
Cohere API
cohere.com
AI UtilitiesListed, not routed yet
Command, Embed, Rerank and Parse model APIs for enterprise.
What it does
Enterprise LLM provider (Command chat, Embed, Rerank, Parse, Aya). Trial keys are free but rate limited and limited to 1,000 calls/month; production keys have higher per-endpoint limits (e.g. Command A 500 req/min, Rerank 1,000 req/min). Model Vault dedicated instances priced hourly/monthly.
In its API docs
Pricing
What Cohere publishes for buying direct, as listed on its own pages.
Buying direct from Cohere
- Command (legacy)$1.00/1M input tokens
- Model Vault Embed 4 Small$4.00/hour per instance
Free tier: Trial key: 1,000 API calls a month, non-production. Larger plans through sales. Cohere pricing, checked Sep 29, 2026
Docs
Cohere's own pages, linked as published.
- API referencedocs.cohere.com/reference/about
- OpenAPI specraw.githubusercontent.com/cohere-ai/cohere-developer-experience/main/cohere-openapi.yaml
- Pricingcohere.com/pricing
- Rate limitsdocs.cohere.com/docs/rate-limits
- Status pagestatus.cohere.com
- Websitecohere.com
Its OpenAPI document: 42 operations and rate limits
| Method | Path | Summary | Params | Source |
|---|---|---|---|---|
| POST | /v1/chat | Chat API (v1) | 1 | Spec |
| POST | /v2/chat | Chat API (v2) | 0 | Spec |
| POST | /v2/parse | Parse API (v2) | 0 | Spec |
| POST | /v1/generate | Generate | 0 | Spec |
| POST | /v1/embed | Embed API (v1) | 0 | Spec |
| POST | /v2/embed | Embed API (v2) | 0 | Spec |
| POST | /v2/audio/transcriptions | Create a transcription | 0 | Spec |
| GET | /v2/batches | List batches | 3 | Spec |
| POST | /v2/batches | Create a batch | 0 | Spec |
| GET | /v2/batches/{id} | Retrieve a batch | 1 | Spec |
| POST | /v2/batches/{id}:cancel | Cancel a batch | 1 | Spec |
| GET | /v1/embed-jobs | List Embed Jobs | 0 | Spec |
| POST | /v1/embed-jobs | Create an Embed Job | 0 | Spec |
| GET | /v1/embed-jobs/{id} | Fetch an Embed Job | 1 | Spec |
| POST | /v1/embed-jobs/{id}/cancel | Cancel an Embed Job | 1 | Spec |
| POST | /v1/rerank | Rerank API (v1) | 0 | Spec |
| POST | /v2/rerank | Rerank API (v2) | 0 | Spec |
| POST | /v1/classify | Classify | 0 | Spec |
| GET | /v1/datasets | List Datasets | 6 | Spec |
| POST | /v1/datasets | Create a Dataset | 8 | Spec |
| GET | /v1/datasets/usage | Get Dataset Usage | 0 | Spec |
| GET | /v1/datasets/{id} | Get a Dataset | 1 | Spec |
| DELETE | /v1/datasets/{id} | Delete a Dataset | 1 | Spec |
| POST | /v1/summarize | Summarize | 0 | Spec |
| POST | /v1/tokenize | Tokenize | 0 | Spec |
| POST | /v1/detokenize | Detokenize | 0 | Spec |
| GET | /v1/connectors | List Connectors | 2 | Spec |
| POST | /v1/connectors | Create a Connector | 0 | Spec |
| GET | /v1/connectors/{id} | Get a Connector | 1 | Spec |
| PATCH | /v1/connectors/{id} | Update a Connector | 1 | Spec |
| DELETE | /v1/connectors/{id} | Delete a Connector | 1 | Spec |
| POST | /v1/connectors/{id}/oauth/authorize | Authorize with oAuth | 2 | Spec |
| GET | /v1/models/{model} | Get a Model | 1 | Spec |
| GET | /v1/models | List Models | 4 | Spec |
| POST | /v1/check-api-key | Check API key | 0 | Spec |
| GET | /v1/finetuning/finetuned-models | Lists fine-tuned models. | 3 | Spec |
| POST | /v1/finetuning/finetuned-models | Trains and deploys a fine-tuned model. | 0 | Spec |
| GET | /v1/finetuning/finetuned-models/{id} | Returns a fine-tuned model by ID. | 1 | Spec |
| PATCH | /v1/finetuning/finetuned-models/{id} | Updates a fine-tuned model. | 1 | Spec |
| DELETE | /v1/finetuning/finetuned-models/{id} | Deletes a fine-tuned model. | 1 | Spec |
Showing 40 of 42 operations; the full list is in the spec.
Rate limits
| Limit | Scope | Plan | Endpoint | Burst / concurrency |
|---|---|---|---|---|
| 20 / minute | key | Trial | Chat (Command A) | — / — |
| 500 / minute | key | Production | Chat (Command A) | — / — |
| 10 / minute | key | Trial | Rerank | — / — |
| 1,000 / minute | key | Production | Rerank | — / — |
| 2,000 / minute | key | All | Embed | — / — |
| 1,000 / month | key | Trial | All | — / — |
GridRouter never paces above these and backs off on 429, honoring Retry-After. Source, checked Sep 29, 2026
Sources for this page (3)
- Cohere pricingchecked Sep 29, 2026
- Cohere rate limitschecked Sep 29, 2026
- Cohere API referencechecked Sep 30, 2026