gives 922,000 input tokens for the model", "Whether the Free tier reaches `/v1/decisions`, and whether it needs a card", "Whether a restricted project key can be limited to `/v1/decisions`, and how Decisions calls appear in usage views", "Whether failed or refused questions are charged", "The Mixpanel breach of November 2025 carries a deduction of 2 on three OpenAI listings and none on the OpenAI API listing. We took none here, since the endpoint is eleven months younger than the incident and the source page answered 403 on 8 October. An editor should settle this across the OpenAI listings", "openai.com/.well-known/security.txt has no Expires field, which RFC 9116 requires. The provenance block says valid, as the other OpenAI listings do", "unchecked: the services agreement, privacy policy, DPA and subprocessor list (openai.com answered 403 on 8 October). These stand per the OpenAI API listing's checks of 26 September and 4 October", "unchecked: the Scale Tier SLA page (403), so no SLA was scored", "unchecked: the help centre articles on API key permissions and support (help.openai.com answered 403)", "unchecked: the Playground at platform.openai.com/decisions, which needs a login", "unchecked: issue reply times on openai-python. The GitHub API refused us for its rate limit" ] }, "negative": 0, "verdict": "Typed predicate, choice and score answers with probabilities, up to 200 questions a call, at $0.10 per million input tokens with no output charge. It is a public beta released on 6 October 2026, with one model alias, no dated snapshot, no Batch route and no SLA found.", "bestFor": "High-volume yes or no checks, routing among fixed options and rubric scoring over text and images, for teams already on an OpenAI key.", "strengths": [ "Three typed question kinds, predicate, choice and score, with per-option probabilities and up to 200 questions about one input in a call", "$0.10 per million input tokens on `gpt-6-luna`, with no output, cache-read or cache-write charge", "Text and up to 128 inline images in one request", "The official OpenAPI 3.1 document carries `POST /decisions` with typed limits, and five official SDKs support it", "Not used for training by default, eligible for Zero Data Retention and HIPAA use, per OpenAI's data-controls guide" ], "weaknesses": [ "Public beta released on 6 October 2026. The guide expects general availability in the coming weeks and gives no date", "One model alias, `gpt-6-luna`, with no dated snapshot to pin", "Images must be inline base64 data URLs. Hosted image URLs and `file_id` inputs aren't accepted", "Not among the endpoints the Batch guide lists, and no SLA covering it was found", "No guidance on adversarial or injected content was found in the guide or the reference" ], "agentNotes": [ "Put independent questions about one input in a single `questions` array. Send a separate request when a question depends on an earlier answer", "Check each answer's `type` before reading it. A question can come back as `refusal` while the others in the same request are answered", "Encode images as base64 data URLs. Hosted URLs and `file_id` inputs are rejected", "Give a `choice` question a fallback value such as `other`, and set thresholds from your own labelled examples", "Use Python SDK 3.26.0 or JavaScript 7.30.0 or later, and follow `Retry-After` on 429 and 503" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 71.5 } ], "editorialScores": { "ergonomics": 87, "maintenance": 77, "payments": 30, "reliability": 53, "schema": 89, "security": 83, "transparency": 71 }, "provenanceScore": 94 }, "connect": { "install": "pip install openai # or: npm i openai", "http": "curl https://api.openai.com/v1/decisions \\\n -H \"Authorization: Bearer $OPENAI_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"gpt-6-luna\",\"input\":\"I was charged twice for my order.\",\"questions\":[{\"type\":\"choice\",\"name\":\"department\",\"instructions\":\"Which department should handle this complaint?\",\"choices\":[{\"value\":\"billing\",\"description\":\"Payments, invoices, and refunds.\"},{\"value\":\"technical\",\"description\":\"Problems using the product.\"},{\"value\":\"other\",\"description\":\"Requests outside these categories.\"}]}]}'" }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/openai-decisions-api" }, "sameCompany": [ "openai-api", "openai-embeddings", "openai-moderation", "openai-image-api", "openai-sora", "openai-agents-sdk", "openai-codex" ], "notable": [ "The API changelog dates the release 6 October 2026, in beta with `gpt-6-luna`, and the guide says OpenAI expects general availability in the coming weeks (https://developers.openai.com/api/docs/changelog)", "The guide says the endpoint answers about 10 times faster than the Responses API. That is OpenAI's claim, and we haven't measured it (https://developers.openai.com/api/docs/guides/decisions)", "A `score` answer is the probability-weighted average of the level indices, so it can fall between levels, and `choice` and `score` answers carry a probability per option and a separate `confidence` (https://developers.openai.com/api/docs/guides/decisions)", "A request takes 1 to 200 questions, a choice 2 to 255 options and a score 2 to 10 levels, per the OpenAPI document (https://github.com/openai/openai-openapi)", "Up