# Cohere Chat API (Command models) > Cohere's Chat API generates text with the Command family of models over REST (v2 chat), with tool use, structured outputs, citations and streaming. SDKs cover Python, TypeScript, Java and Go. - Canonical: https://www.anchorterminal.com/tools/cohere-chat - Markdown: https://www.anchorterminal.com/tools/cohere-chat.md (~8,650 tokens) - Slim: https://www.anchorterminal.com/tools/cohere-chat.min.md (~1,780 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/cohere-chat.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - Updated: 2026-10-10 ## Overview **Grade B · 64.7/100 · rank #342 of 950 · #11 in Model APIs & inference · not agent-ready · confidence medium** More from Cohere, listed separately because each is its own product: [Cohere Embed and Rerank](https://www.anchorterminal.com/tools/cohere-embed.md) (Embeddings & rerankers), [Cohere North](https://www.anchorterminal.com/tools/cohere-north.md) (Company knowledge & data catalogues). ## Assessment A public OpenAPI file, Markdown twins of every docs page and SDKs in four languages make the Chat API easy for an agent to read. Production keys do not cover the four newest Command models, whose limits are set by sales, and the SaaS agreement lets Cohere share API data with third parties. ## Facts | Field | Value | | --- | --- | | Vendor | Cohere (https://cohere.com) | | Kind | Model API | | Category | Model APIs & inference (https://www.anchorterminal.com/categories/inference) | | Transport | HTTP | | Endpoint | `https://api.cohere.com/v2/chat` | | Auth | API key · Bearer API key from the dashboard, self-serve. A trial key is created at sign-up. A production key needs a team Owner to complete the Go to Production form and accept the SaaS agreement. Team roles are Owner and User. No key scopes or expiry were found in the docs. | | Pricing | Freemium (from $2.50 / 1M in) · Trial keys are free with no card, limited to 20 chat requests a minute and 1,000 calls a month, and not for commercial use. Production keys bill per input and output token, monthly or at $250 outstanding. Current Command prices are in a script-drawn tab of cohere.com/pricing that we could not read. Production keys stay at trial limits on Command A+, Reasoning, Translate and Vision (checked 2026-10-09). | | x402 | No · No x402, MPP or L402 in the docs, the OpenAPI file or the pricing page (checked 2026-10-09). | | Licence | Proprietary service under Cohere's Commercial SaaS Agreement. The SDKs are MIT | | Packages | pypi: `cohere`; npm: `cohere-ai`; go: `github.com/cohere-ai/cohere-go/v2` | | Source | https://github.com/cohere-ai/cohere-python | | Docs | https://docs.cohere.com/docs/chat-api | | llms.txt | https://docs.cohere.com/llms.txt | | Last release | 2026-09-09 | | Endpoint | `POST /v2/chat` on api.cohere.com per the OpenAPI file (the guide's examples use api.cohere.ai). `model` and `messages` required, 21 request fields, SSE streaming with `stream` | | Live Command models | `command-a-plus-05-2026` (128k context, 64k output, text and images), `command-a-03-2025` (256k, 8k), `command-a-reasoning-08-2025` (256k, 32k), `command-a-vision-07-2025` (128k, 8k), `command-a-translate-08-2025` (8k, 8k), `command-r-plus-08-2024`, `command-r-08-2024` and `command-r7b-12-2024` (128k, 4k) | | Rate limits | Trial 20 requests a minute per chat model and 1,000 calls a month. Production 500 a minute for Command A, R+, R, R7B and North Mini Code. Contact sales for Command A+, Reasoning, Translate and Vision | | Free tier | Trial key at sign-up, no card, not for production or commercial use | | Trains on API data | Paying customers can opt out under Data Controls. Trial use falls under the website terms and privacy policy | | Data retention | 30 days for logged prompts and generations unless flagged. Zero data retention by approval | | Data location | Google Cloud US-Central per the trust centre. Nine sub-processors listed, all in the US | | Structured output and tools | `response_format` with `json_object` or a JSON Schema, `tools` with `tool_choice` REQUIRED or NONE, `strict_tools` (beta), citations from `documents`, `thinking` with a token budget | | Batch | `/v2/batches` creates, lists, reads and cancels batches from an uploaded dataset. No batch price found | | Errors | 400, 401, 402, 404, 429, 499, 500 and others, each with sample messages. Bodies carry `message` and `id`, no error