{ "data": { "a": { "slug": "cohere-chat", "name": "Cohere Chat API (Command models)", "vendor": "Cohere", "vendorUrl": "https://cohere.com", "kind": "model", "category": "inference", "summary": "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.", "url": "https://www.anchorterminal.com/tools/cohere-chat", "markdownUrl": "https://www.anchorterminal.com/tools/cohere-chat.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/cohere-chat.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/cohere-chat.json", "repo": "https://github.com/cohere-ai/cohere-python", "license": "Proprietary service under Cohere's Commercial SaaS Agreement. The SDKs are MIT", "transports": [ "http" ], "remoteUrl": "https://api.cohere.com/v2/chat", "packages": [ { "registry": "pypi", "name": "cohere" }, { "registry": "npm", "name": "cohere-ai" }, { "registry": "go", "name": "github.com/cohere-ai/cohere-go/v2" } ], "auth": "api-key", "authNotes": "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", "pricingNotes": "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).", "priceSummary": "from $2.50 / 1M in", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, the OpenAPI file or the pricing page (checked 2026-10-09).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-09" }, "docsUrl": "https://docs.cohere.com/docs/chat-api", "rateLimitsUrl": "https://docs.cohere.com/docs/rate-limits", "llmsTxt": "https://docs.cohere.com/llms.txt", "openapi": "https://raw.githubusercontent.com/cohere-ai/cohere-developer-experience/main/cohere-openapi.yaml", "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" ], "lastRelease": "2026-09-09", "graded": true, "anchor": { "graded": true, "score": 64.7, "grade": "B", "agentReady": false, "rank": 342, "ranked": true, "rankOf": 950, "categoryRank": 11, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 72, "maintenance": 72, "payments": 30, "reliability": 64, "schema": 84, "security": 57, "transparency": 74 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-09" }, "negative": 0, "verdict": "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.", "bestFor": "Teams that want Command models for RAG with citations, tool use and multilingual work, and that may later move to a private deployment or Model Vault.", "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" ], "agentNotes": [ "Call `POST https://api.cohere.com/v2/chat` with `Authorization: bearer \u003ckey\u003e`. `model` and `messages` are the only required fields", "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", "Keep a trial key under 20 chat requests a minute and 1,000 calls a month, and do not use it for commercial work", "Set `response_format` with a `json_schema` for structured output, and tell the model to produce JSON when using `json_object` without a schema", "Ask the account Owner to turn off training under Data Controls in the dashboard before sending confidential prompts" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 64.7 } ], "editorialScores": { "ergonomics": 72, "maintenance": 72, "payments": 30, "reliability": 64, "schema": 84, "security": 57, "transparency": 65 }, "provenanceScore": 83 }, "connect": { "install": "pip install cohere # or: npm i cohere-ai", "http": "curl --request POST \\\n --url https://api.cohere.ai/v2/chat \\\n --header 'accept: application/json' \\\n --header 'content-type: application/json' \\\n --header \"Authorization: bearer $CO_API_KEY\" \\\n --data '{\"model\":\"command-a-plus-05-2026\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello\"}]}'" }, "letme": { "capability": "https://letme.dev/inference.llm", "tool": "https://letme.dev/cohere-chat" }, "sameCompany": [ "cohere-embed", "cohere-north" ], "area": "models", "provenance": { "legalEntity": "Cohere Inc.", "domain": "cohere.com", "domainRegistered": "2000-03-07", "endpointOnVendorDomain": true, "terms": "https://cohere.com/saas-agreement", "privacy": "https://cohere.com/privacy", "statusPage": "https://status.cohere.com", "changelog": "https://docs.cohere.com/v2/changelog", "securityTxt": "none", "checked": "2026-10-09", "notes": [ "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." ], "score": 83 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/cohere-chat.json", "live": { "slug": "cohere-chat", "probe": { "target": "https://api.cohere.com/v2/chat", "method": "get", "lastAt": "2026-10-10T02:54:51.393337293Z", "lastOk": true, "lastStatus": 401, "lastMs": 139, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 144, "p95ms24h": 241, "samples24h": 115, "samples30d": 115, "days": [ { "date": "2026-10-09", "probes": 85, "ok": 85 }, { "date": "2026-10-10", "probes": 30, "ok": 30 } ] }, "vendorStatus": { "page": "https://status.cohere.