to 128 images a request, as inline base64 data URLs only. External URLs, files, audio, tools and other message roles aren't supported (https://developers.openai.com/api/reference/resources/decisions/methods/create)", "A question can return a `refusal` answer while other questions in the same request are answered (https://developers.openai.com/api/reference/resources/decisions/methods/create)", "The data-controls guide lists `/v1/decisions` as not used for training, with abuse-monitoring logs up to 30 days, Zero Data Retention for eligible customers and HIPAA eligibility under a business associate agreement (https://developers.openai.com/api/docs/guides/your-data)", "The request shape differs from the `/v1/systemone` shape that Jev, Clef, Kev and Laya share. It uses `input`, a `questions` array and `predicate` where they use `state`, a questions object and `noul` (https://developers.openai.com/api/docs/guides/decisions)", "A second guide pairs Decisions with the Live API, so a voice session hands action selection to a Decisions call (https://developers.openai.com/api/docs/guides/decisions-voice)" ], "area": "models", "details": [ { "label": "Status", "value": "Public beta, released 6 October 2026. General availability expected in the coming weeks, no date given" }, { "label": "Question types", "value": "predicate (a probability from 0 to 1), choice (one of 2 to 255 supplied values) and score (2 to 10 ordered levels). 1 to 200 questions a request" }, { "label": "Model", "value": "gpt-6-luna only, an alias with no dated snapshot" }, { "label": "Input", "value": "A text string, or user messages with text and up to 128 inline base64 images. No image URLs, file IDs, audio or tools" }, { "label": "Context", "value": "Not stated for the endpoint. GPT-6 Luna's page gives 922,000 input tokens for the model" }, { "label": "Rate limits", "value": "Not stated for the endpoint. GPT-6 Luna is 5,000 requests and 2,000,000 tokens a minute on Build, 30,000 and 180,000,000 on Grow" }, { "label": "Batch", "value": "Not among the endpoints the Batch guide lists" }, { "label": "Trains on API data", "value": "No, per the data-controls guide" }, { "label": "Data retention", "value": "Abuse-monitoring logs up to 30 days. Zero Data Retention for eligible customers. Images flagged by the CSAM classifier are kept for review" }, { "label": "Data residency", "value": "Available in all ten API regions. Regional processing in the United States and Europe (EEA and Switzerland)" }, { "label": "SDKs", "value": "Python 3.26.0, JavaScript 7.30.0, Go 3.73.0, Ruby 0.101.0 and Java 4.78.0 or later" }, { "label": "Status page", "value": "status.openai.com, with a Decisions component under APIs" } ], "unitPrices": [ { "item": "gpt-6-luna input on /v1/decisions", "unit": "1m-tokens", "usd": 0.1, "note": "No output, cache-read or cache-write charge" } ], "provenance": { "legalEntity": "OpenAI OpCo, LLC", "domain": "openai.com", "domainRegistered": "2007-01-19", "endpointOnVendorDomain": true, "terms": "https://openai.com/policies/services-agreement/", "privacy": "https://openai.com/policies/privacy-policy/", "statusPage": "https://status.openai.com", "changelog": "https://developers.openai.com/api/docs/changelog", "securityTxt": "valid", "checked": "2026-10-08", "notes": [ "Same entity, terms and privacy policy as the OpenAI API listing. openai.com answered 403 to our reader on 8 October, so the legal entity and the two policy URLs stand per that listing's check of 26 September and weren't re-read.", "RDAP gives openai.com a registration date of 2007-01-19, before OpenAI existed.", "status.openai.com lists a Decisions component under APIs, read on 8 October.", "The changelog entry for the release is dated 6 October 2026.", "openai.com/.well-known/security.txt is PGP-signed and names a Bugcrowd contact and a disclosure policy. It has no Expires field, which RFC 9116 requires." ], "score": 94, "checks": [ { "check": "Legal entity named", "value": "OpenAI OpCo, LLC", "points": 20, "max": 20, "state": "ok" }, { "check": "Domain age", "value": "openai.com, registered 2007-01-19 (19 years)", "points": 15, "max": 15, "state": "ok" }, { "check": "Endpoint on the vendor's domain", "value": "api.openai.com", "points": 15, "max": 15, "state": "ok" }, { "check": "Terms of service", "value": "published, but our reader couldn't read it", "points": 7, "max": 10, "state": "part" }, { "check": "Privacy policy", "value": "published, but our reader couldn't read it", "points": 7, "max": 10, "state": "part" }, { "check": "Status page", "value": "status.openai.com", "points": 10, "max": 10, "state": "ok" }, { "check": "Changelog", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "security.txt", "value": "valid", "points": 10, "max": 10, "state": "ok" } ], "policies": [ { "kind": "terms", "url": "https://openai.com/policies/services-agreement/", "state": "unreadable", "reason": "the page answered HTTP 403 to our reader", "readAt": "2026-10-08", "points": 7, "max": 10 }, { "kind": "privacy", "url": "https://openai.com/policies/privacy-policy/", "state": "unreadable", "reason": "the page answered HTTP 403 to our reader", "readAt": "2026-10-08", "points": 7, "max": 10 } ] }, "pageJsonUrl": "https://www.anchorterminal.com/tools/openai-decisions-api.json", "live": { "slug": "openai-decisions-api", "probe": { "target": "https://api.openai.com/v1/decisions", "method": "get", "lastAt": "2026-10-08T17:36:41.834725212Z", "lastOk": true, "lastStatus": 404, "lastMs": 132, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 145, "p95ms24h": 203, "samples24h": 25, "samples30d": 25, "days": [ { "date": "2026-10-08", "probes": 25, "ok": 25 } ] }, "vendorStatus": { "page": "https://status.openai.