# Decision 3.0 vs OpenAI Decisions API (slim)

> OpenAI Decisions scores 71.5 (BB) to Decision 3.0's 63.1 (B) for decision models. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/decision-3-vs-openai-decisions-api.md (~2,750 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/decision-3-vs-openai-decisions-api.json · canonical https://www.anchorterminal.com/compare/decision-3-vs-openai-decisions-api
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-12

OpenAI Decisions API scores 71.5 (BB) on agent readiness against Decision 3.0's 63.1 (B), and leads in 4 of 7 scored categories. Decision 3.0 leads on reliability, payments & pricing and maintenance & community. Both do decision models.

- Decision 3.0: B 63.1, rank #413 of 965 · https://www.anchorterminal.com/tools/decision-3.min.md
- OpenAI Decisions API: BB 71.5, rank #123 of 965 · https://www.anchorterminal.com/tools/openai-decisions-api.min.md
- Decision 3.0, good for Self-hosted typed decisions over screenshots, documents and short video as well as text, where open weights matter. Ahead on Reliability, 58 against 53; Payments & pricing, 60 against 30; Maintenance & community, 82 against 77. Also No key needed to call it; Open source.
- OpenAI Decisions API, good for High-volume yes or no checks, routing among fixed options and rubric scoring over text and images, for teams already on an OpenAI key. Ahead on Schema & documentation, 89 against 70; Agent ergonomics, 87 against 72; Security & auth, 83 against 56; Transparency & trust, 83 against 45. Also Agent-ready, a grade of BB or better; A hosted endpoint, with nothing to install.

| Category | Decision 3.0 | OpenAI Decisions API |
| --- | --- | --- |
| Reliability (16%) | 58 | 53 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 70 | 89 |
| Agent ergonomics (13%) | 72 | 87 |
| Security & auth (14%) | 56 | 83 |
| Payments & pricing (10%) | 60 | 30 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 82 | 77 |
| Transparency & trust (7%) | 45 | 83 |

| Fact (where they differ) | Decision 3.0 | OpenAI Decisions API |
| --- | --- | --- |
| Vendor | vLLM Semantic Router Team | OpenAI |
| Hosted endpoint | no (local only) | `https://api.openai.com/v1/decisions` |
| Auth | None | API key |
| Pricing | Free | Pay per use |
| Price for decision models | free | $0.10 per 1M tokens |
| Licence | Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases | Proprietary service under OpenAI's services agreement. The official SDKs are Apache-2.0 |
| llms.txt | no | yes |
| Last release | 2026-10-11 | 2026-10-06 |
| Terms last updated | no document linked | couldn't be read |
| Privacy policy last updated | no document linked | couldn't be read |
| Customer content may train models |  | couldn't be read |
| Terms restrict automated access |  | couldn't be read |
| Terms restrict benchmarking |  | couldn't be read |
| Terms or service can change without notice |  | couldn't be read |
| Arbitration or class-action waiver |  | couldn't be read |
| Popularity | none | 32k stars |