code. No Retry-After documented | | SDKs | Python `cohere` 7.1.0, TypeScript `cohere-ai` 8.1.0, Java 1.11.0 and Go v2.19.0, all tagged 26 August 2026, MIT | | Status | status.cohere.com on incident.io, a component per model, three incidents between 23 July and 1 September 2026 | | Certifications | SOC 2 Type II, ISO 27001, ISO 42001 and UK Cyber Essentials per the trust centre, with a bug bounty under a responsible disclosure policy | | Other deployments | Model Vault (Command A at $40 to $48 an instance-hour, by waitlist), private deployments, Amazon Bedrock and SageMaker, Azure AI Foundry and Oracle OCI | | Capabilities | inference.llm, inference.open-weights | | Tags | official, hosted, model, free-tier, no-card, openapi, llms-txt, openai-compatible, python, typescript, java, go, status-page, soc2, bug-bounty | | JSON | https://www.anchorterminal.com/api/v1/tools/cohere-chat.json | ## Score breakdown (methodology v0.4, October 2026 research run) Assessed 2026-10-09 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. | Category | Weight | This run | Score (0–100) | Points | | --- | --- | --- | --- | --- | | Reliability | 16% | 20 | 64 | 12.8 | | Performance | 10% | pending | pending | n/a | | Schema & documentation | 13% | 16.2 | 84 | 13.7 | | Agent ergonomics | 13% | 16.2 | 72 | 11.7 | | Security & auth | 14% | 17.5 | 57 | 10.0 | | Payments & pricing | 10% | 12.5 | 30 | 3.8 | | Task success | 10% | pending | pending | n/a | | Maintenance & community | 7% | 8.8 | 72 | 6.3 | | Transparency & trust (editorial 65, provenance 83) | 7% | 8.8 | 74 | 6.5 | | Negative events | up to −15 | up to −15 | none recorded | 0 | | **Total** | | | | **64.7 → B** | ### Why each score - Reliability 64: Hosted lines. status.cohere.com (incident.io) lists each Command model and the endpoints as components with uptime from July to October 2026 (20). Its feed shows three incidents in 90 days. 'Multiple Endpoint Disruptions' on 1 September 2026 touched embeddings, rerank and `command-a-reasoning-08-2025`, with no duration in the feed, and the other two were docs loading on 5 August and dashboard login on 23 July. Model and endpoint uptime still reads 100 per cent, so we count minor incidents only (20). Chat limits are published per model, 20 requests a minute and 1,000 calls a month on a trial key and 500 a minute on a production key for Command A, R, R+ and R7B, while the four newest variants say contact sales (12 of 15). The errors page documents 429 with sample messages. No Retry-After header, backoff guidance or idempotency key was found (5 of 15). cohere.com/slo is titled Service Level Objective and its text is script-drawn, so it was unread and scores as absent (0). The v2 chat endpoint is the default docs version, but the sample response on the chat guide still carries `is_experimental` and the newest models are not open to production keys (7 of 10). - 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. - Schema & documentation 84: Model reading. Public OpenAPI 3.1 file `cohere-openapi.yaml` in cohere-ai/cohere-developer-experience, 43 operations, last changed 29 September 2026 (25). docs.cohere.com/llms.txt and a Markdown twin of every page by adding `.md`, though the llms.txt files list no pages (8 of 10). The v2 chat operation describes each of its 21 request fields with defaults and limits, and says less about when to prefer one option (16 of 20). Enums on `tool_choice`, `safety_mode` and `thinking.type`, numeric bounds on `temperature`, `k`, `p` and `priority`, with penalties bounded only in prose (12 of 15). Eight request examples on the operation and an errors page with sample messages for each status code, with error bodies carrying a message and no machine code (12 of 15). v1 and v2 live side by side in the path and the changelog is dated, but the OpenAPI file is version 1.0 throughout and its changes are committed as 'Add spec changes' with no per-change note (11 of 15). - Agent ergonomics 72: Model reading. Function calling with `tool_choice` REQUIRED or NONE and `strict_tools`, which the reference marks beta (17 of 20). `response_format` takes `json_object` or a JSON Schema, with limits documented and no support in RAG mode (13 of 15). The usage object reports `cached_tokens`, and no guide or price for prompt caching was found (5 of 15). Context is 256,000 tokens on Command A and Command A Reasoning and 128,000 on Command A+ (10 