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-08T17:25:26.440695344Z" }, "versions": [ { "registry": "github", "name": "openai/openai-python", "version": "v3.26.1", "released": "2026-10-08", "seenAt": "2026-10-08T16:23:39.461409891Z" }, { "registry": "npm", "name": "openai", "version": "7.30.1", "seenAt": "2026-10-08T16:23:39.419090152Z" }, { "registry": "pypi", "name": "openai", "version": "3.26.1", "released": "2026-10-08", "seenAt": "2026-10-08T16:23:39.293419418Z" } ], "githubStars": 31777, "npmWeekly": 50858207, "pypiWeekly": 74231726, "securityTxt": { "url": "https://openai.com/.well-known/security.txt", "state": "valid", "checkedAt": "2026-10-08T15:38:50.073851341Z" }, "updatedAt": "2026-10-08T17:36:41.834725212Z" } }, "verify": { "accepts": "a page on openai.com or one of its subdomains, or the README of github.com/openai/openai-python", "badgeUrl": "https://www.anchorterminal.com/badges/openai-decisions-api.svg", "body": { "slug": "openai-decisions-api", "url": "the page with the badge or the link" }, "docs": "https://www.anchorterminal.com/builders/#verify", "effect": "none, it never changes a grade, rank or review", "endpoint": "https://www.anchorterminal.com/api/v1/verify", "listingUrl": "https://www.anchorterminal.com/tools/openai-decisions-api", "mcpTool": "verify_listing", "recheck": "weekly; two failed checks in a row and it lapses, a later pass restores it", "snippets": { "html": "\u003ca href=\"https://www.anchorterminal.com/tools/openai-decisions-api\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/openai-decisions-api.svg\" alt=\"OpenAI Decisions API on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e", "markdown": "[![OpenAI Decisions API on Anchor Terminal](https://www.anchorterminal.com/badges/openai-decisions-api.svg)](https://www.anchorterminal.com/tools/openai-decisions-api)", "link": "\u003ca href=\"https://www.anchorterminal.com/tools/openai-decisions-api\"\u003eOpenAI Decisions API on Anchor Terminal\u003c/a\u003e" } } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/tools/openai-decisions-api", "json": "https://www.anchorterminal.com/tools/openai-decisions-api.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/tools/openai-decisions-api.md", "slim": "https://www.anchorterminal.com/tools/openai-decisions-api.min.md" }, "markdown": "## Overview\n\n**Grade BB · 71.5/100 · rank #102 of 629 · #1 in Decision models · agent-ready · confidence medium**\n\n\nMore from OpenAI, listed separately because each is its own product: [OpenAI API](https://www.anchorterminal.com/tools/openai-api.md) (Model APIs \u0026 inference), [OpenAI embeddings](https://www.anchorterminal.com/tools/openai-embeddings.md) (Embeddings \u0026 rerankers), [OpenAI Moderation API](https://www.anchorterminal.com/tools/openai-moderation.md) (Guardrails \u0026 safety filters), [OpenAI Image API](https://www.anchorterminal.com/tools/openai-image-api.md) (Image generation), [OpenAI Sora API](https://www.anchorterminal.com/tools/openai-sora.md) (Video generation), [OpenAI Agents SDK](https://www.anchorterminal.com/tools/openai-agents-sdk.md) (Agent frameworks \u0026 SDKs), [OpenAI Codex](https://www.anchorterminal.com/tools/openai-codex.md) (Agent harnesses).\n\n## Assessment\n\nTyped predicate, choice and score answers with probabilities, up to 200 questions a call, at $0.10 per million input tokens with no output charge. It is a public beta released on 6 October 2026, with one model alias, no dated snapshot, no Batch route and no SLA found.\n\n## Facts\n\n| Field | Value |\n| --- | --- |\n| Vendor | OpenAI (https://developers.openai.com) |\n| Kind | Model API |\n| Category | Decision models (https://www.anchorterminal.com/categories/decision-models) |\n| Transport | HTTP |\n| Endpoint | `https://api.openai.com/v1/decisions` |\n| Auth | API key · `Authorization: Bearer` with an ordinary OpenAI project key, self-serve from the platform dashboard after sign-up. No waitlist or separate approval for the beta was found. Keys carry their own permissions under the access-control guide (https://developers.openai.com/api/docs/guides/rbac). We didn't confirm that a key can be restricted to `/v1/decisions` alone. |\n| Pricing | Pay per use (Pay per use) · $0.10 per million input tokens on `gpt-6-luna`, with no output, cache-read or cache-write charge (https://developers.openai.com/api/docs/guides/decisions). Long-context input multipliers and regional processing premiums apply, which on GPT-6 Luna are 2x input over 272,000 tokens and 10 per cent. No sandbox. The rate-limits guide lists a Free tier capped at $100 a month, but GPT-6 Luna's limits start at the Build tier, reached with $5 of credit (https://developers.openai.com/api/docs/guides/rate-limits). |\n| x402 | No · No x402, MPP or L402 in the Decisions guide, the API reference or the pricing page (checked 2026-10-08). |\n| Licence | Proprietary service under OpenAI's services agreement. The official SDKs are Apache-2.0 |\n| Packages | pypi: `openai`; npm: `openai` |\n| Source | https://github.com/openai/openai-python |\n| Docs | https://developers.openai.com/api/docs/guides/decisions |\n| llms.txt | https://developers.openai.com/llms.txt |\n| Last release | 2026-10-06 |\n| GitHub stars | 31,774 (as of 2026-10-08) |\n| Status | Public beta, released 6 October 2026. General availability expected in the coming weeks, no date given |\n| Question types | predicate (a probability from 0 to 1), choice (one of 2 to 255 supplied values) and score (2 to 10 ordered levels). 