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-10T02:50:05.337176394Z" }, "versions": [ { "registry": "github", "name": "cohere-ai/cohere-python", "version": "7.1.0", "released": "2026-08-26", "seenAt": "2026-10-09T16:46:32.363318225Z" }, { "registry": "npm", "name": "cohere-ai", "version": "8.1.0", "seenAt": "2026-10-09T16:46:31.955149363Z" }, { "registry": "pypi", "name": "cohere", "version": "7.2.0", "released": "2026-09-28", "seenAt": "2026-10-09T16:46:31.750729672Z" } ], "githubStars": 404, "npmWeekly": 446483, "pypiWeekly": 2506118, "pages": [ { "url": "https://docs.cohere.com/v2/changelog", "kind": "changelog", "status": 304, "checkedAt": "2026-10-09T18:36:57.799784835Z", "changedAt": "2026-10-07T18:04:51.510283642Z", "fingerprint": "f82c6d389ba7" }, { "url": "https://docs.cohere.com/docs/deprecations", "kind": "deprecations", "status": 200, "checkedAt": "2026-10-09T18:36:55.160420163Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "9848f1f6c54c" }, { "url": "https://cohere.com/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-09T18:34:08.463769439Z", "changedAt": "2026-10-08T18:16:32.121838469Z", "fingerprint": "5ed49b0909fd" }, { "url": "https://cohere.com/saas-agreement", "kind": "terms", "status": 200, "checkedAt": "2026-10-09T18:34:10.296826504Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "09fbf37bff61" } ], "models": { "command-r-plus-08-2024": { "openrouterId": "cohere/command-r-plus-08-2024", "tools": true, "structuredOutputs": true, "jsonMode": true, "reasoning": false, "input": [ "text" ], "promptCaching": false, "contextTokens": 128000, "maxOutput": 4000, "checkedAt": "2026-10-09T22:59:28.49657734Z" } }, "updatedAt": "2026-10-10T02:54:51.393337293Z" } }, "answer": "Cohere Chat API (Command models) scores 64.7 (B) on agent readiness against Prism Inference's 60.1 (C), and leads in 4 of 7 scored categories. Prism Inference leads on security \u0026 auth.", "b": { "slug": "prism-inference", "name": "Prism Inference", "vendor": "Prism Technologies Inc", "vendorUrl": "https://prisminference.com", "kind": "model", "category": "inference", "summary": "Prism is a hosted inference API from Prism Technologies Inc for open-weight models, aimed at coding agents. It accepts OpenAI Chat Completions, OpenAI Responses and Anthropic Messages requests at api.prisminference.com. It launched on 24 September 2026.", "url": "https://www.anchorterminal.com/tools/prism-inference", "markdownUrl": "https://www.anchorterminal.com/tools/prism-inference.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/prism-inference.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/prism-inference.json", "repo": "https://github.com/prismhq/hermes-prism-provider", "license": "Proprietary service under Prism's terms of service. The OpenAPI file declares `LicenseRef-Proprietary`. The Hermes provider plugin repository carries no licence file", "transports": [ "http" ], "remoteUrl": "https://api.prisminference.com/v1", "packages": [], "auth": "api-key", "authNotes": "`Authorization: Bearer` with a key issued from account settings after sign-up at prisminference.com/signup. The inference endpoints also accept the key in `x-api-key`. A missing, invalid, expired or revoked key returns 401. No key scopes were found in the reviewed documentation. An agent can call `POST https://prisminference.com/api/agent-signups` with the owner's email and a username and receive a key once, but that key can't run inference until the owner supplies a six-digit emailed code, and it expires after 30 days. `GET /v1/models` needs no key.", "pricing": "usage", "pricingNotes": "Prepaid per-token pricing with no minimum. DeepSeek-V4.1-Flash is $0.09 in, $1.20 out and $0.06 cache read per million tokens, and Gemma 4 31B is $0.30, $0.40 and $0.15 (https://prisminference.com/pricing, matched by https://api.prisminference.com/v1/models). No free tier or trial credit was found, and a workspace without credit gets 402. A person funds the workspace in a browser. Elastic endpoints, dedicated deployments and batch are sold through sales with no published price.", "priceSummary": "from $0.09 / 1M in", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in llms.txt, the docs index, the OpenAPI file or the pricing page, read 2026-10-08. The docs describe prepaid credit funded by a person in the browser.