of 15). `/v2/batches` runs a batch from an uploaded dataset, with no price or discount found (6 of 10). Official SDKs for Python, TypeScript, Java and Go (10). Error messages are specific and readable, with no stable error codes (11 of 15). - Security & auth 57: Model reading. Bearer keys of two kinds, trial and production. Team roles are Owner and User, only Owners delete production keys, and a production key is shown in full once. No scopes, expiry or per-model restriction was found (18 of 30). Paying customers can switch training off under Data Controls, which implies it is on until they do, trial keys fall under the website terms, and the SaaS agreement grants an irrevocable right to use API data to improve the services and share it with third parties (8 of 20). Logged prompts and generations are deleted after 30 days unless flagged, and zero data retention needs approval (12 of 15). The dashboard shows usage history, and no customer audit log was found (2 of 15). The trust centre lists SOC 2 Type II, ISO 27001, ISO 42001, UK Cyber Essentials, penetration tests on request and a responsible disclosure policy with a bug bounty. cohere.com/.well-known/security.txt answers 404 (17 of 20). - Payments & pricing 30: No x402, MPP or L402 in the docs, the OpenAPI file or the pricing page (0). The docs say Command models are billed per input and output token, and the pricing page's Generative models tab is script-drawn, so current prices were unread. The page text shows only legacy prices, such as $2.50 and $10.00 per million tokens for Command R+ 08-2024. Half marks, and the gap is ours to state (10 of 20). A trial key is created at sign-up and is free with no card (20). Sign-up is in a browser, and a production key needs an Owner to complete a Go to Production form (0). - 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. - Maintenance & community 72: Model reading. The last dated release on the Chat endpoint is North Small Translate on 9 September 2026, 30 days before the check. The last Command model is Command A+ on 20 May 2026, and the SDKs last shipped on 26 August, so we score the 90-day band (20 of 30). The deprecations page defines Active, Legacy, Deprecated and Shutdown and promises email notice, with no minimum notice period (6 of 12). No chat model was retired in the last 90 days. The last retirement was two Aya models on 4 April 2026 (8 of 8). Dated changelog with three entries since 27 August, one of them for a chat model (12 of 15). SDK issue replies not sampled (5 of 10). Python SDK 7.0.7, 7.0.8, 7.0.9 and 7.1.0 between 21 July and 26 August 2026, with TypeScript 8.1.0, Java 1.11.0 and Go v2.19.0 on 26 August (15). The Python SDK is generated from the OpenAPI file and has a CI workflow, whose runs we did not read (6 of 10). - Transparency & trust 74: Closed service under a published SaaS agreement, MIT SDKs, and the docs say Command A+ weights are on Hugging Face under Apache 2.0, which we did not open (15 of 30). The Enterprise Data Commitments (5 December 2025) and the privacy policy (1 May 2026) agree on 30-day retention and a training opt-out. The SaaS agreement (8 April 2025) does not mention the opt-out and grants an irrevocable right to use and share API data, and the DPA is sent on request (16 of 30). Deprecations page with dated history back to 2024 and lifecycle terms, no minimum notice (16 of 20). The trust centre names nine sub-processors, all in the US, and Google Cloud US-Central as the data location (18 of 20). Fix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (20 items): https://www.anchorterminal.com/fixes/cohere-chat.md (JSON https://www.anchorterminal.com/fixes/cohere-chat.json) ### What we couldn't check - unchecked: current per-token prices for Command A, Command A+ and the other live Command models. The Generative models tab of cohere.com/pricing is script-drawn - unchecked: the Service Level Objective at cohere.com/slo, whose text is script-drawn. Reliability scores an SLA as absent - unchecked: the Data Processing Addendum, sent on request, and the SOC 2 report, behind an NDA - unchecked: the Hugging Face page for Command A+ weights and its licence - unchecked: duration and scope of the 1 September 2026 'Multiple Endpoint Disruptions' incident, which the feed gives only as resolved - unchecked: GitHub stars, download counts and issue responsiveness for the SDK repositories - The chat