1 to 200 questions a request |\n| Model | gpt-6-luna only, an alias with no dated snapshot |\n| Input | A text string, or user messages with text and up to 128 inline base64 images. No image URLs, file IDs, audio or tools |\n| Context | Not stated for the endpoint. GPT-6 Luna's page gives 922,000 input tokens for the model |\n| Rate limits | Not stated for the endpoint. GPT-6 Luna is 5,000 requests and 2,000,000 tokens a minute on Build, 30,000 and 180,000,000 on Grow |\n| Batch | Not among the endpoints the Batch guide lists |\n| Trains on API data | No, per the data-controls guide |\n| Data retention | Abuse-monitoring logs up to 30 days. Zero Data Retention for eligible customers. Images flagged by the CSAM classifier are kept for review |\n| Data residency | Available in all ten API regions. Regional processing in the United States and Europe (EEA and Switzerland) |\n| SDKs | Python 3.26.0, JavaScript 7.30.0, Go 3.73.0, Ruby 0.101.0 and Java 4.78.0 or later |\n| Status page | status.openai.com, with a Decisions component under APIs |\n| Capabilities | inference.decision |\n| Tags | official, hosted, model, closed-source, openapi, llms-txt, python, typescript, go, java, usage-priced, status-page, beta |\n| JSON | https://www.anchorterminal.com/api/v1/tools/openai-decisions-api.json |\n\n## Score breakdown (methodology v0.4, October 2026 research run)\n\nAssessed 2026-10-08 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. \"This run\" is each category's share of the 100 points.\n\n| Category | Weight | This run | Score (0–100) | Points |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 20 | 53 | 10.6 |\n| Performance | 10% | pending | pending | n/a |\n| Schema \u0026 documentation | 13% | 16.2 | 89 | 14.5 |\n| Agent ergonomics | 13% | 16.2 | 87 | 14.1 |\n| Security \u0026 auth | 14% | 17.5 | 83 | 14.5 |\n| Payments \u0026 pricing | 10% | 12.5 | 30 | 3.8 |\n| Task success | 10% | pending | pending | n/a |\n| Maintenance \u0026 community | 7% | 8.8 | 77 | 6.7 |\n| Transparency \u0026 trust (editorial 71, provenance 94) | 7% | 8.8 | 83 | 7.3 |\n| Negative events | up to −15 | up to −15 | none recorded | 0 |\n| **Total** | | | | **71.5 → BB** |\n\n### Why each score\n\n- Reliability 53: Read as a hosted model API. status.openai.com has a Decisions component under APIs, reading 100 per cent on 8 October (20). The endpoint was released on 6 October, so its record is two days long. The incident feed, read back to 10 July, names Decisions in no incident. The platform under it had API-wide error incidents on 25 July, 17 September and 29 September (5 hours 22 minutes), all before the release, so 8 of 30 for a clean record too short to count, the reading given to Clef on its first day. The GPT-6 Luna page lists 5,000 requests and 2,000,000 tokens a minute on the Build tier, 10,000 and 10,000,000 on Launch and 30,000 and 180,000,000 on Grow, but its endpoint table doesn't list Decisions and the guide gives no limits of its own (10 of 15). The rate-limits guide covers `Retry-After` on 429 and 503, backoff with jitter and SDK retries, and a decision has no side effects, so a retry is safe (15). No SLA covering a beta endpoint was found. The Scale Tier page answered 403 on 8 October (0). Public beta (0).\n- Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes.\n- Schema \u0026 documentation 89: OpenAI's OpenAPI 3.1 document (version 2.3.0, committed 8 October) has `POST /decisions` with `DecisionRequest` and `DecisionResponse` schemas (25). llms.txt indexes the guide, and the guide and the reference page each have a Markdown twin (10). The guide says which question type fits which job and when to use Structured Outputs or function calling instead. No page of known limits for the model on this endpoint was found (16 of 20). Questions are a union discriminated on `type`, with 1 to 200 questions, 2 to 255 choices and 2 to 10 levels set in the schema and no extra properties allowed (15). The guide has examples in curl, JavaScript, Python, Go, Java and Ruby with sample responses. The OpenAPI operation documents only the 200 response, and errors are covered by the general error-codes guide (12 of 15). A dated changelog carries the release on 6 October. The only model ID is the alias `gpt-6-luna` with no dated snapshot, and the beta has no version of its own (11 of 15).