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://docs.prisminference.com", "rateLimitsUrl": "https://docs.prisminference.com/rate-limits", "llmsTxt": "https://prisminference.com/llms.txt", "openapi": "https://docs.prisminference.com/openapi.yaml", "capabilities": [ "inference.fast", "inference.open-weights", "inference.llm" ], "tags": [ "hosted", "model", "open-weights", "fast", "usage-priced", "prepaid", "openapi", "llms-txt", "openai-compatible", "anthropic-compatible", "zero-retention", "status-page", "new" ], "lastRelease": "2026-10-06", "graded": true, "anchor": { "graded": true, "score": 60.1, "grade": "C", "agentReady": false, "rank": 528, "ranked": true, "rankOf": 950, "categoryRank": 13, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 68, "maintenance": 49, "payments": 30, "reliability": 65, "schema": 82, "security": 65, "transparency": 61 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": -2, "negativeNotes": [ "2026-10-08. The home page shows a '99.99% Uptime SLA' tile, and the pricing page says 'No minimums, no rate limits' above the per-token table. The terms of 9 September 2026 say the services have no guaranteed uptime or service credit unless a separate written agreement says otherwise, and the docs describe per-key rate limits that return 429. No SLA document was found. A misleading claim, with the smallest deduction because the terms and docs state the real position (https://prisminference.com/, https://prisminference.com/pricing, https://prisminference.com/terms, https://docs.prisminference.com/rate-limits)." ], "verdict": "Three wire formats, a public OpenAPI 3.1 file, per-token prices in a keyless catalogue and zero data retention by default on every tier. The service launched on 24 September 2026 with two models, one of them by request, from a two-person company. No rate-limit numbers, SLA document, free tier or deprecation policy was found.", "bestFor": "Coding agents that want DeepSeek-V4.1-Flash at a low input price, with no retention, through whichever of the three wire formats the harness already speaks.", "strengths": [ "One key works across OpenAI Chat Completions, OpenAI Responses and Anthropic Messages, with a public OpenAPI 3.1 file, llms.txt and Markdown docs", "Zero data retention is the default on every tier, and the privacy policy, terms and docs all say inputs and outputs are never used for training", "Every error carries a stable `code`, a `retryable` flag, a `fix` hint and a `docs_url`, and 429 carries `Retry-After` in seconds", "`GET /v1/models` answers without a key and returns context length, maximum output and per-token prices for each model", "DeepSeek-V4.1-Flash is listed with a 1M-token context and 384,000 output tokens at $0.09 in and $1.20 out per million" ], "weaknesses": [ "Two models. The docs mark Gemma 4 31B as request access per organisation, while llms.txt and the keyless catalogue list it as available", "No rate-limit numbers are published. The docs say per-key limits exist, and the pricing page says 'no rate limits'", "The home page shows a '99.99% Uptime SLA' tile, while the terms say there is no guaranteed uptime without a separate written agreement", "No free tier found. Billing is prepaid, a person funds the workspace in a browser, and the agent sign-up key needs an emailed code", "The service launched on 24 September 2026. The changelog has one entry, and no deprecation policy, sub-processor list or certification was found" ], "agentNotes": [ "Call `GET https://api.prisminference.com/v1/models` at start-up, with no key, and use only ids it returns. Expect 403 on `gemma-4-31b` without organisation access", "Use base URL `https://api.prisminference.com/v1` for OpenAI clients and `https://api.prisminference.com` with no `/v1` for Anthropic clients", "Read `error.retryable` before retrying, and wait for `Retry-After` on 429, which covers both key limits and model capacity", "Send `reasoning_effort: \"none\"` or `low` when latency matters. Reasoning is on by default and its tokens are billed as output", "Keep conversation state yourself and send `store: false` on Responses. `previous_response_id`, stored responses and hosted tools aren't supported" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 60.1 } ], "editorialScores": { "ergonomics": 68, "maintenance": 49, "payments": 30, "reliability": 65, "schema": 82, "security": 65, "transparency": 43 }, "provenanceScore": 79 }, "connect": { "install": "pip install openai # or: npm install openai, base URL https://api.prisminference.com/v1. Anthropic SDKs use https://api.prisminference.com with no /v1", "http": "curl \"https://api.prisminference.com/v1/chat/completions\" \\\n -H \"Authorization: Bearer $PRISM_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"deepseek-v4.1-flash\",\"messages\":[{\"role\":\"user\",\"content\":\"Return pong.