guide's examples call api.cohere.ai while the OpenAPI file names api.cohere.com as the server. Both are Cohere domains and we sent nothing to either - Whether training on prompts is on by default for paying customers is implied by the opt-out toggle and not stated in the pages read - docs.cohere.com/llms.txt carries a section headed 'Instructions for AI Agents' (append `.md`, use the docs MCP server). Recorded as a fact and not acted on beyond reading Markdown twins - The SaaS agreement bars use of the services for benchmarking or competitive analysis. No deduction, and it matters before any probe is run - A slip on our side. One typed address, docs.cohere.com/docs/rate-limit.md, answered 404 and yielded nothing. The real page was then read from the docs source ### Sources - Chat API guide (Markdown twin): (seen 2026-10-09) - docs llms.txt: (seen 2026-10-09) - OpenAPI description file, read in the docs repository and not as the rendered reference: (seen 2026-10-09) - rate limits page, read from the docs source the page links: (seen 2026-10-09) - models overview, read from the docs source: (seen 2026-10-09) - Command A+ model page, read from the docs source: (seen 2026-10-09) - deprecations page, read from the docs source: (seen 2026-10-09) - errors page, read from the docs source: (seen 2026-10-09) - pricing guide, read from the docs source: (seen 2026-10-09) - changelog: (seen 2026-10-09) - pricing page: (seen 2026-10-09) - legal centre: (seen 2026-10-09) - Commercial SaaS Agreement, last updated 8 April 2025: (seen 2026-10-09) - Enterprise Data Commitments, 5 December 2025: (seen 2026-10-09) - privacy policy, 1 May 2026: (seen 2026-10-09) - security page: (seen 2026-10-09) - trust centre: (seen 2026-10-09) - status page: (seen 2026-10-09) - status incident feed: (seen 2026-10-09) - Python SDK tags: (seen 2026-10-09) - TypeScript SDK tags: (seen 2026-10-09) - RDAP record for cohere.com: (seen 2026-10-09) ## Who's behind it (provenance 83/100, checked 2026-10-09) | Check | Finding | Points | | --- | --- | --- | | Legal entity named | Cohere Inc. | 20/20 | | Domain age | cohere.com, registered 2000-03-07 (26 years) | 15/15 | | Endpoint on the vendor's domain | api.cohere.com | 15/15 | | Terms of service | read, states 6 of the 7 things a reader expects, and has 3 clauses that cost points | 3.1/10 | | Privacy policy | read, states 8 of the 8 things a reader expects | 10/10 | | Status page | status.cohere.com | 10/10 | | Changelog | published | 10/10 | | security.txt | not found | 0/10 | The Commercial SaaS Agreement (last updated 8 April 2025) names Cohere Inc., 171 John Street, Suite 200, Toronto, Ontario, and is governed by Ontario law. The privacy policy (last updated 1 May 2026) says it does not apply to customer inputs and outputs under an enterprise agreement, which the agreement and a DPA govern. The DPA is sent on request. The OpenAPI file names https://api.cohere.com as the server and the chat guide's examples call https://api.cohere.ai. Both are Cohere's. cohere.com/.well-known/security.txt answers 404. The trust centre holds a responsible disclosure policy for the bug bounty. status.cohere.ai redirects to status.cohere.com, whose robots.txt answers 404, so the host publishes no rules. RDAP for cohere.com gives a registration date of 2000-03-07. ### Terms and privacy, as read A reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice. **Terms of service** (https://cohere.com/saas-agreement), read 2026-10-09, dated 2025-04-08, states 6 of the 7 things a reader expects. - To know. Says it may use customer content to train or improve models, and no opt-out was found (costs points). "(III) IMPROVE AND ENHANCE THE SERVICES AND COHERE’S OTHER OFFERINGS AND BENCHMARK THE FOREGOING, INCLUDING BY SHARING API DATA AND FINETUNING DATA WITH THIRD PARTIES WHO MAY USE THE FINETUNING DATA AND API DATA TO PROVIDE SERVICES TO COHERE" - To know. Restricts benchmarking or competitive use (costs points). "THE COHERE API SAAS SERVICES MAY NOT BE ACCESSED FOR PURPOSES OF MONITORING ITS AVAILABILITY, PERFORMANCE OR FUNCTIONALITY, OR FOR ANY OTHER BENCHMARKING OR COMPETITIVE PURPOSES." - To know. Says the terms or the service can change without notice (costs points). "Cohere reserves the right to change the Cohere API and related Documentation at any time and without notice." - To know. Says access can be ended without notice or for any