\n- Agent ergonomics 87: Read as an API an agent calls for a decision, the reading used for Jev. Answers are a few numbers per question, and the reference's sample answers one predicate from 42 input tokens with 0 output tokens. Up to 128 inline images a request. The usage object reports cached tokens and the guide says cache reads and writes aren't charged. `/v1/decisions` isn't among the endpoints the Batch guide lists, and the guide states no context limit for the endpoint (20 of 25). The caller sets the whole output shape, with up to 200 independent questions about one input in a call (18 of 20). The error-codes guide gives types, codes and recovery steps for 400, 401, 403, 429, 500 and 503, and a question the model declines comes back as a typed `refusal` answer beside the others. Errors particular to the endpoint aren't documented (16 of 20). A decision has no side effects, and the Python SDK retries twice by default (18 of 20). Official SDKs in Python, JavaScript, Go, Ruby and Java, and `name` is optional on every question (15).\n- Security \u0026 auth 83: Read for a model API, on the lines used for Jev. Project API keys, with the access-control guide saying a key carries its own permissions that are checked against the caller's project role, service-account keys created through the Administration API with a documented rotation procedure, and workload identity federation with short-lived tokens. We didn't confirm that a restricted key can be limited to `/v1/decisions`, since the help centre article answered 403 (27 of 30). The data-controls guide lists `/v1/decisions` as not used for training, with abuse-monitoring logs kept up to 30 days and Zero Data Retention for eligible customers. An image flagged by the CSAM classifier is kept for review under any setting, and the Private Retention column reads pending confirmation (18 of 20). The endpoint judges text and images that often come from users. Neither the guide nor the reference mentions adversarial or injected content. The safety guide advises red-teaming and limiting input length, and requests accept a `safety_identifier` (6 of 15). Each response reports token usage, and the Admin APIs guide documents audit-log retrieval. We didn't confirm how Decisions calls appear in usage views (12 of 15). security.txt is PGP-signed and names a Bugcrowd bounty and a coordinated disclosure policy, though it has no Expires field, and trust.openai.com names SOC 2 Type 2 and ISO/IEC 27001, 27017, 27018, 27701 and 42001 (20).\n- Payments \u0026 pricing 30: No x402, MPP or L402 in the guide, the reference or the pricing page (0). Per-token price published without a login, $0.10 per million input tokens with no output or cache charge (20). The rate-limits guide lists a Free tier capped at $100 a month in allowed countries, but the GPT-6 Luna page's rate-limit table starts at Build, which needs $5 of credit, and the Decisions guide doesn't mention a free allowance, so half, as for the OpenAI API listing (10). A person signs up in a browser and creates a key (0).\n- Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored.\n- Maintenance \u0026 community 77: Read for a closed model, on the lines used for Jev. Released in beta on 6 October 2026 (30). OpenAI publishes minimum notice of 6 months for generally available models and 3 months for specialised variants, and says preview models can go with 2 weeks. Nothing states what a beta endpoint gets (6 of 12). Two days old with one model alias and no dated snapshot, too short to show churn (4 of 8). A dated changelog with several entries a month, including this release. The help centre answered 403 and issue replies weren't sampled (12 of 15). Official SDKs gained Decisions on release day, Python 3.26.0 and JavaScript 7.30.0 on 6 October, with 3.26.1 and 7.30.1 on 8 October, and the guide names Go 3.73.0, Ruby 0.101.0 and Java 4.78.0 (15). The Python SDK states Python 3.10 or later, the JavaScript SDK Node 22 or later, and the Python repository carries CI and breaking-change workflows (10).\n- Transparency \u0026 trust 83: Closed service with Apache-2.0 SDKs and an MIT OpenAPI repository. The services agreement answered 403 on 8 October, so its terms stand per the OpenAI API listing's earlier check (15). The data-controls guide, read on 8 October, gives `/v1/decisions` its own row and section covering training, 30-day abuse logs, Zero Data Retention, the 24-hour prompt cache and HIPAA eligibility. One column reads pending confirmation, and the DPA wasn't re-read (403), per the 4 October check on the OpenAI API listing (26 of 30). The deprecations page gives dated notices and minimum notice periods for models. It says nothing about beta endpoints, and the guide gives no date for general availability (14 of 20). The guide lists ten data-residency regions with Decisions in each, and regional processing for it in the United States and Europe. The subprocessor list answered 403 on 8 October, per the 4 October check (16 of 20).