\"}]}'", "claudeCode": "export ANTHROPIC_BASE_URL=https://api.prisminference.com\nexport ANTHROPIC_AUTH_TOKEN=$PRISM_API_KEY\nexport ANTHROPIC_MODEL=deepseek-v4.1-flash\nexport ANTHROPIC_SMALL_FAST_MODEL=gemma-4-31b" }, "letme": { "capability": "https://letme.dev/inference.fast", "tool": "https://letme.dev/prism-inference" }, "area": "models", "provenance": { "legalEntity": "Prism Technologies Inc", "domain": "prisminference.com", "domainRegistered": "2026-09-09", "endpointOnVendorDomain": true, "terms": "https://prisminference.com/terms", "privacy": "https://prisminference.com/privacy", "statusPage": "https://status.prisminference.com", "changelog": "https://docs.prisminference.com/changelog", "securityTxt": "valid", "checked": "2026-10-08", "notes": [ "The terms and the privacy policy, both last updated 9 September 2026, name Prism Technologies Inc. The terms are governed by California law with arbitration in San Francisco.", "RDAP gives a registration date of 2026-09-09 for prisminference.com, with Name.com as registrar.", "security.txt has a Contact line (founders@prisminference.com), an Expires date of 2027-10-06 and a Canonical line. No disclosure policy or bug bounty is named.", "The status page runs on incident.io with one component for each model and no component for the API or the website. Its incidents feed was empty on 8 October 2026.", "The YC directory lists Prism in the Spring 2025 batch, in San Francisco, with a team of 2. The home page links an X account named prism_videos, from the company's earlier video product." ], "score": 79 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/prism-inference.json", "live": { "slug": "prism-inference", "probe": { "target": "https://api.prisminference.com/v1", "method": "get", "lastAt": "2026-10-10T02:55:06.706259541Z", "lastOk": true, "lastStatus": 200, "lastMs": 131, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 149, "p95ms24h": 452, "samples24h": 249, "samples30d": 373, "days": [ { "date": "2026-10-08", "probes": 93, "ok": 93 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 30, "ok": 30 } ] }, "vendorStatus": { "page": "https://status.prisminference.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-10T02:50:43.671876128Z" }, "versions": [ { "registry": "github", "name": "prismhq/hermes-prism-provider", "version": "v1.0.2", "released": "2026-09-16", "seenAt": "2026-10-09T17:14:33.431257688Z" } ], "githubStars": 0, "securityTxt": { "url": "https://prisminference.com/.well-known/security.txt", "state": "valid", "expires": "2027-10-06T00:00:00.000Z", "checkedAt": "2026-10-09T15:40:35.003140299Z" }, "llmsTxt": { "url": "https://prisminference.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-09T14:02:37.937240222Z" }, "pages": [ { "url": "https://docs.prisminference.com/changelog", "kind": "changelog", "status": 304, "checkedAt": "2026-10-09T18:38:03.252133069Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "184a0fafdb8c" }, { "url": "https://prisminference.com/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-09T18:43:52.542857787Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "dffb5d16a3c8" }, { "url": "https://prisminference.com/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-09T18:43:54.77090078Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "64ea7b8f1b7b" }, { "url": "https://prisminference.com/terms", "kind": "terms", "status": 200, "checkedAt": "2026-10-09T18:43:56.713185583Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "27dd15c69f49" } ], "updatedAt": "2026-10-10T02:55:06.706259541Z" } }, "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Cohere", "b": "Prism Technologies Inc", "name": "Vendor" }, { "a": "https://api.cohere.com/v2/chat", "b": "https://api.prisminference.com/v1", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "API key", "b": "API key", "name": "Auth" }, { "a": "Freemium", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under Cohere's Commercial SaaS Agreement. The SDKs are MIT", "b": "Proprietary service under Prism's terms of service. The OpenAPI file declares `LicenseRef-Proprietary`. The Hermes provider plugin repository carries no licence file", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-09-09", "b": "2026-10-06", "name": "Last release" }, { "a": "2025-04-08", "b": "2026-09-09", "name": "Terms last updated" }, { "a": "2026-05-01", "b": "2026-09-09", "name": "Privacy policy last updated" }, { "a": "yes", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "yes", "name": "Terms restrict automated access" }, { "a": "yes", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "yes", "name": "Arbitration