reason. "suspend or revoke Customer’s access to or use of the Cohere Products or Services, at any time, for any reason, including:" - Gives the date it was last updated. Last updated 2025-04-08. - Names the governing law or courts. The law of the Province of Ontario. - States a limit on its liability. Capped at $1,000.00. - Says how changes to the terms are announced. Says it gives notice of a change. - Not found in the text. Refers to a service level or uptime commitment. - Also in the text (2026-10-08). API data and finetuning data may be shared with third parties, whose own terms may let them use it for their own purposes. "ANY FINETUNING DATA OR API DATA SHARED BY COHERE WITH THIRD PARTIES WILL BE ACCESSED, USED, AND OTHERWISE HANDLED BY SUCH THIRD PARTIES IN ACCORDANCE WITH THEIR TERMS AND CONDITIONS, WHICH MAY PERMIT SUCH THIRD PARTY TO USE FINETUNING DATA OR API DATA FOR ITS OWN PURPOSES." - Also in the text (2026-10-08). After the agreement ends, Cohere has no obligation to delete API data or finetuning data the customer submitted. "Notwithstanding the foregoing, Cohere will have no obligation to delete or otherwise render inaccessible any API Data or Finetuning Data submitted by Customer to Cohere in accordance with Section 3(a)(iii)." - Also in the text (2026-10-08). Cohere may use the customer's name, logo and trademark in its publicity and disclose that the agreement exists. "Cohere may use Customer’s name, logo and trademark in conjunction with any Publicity and disclose the existence of this Agreement, the Cohere API SaaS Services provided to Customer and any testimonials received from Customer in any such Publicity." **Privacy policy** (https://cohere.com/privacy), read 2026-10-08, dated 2026-05-01, states 8 of the 8 things a reader expects. - To know. Says it may use customer content to train or improve models, and gives an opt-out. "Enterprise Users can control how we train on their data and can request a DPA if personal information will be processed in the course of using Cohere Products." - To know. Says it sells personal data or shares it for advertising. "The use of cookies for this purpose may be considered a “sale” or “sharing” under California privacy law." - Gives the date it was last updated. Last updated 2026-05-01. - Says how long data is kept. Names a period of 30 days. - Says whether personal data is sold or shared for advertising. Says it does not sell personal data. - Gives a privacy contact. privacy@cohere.com. - Says where data is transferred or stored. Relies on standard contractual clauses. - Also in the text (2026-10-08). Content submitted and outputs generated under free trial accounts and on research platforms may be used for research and development. "We may use this input and output data to conduct research and development." - Also in the text (2026-10-08). The policy does not cover inputs and outputs of enterprise users under an enterprise agreement, which that agreement governs. "To Customer Data: This Policy does not apply to Customer Data (i.e. inputs and outputs) associated with the use of Cohere Products by Enterprise Users under an enterprise agreement." - Also in the text (2026-10-08). Fullstory records interactions with the website or platform, including mouse movements, clicks, scrolling and typing. "We use Fullstory to capture and analyze your digital experience and interactions with our Website or Platform (such as mouse movements, clicks, scrolling and typing)." ## Live (updated 2026-10-10 02:54 UTC) - Right now: up, HTTP 401, 139 ms, checked 2026-10-10 02:54 UTC (get on `https://api.cohere.com/v2/chat`, asks for auth) - Uptime 24h 100.0% (115 probes) · 30 days 100.0% (115 probes) · p50 144 ms · p95 241 ms - Vendor status page: none, All Systems Operational - github `cohere-ai/cohere-python` 7.1.0, released 2026-08-26 - npm `cohere-ai` 8.1.0 - pypi `cohere` 7.2.0, released 2026-09-28 - Watching changelog , last changed 2026-10-07 18:04 UTC - Watching deprecations - Watching privacy , last changed 2026-10-08 18:16 UTC - Watching terms - Always current: https://www.anchorterminal.com/api/v1/live/cohere-chat.json ## Probe metrics Not 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. ## Models and prices (per 1M tokens) | Model | Input | Output | Context | Role | Supports | | --- | --- | --- | --- | --- | --- | | `command-r-plus-08-2024` Command R+ 08-2024 | $2.50 | $10 | 128k | mid (the only live Command model whose price is in the pricing page's text, listed there under legacy models. Prices for Command A and A+ were unread) | tool calling, structured output | Supports: as OpenRouter's public model list reports it, checked 2026-10-09 22:59 UTC. Rate limits depend on your account tier: https://docs.cohere.com/docs/rate-limits ## Dated changes - 2026-04-04 · Shutdown · `embed-english-v2.0`, `embed-multilingual-v2.0`, `c4ai-aya-expanse-8b` and `c4ai-aya-vision-8b` retired (source: ) - 2025-09-15 · Notice · `command`, `command-light`, `command-r-03-2024`, `command-r-plus-04-2024`, `/v1/generate`, `/v1/summarize`, `/v1/classify`, connectors and fine-tuning deprecated (source: ) All listings, as a calendar: https://www.anchorterminal.com/sunsets.ics ## Strengths - Public OpenAPI 3.1 file in the docs repository, last changed 29 September 2026, and a Markdown twin of every docs page - A trial key is created at sign-up with no card, limited to 20 chat requests a minute and 1,000 calls a month - Official SDKs for Python, TypeScript, Java and Go, each with a release on 26 August 2026 - JSON Schema structured outputs, `strict_tools` (beta), citations, reasoning budgets and safety modes on the v2 chat request - The trust centre lists SOC 2 Type II, ISO 27001, ISO 42001 and a bug bounty, with nine sub-processors, all in the US ## Weaknesses - Production keys work like trial keys on Command A+, Reasoning, Translate and Vision. The docs send production use of those models to sales or to Model Vault - Prices for current Command models sit in a script-drawn tab of the pricing page that we could not read. Only legacy prices appear in the page text - The SaaS agreement of 8 April 2025 grants Cohere an irrevocable right to use API data to improve its services and to share it with third parties - No Retry-After header, backoff guidance or idempotency key was found in the reviewed documentation - The SaaS agreement forbids use of the services for benchmarking or competitive analysis. Recorded as a fact, and it matters before any probe is run ## Before you call it (notes for agents) 1. Call `POST https://api.cohere.com/v2/chat` with `Authorization: bearer `. `model` and `messages` are the only required fields 2. Use `command-a-03-2025`, `command-r-08-2024`, `command-r-plus-08-2024` or `command-r7b-12-2024` for production traffic. Newer variants stay at trial limits on a production key 3. Keep a trial key under 20 chat requests a minute and 1,000 calls a month, and do not use it for commercial work 4. Set `response_format` with a `json_schema` for structured output, and tell the model to produce JSON when using `json_object` without a schema 5. Ask the account Owner to turn off training under Data Controls in the dashboard before sending confidential prompts ## Connect Install: ```bash pip install cohere # or: npm i cohere-ai ``` First request: ```bash curl --request POST \ --url https://api.cohere.ai/v2/chat \ --header 'accept: application/json' \ --header 'content-type: application/json' \ --header "Authorization: bearer $CO_API_KEY" \ --data '{"model":"command-a-plus-05-2026","messages":[{"role":"user","content":"Hello"}]}' ``` ## Similar tools Ranked by shared capabilities, then score. Same-category tools with no shared capability key are listed last. | Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown | | --- | --- | --- | --- | --- | --- | --- | | GroqCloud | BB | 75.6 | 44 | inference.llm, inference.open-weights | no | https://www.anchorterminal.com/tools/groq.md | | Mistral AI API | BB | 71.2 | 135 | inference.llm, inference.open-weights | no | https://www.anchorterminal.com/tools/mistral-api.md | | Cloudflare Workers AI | B | 68.3 | 224 | inference.llm, inference.open-weights | no | https://www.anchorterminal.com/tools/cloudflare-workers-ai.md | | SambaCloud | B | 66.4 | 293 | inference.llm, inference.open-weights | no | https://www.anchorterminal.com/tools/sambanova.md | | DeepInfra | B | 63 | 411 | inference.llm, inference.open-weights | no | https://www.anchorterminal.com/tools/deepinfra.md | | Prism Inference | C | 60.1 | 528 | inference.open-weights, inference.llm | no | https://www.anchorterminal.com/tools/prism-inference.md | ## Panel reviews (0) Reviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): . Desk 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 ## Notable - Production keys work like trial