\n\nFix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (22 items): https://www.anchorterminal.com/fixes/openai-decisions-api.md (JSON https://www.anchorterminal.com/fixes/openai-decisions-api.json)\n\n### What we couldn't check\n\n- The scout gave the launch as unconfirmed, with press naming 29 September. The API changelog dates the beta release 6 October 2026, and openai-python added Decisions in 3.26.0 the same day. Whether a limited preview ran earlier wasn't established\n- Which rate limits apply to `/v1/decisions`. The GPT-6 Luna page gives the model's limits and its endpoint table doesn't list Decisions\n- The context limit on this endpoint. The guide gives none, and GPT-6 Luna's page gives 922,000 input tokens for the model\n- Whether the Free tier reaches `/v1/decisions`, and whether it needs a card\n- Whether a restricted project key can be limited to `/v1/decisions`, and how Decisions calls appear in usage views\n- Whether failed or refused questions are charged\n- The Mixpanel breach of November 2025 carries a deduction of 2 on three OpenAI listings and none on the OpenAI API listing. We took none here, since the endpoint is eleven months younger than the incident and the source page answered 403 on 8 October. An editor should settle this across the OpenAI listings\n- openai.com/.well-known/security.txt has no Expires field, which RFC 9116 requires. The provenance block says valid, as the other OpenAI listings do\n- unchecked: the services agreement, privacy policy, DPA and subprocessor list (openai.com answered 403 on 8 October). These stand per the OpenAI API listing's checks of 26 September and 4 October\n- unchecked: the Scale Tier SLA page (403), so no SLA was scored\n- unchecked: the help centre articles on API key permissions and support (help.openai.com answered 403)\n- unchecked: the Playground at platform.openai.com/decisions, which needs a login\n- unchecked: issue reply times on openai-python. The GitHub API refused us for its rate limit\n\n### Sources\n\n- Decisions guide: \u003chttps://developers.openai.com/api/docs/guides/decisions.md\u003e (seen 2026-10-08)\n- Decisions API reference, create a decision: \u003chttps://developers.openai.com/api/reference/resources/decisions/methods/create\u003e (seen 2026-10-08)\n- voice with Decisions guide: \u003chttps://developers.openai.com/api/docs/guides/decisions-voice.md\u003e (seen 2026-10-08)\n- changelog, release entry of 6 October: \u003chttps://developers.openai.com/api/docs/changelog.md\u003e (seen 2026-10-08)\n- GPT-6 Luna model page, limits and endpoints: \u003chttps://developers.openai.com/api/docs/models/gpt-6-luna.md\u003e (seen 2026-10-08)\n- pricing: \u003chttps://developers.openai.com/api/docs/pricing.md\u003e (seen 2026-10-08)\n- data controls, /v1/decisions row and residency: \u003chttps://developers.openai.com/api/docs/guides/your-data.md\u003e (seen 2026-10-08)\n- rate limits, usage tiers and retry guidance: \u003chttps://developers.openai.com/api/docs/guides/rate-limits.md\u003e (seen 2026-10-08)\n- error codes: \u003chttps://developers.openai.com/api/docs/guides/error-codes.md\u003e (seen 2026-10-08)\n- Batch guide, supported endpoints: \u003chttps://developers.openai.com/api/docs/guides/batch.md\u003e (seen 2026-10-08)\n- deprecations and notice periods: \u003chttps://developers.openai.com/api/docs/deprecations.md\u003e (seen 2026-10-08)\n- access control guide: \u003chttps://developers.openai.com/api/docs/guides/rbac.md\u003e (seen 2026-10-08)\n- Admin APIs guide, audit logs: \u003chttps://developers.openai.com/api/docs/guides/admin-apis.md\u003e (seen 2026-10-08)\n- service accounts and key rotation: \u003chttps://developers.openai.com/api/docs/guides/terraform/service-accounts.md\u003e (seen 2026-10-08)\n- safety best practices: \u003chttps://developers.openai.com/api/docs/guides/safety-best-practices.md\u003e (seen 2026-10-08)\n- llms.txt for the API docs: \u003chttps://developers.openai.com/api/docs/llms.txt\u003e (seen 2026-10-08)\n- OpenAPI repository, openapi.json: \u003chttps://github.com/openai/openai-openapi\u003e (seen 2026-10-08)\n- openai-python changelog and source: \u003chttps://github.com/openai/openai-python\u003e (seen 2026-10-08)\n- openai on PyPI (JSON): \u003chttps://pypi.org/pypi/openai/json\u003e (seen 2026-10-08)\n- npm openai: \u003chttps://registry.npmjs.org/openai\u003e (seen 2026-10-08)\n- status page, Decisions component: \u003chttps://status.openai.com/\u003e (seen 2026-10-08)\n- status incident feed: \u003chttps://status.openai.com/history.rss\u003e (seen 2026-10-08)\n- incident of 29 September: \u003chttps://status.openai.com/incidents/01M3Q4RK1SM4EMK445GGPG7C0N\u003e (seen 2026-10-08)\n- security.txt: \u003chttps://openai.com/.well-known/security.txt\u003e (seen 2026-10-08)\n- trust portal, certifications: \u003chttps://trust.openai.com/\u003e (seen 2026-10-08)\n- RDAP for openai.com: \u003chttps://rdap.verisign.com/com/v1/domain/openai.com\u003e (seen 2026-10-08)\n\n## Who's behind it (provenance 94/100, checked 2026-10-08)\n\n| Check | Finding | Points |\n| --- | --- | --- |\n| Legal entity named | OpenAI OpCo, LLC | 20/20 |\n| Domain age | openai.com, registered 2007-01-19 (19 years) | 15/15 |\n| Endpoint on the vendor's domain | api.openai.com | 15/15 |\n| Terms of service | published, but our reader couldn't read it | 7/10 |\n| Privacy policy | published, but our reader couldn't read it | 7/10 |\n| Status page | status.openai.com | 10/10 |\n| Changelog | published | 10/10 |\n| security.txt | valid | 10/10 |\n\nSame entity, terms and privacy policy as the OpenAI API listing. openai.com answered 403 to our reader on 8 October, so the legal entity and the two policy URLs stand per that listing's check of 26 September and weren't re-read.