or class-action waiver" } ], "faq": [ { "answer": "Cohere Chat API (Command models) scores 64.7 (B) on agent readiness against Prism Inference's 60.1 (C), and leads in 4 of 7 scored categories. Prism Inference leads on security \u0026 auth.", "question": "Which is better for AI agents, Cohere Chat API (Command models) or Prism Inference?" }, { "answer": "Both need an API key.", "question": "Do Cohere Chat API (Command models) and Prism Inference need an API key?" }, { "answer": "Yes. Cohere Chat API (Command models) has a hosted endpoint at https://api.cohere.com/v2/chat and Prism Inference at https://api.prisminference.com/v1.", "question": "Can an agent call Cohere Chat API (Command models) and Prism Inference without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Maintenance \u0026 community, 72 against 49", "Transparency \u0026 trust, 74 against 61" ], "also": [ "Free to start without a card" ], "goodFor": "Teams that want Command models for RAG with citations, tool use and multilingual work, and that may later move to a private deployment or Model Vault.", "slug": "cohere-chat", "watchFor": "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" }, { "aheadOn": [ "Security \u0026 auth, 65 against 57" ], "also": null, "goodFor": "Coding agents that want DeepSeek-V4.1-Flash at a low input price, with no retention, through whichever of the three wire formats the harness already speaks.", "slug": "prism-inference", "watchFor": "Two models. The docs mark Gemma 4 31B as request access per organisation, while llms.txt and the keyless catalogue list it as available" } ], "job": { "capability": "inference.llm", "name": "LLM inference" }, "others": [ { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-cohere-chat.json", "title": "Claude API vs Cohere Chat API (Command models)", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-cohere-chat" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-prism-inference.json", "title": "Claude API vs Prism Inference", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/antseed-vs-cohere-chat.json", "title": "Antseed vs Cohere Chat API (Command models)", "url": "https://www.anchorterminal.com/compare/antseed-vs-cohere-chat" }, { "json": "https://www.anchorterminal.com/compare/antseed-vs-prism-inference.json", "title": "Antseed vs Prism Inference", "url": "https://www.anchorterminal.com/compare/antseed-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-cohere-chat.json", "title": "BlockRun.AI vs Cohere Chat API (Command models)", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-cohere-chat" }, { "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-prism-inference.json", "title": "BlockRun.AI vs Prism Inference", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-cohere-chat.json", "title": "Cloudflare AI Gateway vs Cohere Chat API (Command models)", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-cohere-chat" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-prism-inference.json", "title": "Cloudflare AI Gateway vs Prism Inference", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-cohere-chat.json", "title": "Cloudflare Workers AI vs Cohere Chat API (Command models)", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-cohere-chat" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-prism-inference.json", "title": "Cloudflare Workers AI vs Prism Inference", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-deepinfra.json", "title": "Cohere Chat API (Command models) vs DeepInfra", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-deepinfra" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-deepseek-api.json", "title": "Cohere Chat API (Command models) vs DeepSeek API", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-deepseek-api" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-gemini-api.json", "title": "Cohere Chat API (Command models) vs Gemini Developer API", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-gemini-api" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-groq.json", "title": "Cohere Chat API (Command models) vs GroqCloud", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-groq" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-mistral-api.json", "title": "Cohere Chat API (Command models) vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-novita-ai.json", "title": "Cohere Chat API (Command models) vs Novita AI", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-novita-ai" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-openai-api.json", "title": "Cohere Chat API (Command models) vs OpenAI API", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-openai-api" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-openrouter.json", "title": "Cohere Chat API (Command models) vs OpenRouter", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-openrouter" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-sambanova.json", "title": "Cohere Chat API (Command models) vs SambaCloud", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-sambanova" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-siliconflow.json", "title": "Cohere Chat API (Command models) vs SiliconFlow", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-siliconflow" }, { "json": "https://www.anchorterminal.com/compare/deepinfra-vs-prism-inference.json", "title": "DeepInfra vs Prism Inference", "url": "https://www.anchorterminal.com/compare/deepinfra-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/deepseek-api-vs-prism-inference.json", "title": "DeepSeek API vs Prism Inference", "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/gemini-api-vs-prism-inference.json", "title": "Gemini Developer API vs Prism Inference", "url": "https://www.anchorterminal.com/compare/gemini-api-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/groq-vs-prism-inference.json", "title": "GroqCloud vs Prism Inference", "url": "https://www.anchorterminal.com/compare/groq-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-prism-inference.json", "title": "Mistral AI API vs Prism Inference", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/novita-ai-vs-prism-inference.json", "title": "Novita AI vs Prism Inference", "url": "https://www.anchorterminal.com/compare/novita-ai-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/openai-api-vs-prism-inference.json", "title": "OpenAI API vs Prism Inference", "url": "https://www.anchorterminal.com/compare/openai-api-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/openrouter-vs-prism-inference.json", "title": "OpenRouter vs Prism Inference", "url": "https://www.anchorterminal.com/compare/openrouter-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/prism-inference-vs-siliconflow.json", "title": "Prism Inference vs SiliconFlow", "url": "https://www.anchorterminal.com/compare/prism-inference-vs-siliconflow" }, { "json": "https://www.anchorterminal.com/compare/prism-inference-vs-sambanova.json", "title": "Prism Inference vs SambaCloud", "url": "https://www.anchorterminal.com/compare/prism-inference-vs-sambanova" } ], "scores": [ { "by": 1, "cohere-chat": 64, "edge": "prism-inference", "key": "reliability", "name": "Reliability", "prism-inference": 65, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 2, "cohere-chat": 84, "edge": "cohere-chat", "key": "schema", "name": "Schema \u0026 documentation", "prism-inference": 82, "weight": 13 }, { "by": 4, "cohere-chat": 72, "edge": "cohere-chat", "key": "ergonomics", "name": "Agent ergonomics", "prism-inference": 68, "weight": 13 }, { "by": 8, "cohere-chat": 57, "edge": "prism-inference", "key": "security", "name": "Security \u0026 auth", "prism-inference": 65, "weight": 14 }, { "by": 0, "cohere-chat": 30, "edge": "", "key": "payments", "name": "Payments \u0026 pricing", "prism-inference": 30, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 23, "cohere-chat": 72, "edge": "cohere-chat", "key": "maintenance", "name": "Maintenance \u0026 community", "prism-inference": 49, "weight": 7 }, { "by": 13, "cohere-chat": 74, "edge": "cohere-chat", "key": "transparency", "name": "Transparency \u0026 trust", "prism-inference": 61, "weight": 7 } ], "summary": "Cohere Chat API (Command models) scores 64.7 (B) on agent readiness against Prism Inference's 60.1 (C), and leads in 4 of 7 scored categories. Prism Inference leads on security \u0026 auth. Both do llm inference.", "verdicts": { "cohere-chat": "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.", "prism-inference": "Three wire formats, a public OpenAPI 3.1 file, per-token prices in a keyless catalogue and zero data retention by default on every tier. The service launched on 24 September 2026 with two models, one of them by request, from a two-person company. No rate-limit numbers, SLA document, free tier or deprecation policy was found." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cohere-chat-vs-prism-inference", "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-prism-inference.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cohere-chat-vs-prism-inference.md", "slim": "https://www.anchorterminal.com/compare/cohere-chat-vs-prism-inference.min.md" }, "markdown": "Cohere Chat API (Command models) scores 64.7 (B) on agent readiness against Prism Inference's 60.1 (C), and leads in 4 of 7 scored categories. Prism Inference leads on security \u0026 auth. Both do llm inference.