keys for newer model variants such as Command A Reasoning, and the rate-limit table says contact sales for Command A+, Reasoning, Translate and Vision (source: ) - The Command A+ page says the model can be used in production through Model Vault and that its weights are on Hugging Face under Apache 2.0 (source: ) - The SaaS agreement, last updated 8 April 2025, grants Cohere an irrevocable right to use customer data to improve its services, including by sharing API data with third parties, and forbids benchmarking (source: ) - Logged prompts and generations are deleted after 30 days unless flagged, training can be switched off under Data Controls, and zero data retention needs approval (source: ) - An OpenAI-style Compatibility API answers at https://api.cohere.ai/compatibility/v1 (source: ) - The September 2025 deprecation round covered `/v1/generate`, `/v1/summarize`, `/v1/classify`, connectors and all fine-tuning (source: ) - #11 of 17 in Best model APIs and inference for AI agents: https://www.anchorterminal.com/best/inference/index.md - All 136 models comparisons: https://www.anchorterminal.com/compare/inference/index.md ## Compare - [Claude API vs Cohere Chat API (Command models)](https://www.anchorterminal.com/compare/anthropic-api-vs-cohere-chat.md): BB 77.3 vs B 64.7 - [Antseed vs Cohere Chat API (Command models)](https://www.anchorterminal.com/compare/antseed-vs-cohere-chat.md): C 55.1 vs B 64.7 - [BlockRun.AI vs Cohere Chat API (Command models)](https://www.anchorterminal.com/compare/blockrun-ai-vs-cohere-chat.md): BB 72.4 vs B 64.7 - [Cloudflare AI Gateway vs Cohere Chat API (Command models)](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-cohere-chat.md): B 66.8 vs B 64.7 - [Cloudflare Workers AI vs Cohere Chat API (Command models)](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-cohere-chat.md): B 68.3 vs B 64.7 - [Cohere Chat API (Command models) vs DeepInfra](https://www.anchorterminal.com/compare/cohere-chat-vs-deepinfra.md): B 64.7 vs B 63 - [Cohere Chat API (Command models) vs DeepSeek API](https://www.anchorterminal.com/compare/cohere-chat-vs-deepseek-api.md): B 64.7 vs D 46.8 - [Cohere Chat API (Command models) vs Gemini Developer API](https://www.anchorterminal.com/compare/cohere-chat-vs-gemini-api.md): B 64.7 vs B 65.5 - [Cohere Chat API (Command models) vs GroqCloud](https://www.anchorterminal.com/compare/cohere-chat-vs-groq.md): B 64.7 vs BB 75.6 - [Cohere Chat API (Command models) vs Mistral AI API](https://www.anchorterminal.com/compare/cohere-chat-vs-mistral-api.md): B 64.7 vs BB 71.2 - [Cohere Chat API (Command models) vs Novita AI](https://www.anchorterminal.com/compare/cohere-chat-vs-novita-ai.md): B 64.7 vs D 53.5 - [Cohere Chat API (Command models) vs OpenAI API](https://www.anchorterminal.com/compare/cohere-chat-vs-openai-api.md): B 64.7 vs A 83.3 - [Cohere Chat API (Command models) vs OpenRouter](https://www.anchorterminal.com/compare/cohere-chat-vs-openrouter.md): B 64.7 vs B 68.5 - [Cohere Chat API (Command models) vs Prism Inference](https://www.anchorterminal.com/compare/cohere-chat-vs-prism-inference.md): B 64.7 vs C 60.1 - [Cohere Chat API (Command models) vs SambaCloud](https://www.anchorterminal.com/compare/cohere-chat-vs-sambanova.md): B 64.7 vs B 66.4 - [Cohere Chat API (Command models) vs SiliconFlow](https://www.anchorterminal.com/compare/cohere-chat-vs-siliconflow.md): B 64.7 vs D 46.7 ## Verify this listing For the vendor. The badge or a plain link to this page verifies the listing, from a page on cohere.com or one of its subdomains, or the README of github.com/cohere-ai/cohere-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": "cohere-chat", "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 HTML badge: ```html Cohere Chat API (Command models) on Anchor Terminal ``` Markdown badge, for a README: ```markdown [![Cohere Chat API (Command models) on Anchor Terminal](https://www.anchorterminal.com/badges/cohere-chat.svg)](https://www.anchorterminal.com/tools/cohere-chat) ``` Plain link: ```html Cohere Chat API (Command models) on Anchor Terminal ``` ## Share this listing For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Cohere Chat API (Command models) is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score. - Dark: https://www.anchorterminal.com/assets/share/cohere-chat-dark.png - Light: https://www.anchorterminal.com/assets/share/cohere-chat-light.png