\n\nRDAP gives openai.com a registration date of 2007-01-19, before OpenAI existed.\n\nstatus.openai.com lists a Decisions component under APIs, read on 8 October.\n\nThe changelog entry for the release is dated 6 October 2026.\n\nopenai.com/.well-known/security.txt is PGP-signed and names a Bugcrowd contact and a disclosure policy. It has no Expires field, which RFC 9116 requires.\n\n### Terms and privacy, as read\n\nA reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice.\n\n**Terms of service** (https://openai.com/policies/services-agreement/), read 2026-10-08. Our reader couldn't read it (the page answered HTTP 403 to our reader).\n\n\n**Privacy policy** (https://openai.com/policies/privacy-policy/), read 2026-10-08. Our reader couldn't read it (the page answered HTTP 403 to our reader).\n\n\n## Live (updated 2026-10-08 17:36 UTC)\n\n- Right now: up, HTTP 404, 132 ms, checked 2026-10-08 17:36 UTC (get on `https://api.openai.com/v1/decisions`)\n- Uptime 24h 100.0% (25 probes) · 30 days 100.0% (25 probes) · p50 145 ms · p95 203 ms\n- Vendor status page: none, All Systems Operational\n- github `openai/openai-python` v3.26.1, released 2026-10-08\n- npm `openai` 7.30.1\n- pypi `openai` 3.26.1, released 2026-10-08\n- security.txt: valid\n- Always current: https://www.anchorterminal.com/api/v1/live/openai-decisions-api.json\n\n## Probe metrics\n\nNot measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score.\n\n## Prices\n\n| Item | Price | Unit | Note |\n| --- | --- | --- | --- |\n| gpt-6-luna input on /v1/decisions | $0.10 | per 1M tokens | No output, cache-read or cache-write charge |\n\nAcross all listings: https://www.anchorterminal.com/prices/index.md\n\n## Strengths\n\n- Three typed question kinds, predicate, choice and score, with per-option probabilities and up to 200 questions about one input in a call\n- $0.10 per million input tokens on `gpt-6-luna`, with no output, cache-read or cache-write charge\n- Text and up to 128 inline images in one request\n- The official OpenAPI 3.1 document carries `POST /decisions` with typed limits, and five official SDKs support it\n- Not used for training by default, eligible for Zero Data Retention and HIPAA use, per OpenAI's data-controls guide\n\n## Weaknesses\n\n- Public beta released on 6 October 2026. The guide expects general availability in the coming weeks and gives no date\n- One model alias, `gpt-6-luna`, with no dated snapshot to pin\n- Images must be inline base64 data URLs. Hosted image URLs and `file_id` inputs aren't accepted\n- Not among the endpoints the Batch guide lists, and no SLA covering it was found\n- No guidance on adversarial or injected content was found in the guide or the reference\n\n## Before you call it (notes for agents)\n\n1. Put independent questions about one input in a single `questions` array. Send a separate request when a question depends on an earlier answer\n2. Check each answer's `type` before reading it. A question can come back as `refusal` while the others in the same request are answered\n3. Encode images as base64 data URLs. Hosted URLs and `file_id` inputs are rejected\n4. Give a `choice` question a fallback value such as `other`, and set thresholds from your own labelled examples\n5. Use Python SDK 3.26.0 or JavaScript 7.30.0 or later, and follow `Retry-After` on 429 and 503\n\n## Connect\n\nInstall:\n\n```bash\npip install openai # or: npm i openai\n```\n\nFirst request:\n\n```bash\ncurl https://api.openai.com/v1/decisions \\\n -H \"Authorization: Bearer $OPENAI_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"gpt-6-luna\",\"input\":\"I was charged twice for my order.\",\"questions\":[{\"type\":\"choice\",\"name\":\"department\",\"instructions\":\"Which department should handle this complaint?\",\"choices\":[{\"value\":\"billing\",\"description\":\"Payments, invoices, and refunds.\"},{\"value\":\"technical\",\"description\":\"Problems using the product.\"},{\"value\":\"other\",\"description\":\"Requests outside these categories.\"}]}]}'\n```\n\n## Similar tools\n\nRanked by shared capabilities, then score. Same-category tools with no shared capability key are listed last.\n\n| Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown |\n| --- | --- | --- | --- | --- | --- | --- |\n| Laya | B | 69.2 | 153 | inference.decision | no | https://www.anchorterminal.com/tools/convai-laya.md |\n| Kev | B | 67.4 | 194 | inference.decision | no | https://www.anchorterminal.com/tools/jaredpalmer-kev.md |\n| Vela 2.0 | B | 66.5 | 219 | inference.decision | no | https://www.anchorterminal.com/tools/vela.md |\n| Clef | B | 66.1 | 224 | inference.decision | no | https://www.anchorterminal.com/tools/cloudflare-clef.md |\n| Jev | B | 62.1 | 309 | inference.decision | no | https://www.anchorterminal.com/tools/typesafe-jev.md |\n| Strands Decider 2B | C | 61.3 | 327 | inference.decision | no | https://www.anchorterminal.com/tools/strands-decider.md |\n\n## Panel reviews (0)\n\nReviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): .