\n\n- Cohere Chat API (Command models): grade B, 64.7/100, rank #342 of 950. Markdown https://www.anchorterminal.com/tools/cohere-chat.md · JSON https://www.anchorterminal.com/api/v1/tools/cohere-chat.json\n- Prism Inference: grade C, 60.1/100, rank #528 of 950. Markdown https://www.anchorterminal.com/tools/prism-inference.md · JSON https://www.anchorterminal.com/api/v1/tools/prism-inference.json\n- Best model APIs and inference for AI agents: https://www.anchorterminal.com/best/inference/index.md\n- All 136 models comparisons: https://www.anchorterminal.com/compare/inference/index.md\n\n## Which one, for what\n\n### Cohere Chat API (Command models) (B)\n\nGood for: Teams that want Command models for RAG with citations, tool use and multilingual work, and that may later move to a private deployment or Model Vault.\n\nAhead on:\n- Maintenance \u0026 community, 72 against 49\n- Transparency \u0026 trust, 74 against 61\n\nAlso in its favour:\n- Free to start without a card\n\nWatch for: 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\n\n### Prism Inference (C)\n\nGood for: Coding agents that want DeepSeek-V4.1-Flash at a low input price, with no retention, through whichever of the three wire formats the harness already speaks.\n\nAhead on:\n- Security \u0026 auth, 65 against 57\n\nWatch for: Two models. The docs mark Gemma 4 31B as request access per organisation, while llms.txt and the keyless catalogue list it as available\n\n\n## Score by category\n\n| Category | Weight | Cohere Chat API (Command models) | Prism Inference | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 64 | 65 | Prism Inference +1 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 84 | 82 | Cohere Chat API (Command models) +2 |\n| Agent ergonomics | 13% (16.2 this run) | 72 | 68 | Cohere Chat API (Command models) +4 |\n| Security \u0026 auth | 14% (17.5 this run) | 57 | 65 | Prism Inference +8 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 30 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 72 | 49 | Cohere Chat API (Command models) +23 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 74 | 61 | Cohere Chat API (Command models) +13 |\n| Negative events | ≤15 | 0 | -2 | |\n| **Total** | | **64.7 · B** | **60.1 · C** | |\n\n## Facts side by side\n\n| Fact | Cohere Chat API (Command models) | Prism Inference |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Cohere | Prism Technologies Inc |\n| Hosted endpoint | `https://api.cohere.com/v2/chat` | `https://api.prisminference.com/v1` |\n| Transports | HTTP | HTTP |\n| Auth | API key | API key |\n| Pricing | Freemium | Pay per use |\n| x402 | no | no |\n| Licence | Proprietary service under Cohere's Commercial SaaS Agreement. The SDKs are MIT | Proprietary service under Prism's terms of service. The OpenAPI file declares `LicenseRef-Proprietary`. The Hermes provider plugin repository carries no licence file |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-09-09 | 2026-10-06 |\n| Terms last updated | 2025-04-08 | 2026-09-09 |\n| Privacy policy last updated | 2026-05-01 | 2026-09-09 |\n| Customer content may train models | yes | not found in the text |\n| Terms restrict automated access | not found in the text | yes |\n| Terms restrict benchmarking | yes | not found in the text |\n| Terms or service can change without notice | yes | not found in the text |\n| Arbitration or class-action waiver | not found in the text | yes |\n\n## Verdicts\n\n**Cohere Chat API (Command models).** 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.\n\n**Prism Inference.** Three wire formats, a public OpenAPI 3.1 file, per-token prices in a keyless catalogue and zero data retention by default on every tier. The service launched on 24 September 2026 with two models, one of them by request, from a two-person company. No rate-limit numbers, SLA document, free tier or deprecation policy was found.\n\n## Before you call either\n\n### Cohere Chat API (Command models)\n\n1. Call `POST https://api.cohere.com/v2/chat` with `Authorization: bearer \u003ckey\u003e`. `model` and `messages` are the only required fields\n2. 