OpenAI API API
openai.com
AI UtilitiesListed, not routed yet
GPT models for completion, extraction and embeddings.
What it does
OpenAI platform API: responses/chat completions, structured outputs, embeddings and batch; bearer keys with per-project rate limits.
In its API docs
Docs
OpenAI API's own pages, linked as published.
- API referenceplatform.openai.com/docs/api-reference
- OpenAPI specraw.githubusercontent.com/openai/openai-openapi/master/openapi.yaml
- Pricingopenai.com/api/pricing
- Rate limitsplatform.openai.com/docs/guides/rate-limits
- Status pagestatus.openai.com
- Websiteopenai.com
Its OpenAPI document: 352 operations and rate limits
| Method | Path | Summary | Params | Source |
|---|---|---|---|---|
| GET | /assistants | List assistants | 4 | Spec |
| POST | /assistants | Create assistant | 0 | Spec |
| GET | /assistants/{assistant_id} | Retrieve assistant | 1 | Spec |
| POST | /assistants/{assistant_id} | Modify assistant | 1 | Spec |
| DELETE | /assistants/{assistant_id} | Delete assistant | 1 | Spec |
| POST | /audio/speech | Create speech | 0 | Spec |
| POST | /audio/transcriptions | Create transcription | 0 | Spec |
| POST | /audio/translations | Create translation | 0 | Spec |
| GET | /audio/voice_consents | List voice consents | 2 | Spec |
| POST | /audio/voice_consents | Create voice consent | 0 | Spec |
| GET | /audio/voice_consents/{consent_id} | Retrieve voice consent | 1 | Spec |
| POST | /audio/voice_consents/{consent_id} | Update voice consent | 1 | Spec |
| DELETE | /audio/voice_consents/{consent_id} | Delete voice consent | 1 | Spec |
| POST | /audio/voices | Create voice | 0 | Spec |
| GET | /batches | List batches | 2 | Spec |
| POST | /batches | Create batch | 0 | Spec |
| GET | /batches/{batch_id} | Retrieve batch | 1 | Spec |
| POST | /batches/{batch_id}/cancel | Cancel batch | 1 | Spec |
| GET | /chat/completions | List Chat Completions | 5 | Spec |
| POST | /chat/completions | Create chat completion | 0 | Spec |
| GET | /chat/completions/{completion_id} | Get chat completion | 1 | Spec |
| POST | /chat/completions/{completion_id} | Update chat completion | 1 | Spec |
| DELETE | /chat/completions/{completion_id} | Delete chat completion | 1 | Spec |
| GET | /chat/completions/{completion_id}/messages | Get chat messages | 4 | Spec |
| POST | /completions | Create completion | 0 | Spec |
| GET | /containers | List containers | 4 | Spec |
| POST | /containers | Create container | 0 | Spec |
| GET | /containers/{container_id} | Retrieve container | 1 | Spec |
| DELETE | /containers/{container_id} | Delete a container | 1 | Spec |
| GET | /containers/{container_id}/files | List container files | 4 | Spec |
| POST | /containers/{container_id}/files | Create container file | 1 | Spec |
| GET | /containers/{container_id}/files/{file_id} | Retrieve container file | 2 | Spec |
| DELETE | /containers/{container_id}/files/{file_id} | Delete a container file | 2 | Spec |
| GET | /containers/{container_id}/files/{file_id}/content | Retrieve container file content | 2 | Spec |
| GET | /conversations/{conversation_id}/items | List items | 5 | Spec |
| POST | /conversations/{conversation_id}/items | Create items | 2 | Spec |
| GET | /conversations/{conversation_id}/items/{item_id} | Retrieve an item | 3 | Spec |
| DELETE | /conversations/{conversation_id}/items/{item_id} | Delete an item | 2 | Spec |
| POST | /embeddings | Create embeddings | 0 | Spec |
| GET | /evals | List evals | 4 | Spec |
Showing 40 of 352 operations; the full list is in the spec.
Rate limits
| Limit | Scope | Plan | Endpoint | Burst / concurrency |
|---|---|---|---|---|
| 5,000 / minute | plan | Build | Astra, Sol, Terra | — / — |
| 5,000 / minute | plan | Build | Luna | — / — |
| 10,000 / minute | plan | Launch | Astra, Sol, Terra | — / — |
| 10,000 / minute | plan | Launch | Luna | — / — |
| 15,000 / minute | plan | Grow | Astra, Sol, Terra | — / — |
| 30,000 / minute | plan | Grow | Luna | — / — |
Headers: x-ratelimit-limit-requestsx-ratelimit-limit-tokensx-ratelimit-remaining-requestsx-ratelimit-remaining-tokensx-ratelimit-reset-tokens. On 429: Rate limit or hard spend limit reached. GridRouter never paces above these and backs off on 429, honoring Retry-After. Source, checked Sep 29, 2026
Sources for this page (3)
- OpenAI pricingchecked Sep 29, 2026
- OpenAI API referencechecked Sep 29, 2026
- Wikidata: headquarters and inceptionchecked Sep 29, 2026