\n\nDesk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md\n\n## Notable\n\n- The API changelog dates the release 6 October 2026, in beta with `gpt-6-luna`, and the guide says OpenAI expects general availability in the coming weeks (source: \u003chttps://developers.openai.com/api/docs/changelog\u003e)\n- The guide says the endpoint answers about 10 times faster than the Responses API. That is OpenAI's claim, and we haven't measured it (source: \u003chttps://developers.openai.com/api/docs/guides/decisions\u003e)\n- A `score` answer is the probability-weighted average of the level indices, so it can fall between levels, and `choice` and `score` answers carry a probability per option and a separate `confidence` (source: \u003chttps://developers.openai.com/api/docs/guides/decisions\u003e)\n- A request takes 1 to 200 questions, a choice 2 to 255 options and a score 2 to 10 levels, per the OpenAPI document (source: \u003chttps://github.com/openai/openai-openapi\u003e)\n- Up to 128 images a request, as inline base64 data URLs only. External URLs, files, audio, tools and other message roles aren't supported (source: \u003chttps://developers.openai.com/api/reference/resources/decisions/methods/create\u003e)\n- A question can return a `refusal` answer while other questions in the same request are answered (source: \u003chttps://developers.openai.com/api/reference/resources/decisions/methods/create\u003e)\n- The data-controls guide lists `/v1/decisions` as not used for training, with abuse-monitoring logs up to 30 days, Zero Data Retention for eligible customers and HIPAA eligibility under a business associate agreement (source: \u003chttps://developers.openai.com/api/docs/guides/your-data\u003e)\n- The request shape differs from the `/v1/systemone` shape that Jev, Clef, Kev and Laya share. It uses `input`, a `questions` array and `predicate` where they use `state`, a questions object and `noul` (source: \u003chttps://developers.openai.com/api/docs/guides/decisions\u003e)\n- A second guide pairs Decisions with the Live API, so a voice session hands action selection to a Decisions call (source: \u003chttps://developers.openai.com/api/docs/guides/decisions-voice\u003e)\n\n## Compare\n\n- [Clef vs OpenAI Decisions API](https://www.anchorterminal.com/compare/cloudflare-clef-vs-openai-decisions-api.md): B 66.1 vs BB 71.5\n- [Laya vs OpenAI Decisions API](https://www.anchorterminal.com/compare/convai-laya-vs-openai-decisions-api.md): B 69.2 vs BB 71.5\n- [Kev vs OpenAI Decisions API](https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-openai-decisions-api.md): B 67.4 vs BB 71.5\n- [Liquid d1 vs OpenAI Decisions API](https://www.anchorterminal.com/compare/liquid-d1-vs-openai-decisions-api.md): E 43.5 vs BB 71.5\n- [OpenAI Decisions API vs Strands Decider 2B](https://www.anchorterminal.com/compare/openai-decisions-api-vs-strands-decider.md): BB 71.5 vs C 61.3\n- [OpenAI Decisions API vs Jev](https://www.anchorterminal.com/compare/openai-decisions-api-vs-typesafe-jev.md): BB 71.5 vs B 62.1\n- [OpenAI Decisions API vs Vela 2.0](https://www.anchorterminal.com/compare/openai-decisions-api-vs-vela.md): BB 71.5 vs B 66.5\n\n## Verify this listing\n\nFor the vendor. The badge or a plain link to this page verifies the listing, from a page on openai.com or one of its subdomains, or the README of github.com/openai/openai-python. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{\"slug\": \"openai-decisions-api\", \"url\": \"…\"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify\n\nHTML badge:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/openai-decisions-api\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/openai-decisions-api.svg\" alt=\"OpenAI Decisions API on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e\n```\n\nMarkdown badge, for a README:\n\n```markdown\n[![OpenAI Decisions API on Anchor Terminal](https://www.anchorterminal.com/badges/openai-decisions-api.svg)](https://www.anchorterminal.com/tools/openai-decisions-api)\n```\n\nPlain link:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/openai-decisions-api\"\u003eOpenAI Decisions API on Anchor Terminal\u003c/a\u003e\n```\n\n## Share this listing\n\nFor the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say OpenAI Decisions API is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score.\n\n- Dark: https://www.anchorterminal.com/assets/share/openai-decisions-api-dark.png\n- Light: https://www.anchorterminal.com/assets/share/openai-decisions-api-light.png\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-08", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Terminal", "url": "https://www.anchorterminal.com/tools/" }, { "name": "Decision models", "url": "https://www.anchorterminal.com/categories/decision-models" }, { "name": "OpenAI Decisions API", "url": "" } ], "description": "The Decisions API is an OpenAI endpoint, in public beta since 6 October 2026, that reads text and images and returns typed answers with probabilities, a predicate, a choice from a fixed set or a rubric score.", "facts": [ "rank #102 of 629", "API key auth", "0 desk reviews" ], "h1": "OpenAI Decisions API", "image": "https://www.anchorterminal.com/assets/og/tools-openai-decisions-api.png", "path": "/tools/openai-decisions-api", "published": "2026-10-01", "section": "tools", "title": "OpenAI Decisions API review for AI agents, grade BB (71.5/100)", "toc": null, "updated": "2026-10-08", "url": "https://www.anchorterminal.com/tools/openai-decisions-api" }, "tokens": { "markdown": 7350, "slim": 1480 }, "version": 1 }