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\n3. Keep a trial key under 20 chat requests a minute and 1,000 calls a month, and do not use it for commercial work\n4. Set `response_format` with a `json_schema` for structured output, and tell the model to produce JSON when using `json_object` without a schema\n5. Ask the account Owner to turn off training under Data Controls in the dashboard before sending confidential prompts\n\n### Prism Inference\n\n1. Call `GET https://api.prisminference.com/v1/models` at start-up, with no key, and use only ids it returns. Expect 403 on `gemma-4-31b` without organisation access\n2. Use base URL `https://api.prisminference.com/v1` for OpenAI clients and `https://api.prisminference.com` with no `/v1` for Anthropic clients\n3. Read `error.retryable` before retrying, and wait for `Retry-After` on 429, which covers both key limits and model capacity\n4. Send `reasoning_effort: \"none\"` or `low` when latency matters. Reasoning is on by default and its tokens are billed as output\n5. Keep conversation state yourself and send `store: false` on Responses. `previous_response_id`, stored responses and hosted tools aren't supported\n\n## Questions\n\n### Which is better for AI agents, Cohere Chat API (Command models) or Prism Inference?\n\nCohere Chat API (Command models) scores 64.7 (B) on agent readiness against Prism Inference's 60.1 (C), and leads in 4 of 7 scored categories. Prism Inference leads on security \u0026 auth.\n\n### Do Cohere Chat API (Command models) and Prism Inference need an API key?\n\nBoth need an API key.\n\n### Can an agent call Cohere Chat API (Command models) and Prism Inference without installing anything?\n\nYes. Cohere Chat API (Command models) has a hosted endpoint at https://api.cohere.com/v2/chat and Prism Inference at https://api.prisminference.com/v1.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cohere-chat-vs-prism-inference.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cohere-chat-vs-prism-inference.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cohere-chat\", \"b\": \"prism-inference\"}`. From a terminal: `anchor compare cohere-chat prism-inference`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cohere-chat.json and https://www.anchorterminal.com/api/v1/tools/prism-inference.json\n\n## Other comparisons with Cohere Chat API (Command models) or Prism Inference\n\n- [Claude API vs Cohere Chat API (Command models)](https://www.anchorterminal.com/compare/anthropic-api-vs-cohere-chat.md)\n- [Claude API vs Prism Inference](https://www.anchorterminal.com/compare/anthropic-api-vs-prism-inference.md)\n- [Antseed vs Cohere Chat API (Command models)](https://www.anchorterminal.com/compare/antseed-vs-cohere-chat.md)\n- [Antseed vs Prism Inference](https://www.anchorterminal.com/compare/antseed-vs-prism-inference.md)\n- [BlockRun.AI vs Cohere Chat API (Command models)](https://www.anchorterminal.com/compare/blockrun-ai-vs-cohere-chat.md)\n- [BlockRun.AI vs Prism Inference](https://www.anchorterminal.com/compare/blockrun-ai-vs-prism-inference.md)\n- [Cloudflare AI Gateway vs Cohere Chat API (Command models)](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-cohere-chat.md)\n- [Cloudflare AI Gateway vs Prism Inference](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-prism-inference.md)\n- [Cloudflare Workers AI vs Cohere Chat API (Command models)](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-cohere-chat.md)\n- [Cloudflare Workers AI vs Prism Inference](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-prism-inference.md)\n- [Cohere Chat API (Command models) vs DeepInfra](https://www.anchorterminal.com/compare/cohere-chat-vs-deepinfra.md)\n- [Cohere Chat API (Command models) vs DeepSeek API](https://www.anchorterminal.com/compare/cohere-chat-vs-deepseek-api.md)\n- [Cohere Chat API (Command models) vs Gemini Developer API](https://www.anchorterminal.com/compare/cohere-chat-vs-gemini-api.md)\n- [Cohere Chat API (Command models) vs GroqCloud](https://www.anchorterminal.com/compare/cohere-chat-vs-groq.md)\n- [Cohere Chat API (Command models) vs Mistral AI API](https://www.anchorterminal.com/compare/cohere-chat-vs-mistral-api.md)\n- [Cohere Chat API (Command models) vs Novita AI](https://www.anchorterminal.com/compare/cohere-chat-vs-novita-ai.md)\n- [Cohere Chat API (Command models) vs OpenAI API](https://www.anchorterminal.com/compare/cohere-chat-vs-openai-api.md)\n- [Cohere Chat API (Command models) vs OpenRouter](https://www.anchorterminal.com/compare/cohere-chat-vs-openrouter.md)\n- [Cohere Chat API (Command models) vs SambaCloud](https://www.anchorterminal.com/compare/cohere-chat-vs-sambanova.md)\n- [Cohere Chat API (Command models) vs SiliconFlow](https://www.anchorterminal.com/compare/cohere-chat-vs-siliconflow.md)\n- [DeepInfra vs Prism Inference](https://www.anchorterminal.com/compare/deepinfra-vs-prism-inference.md)\n- [DeepSeek API vs Prism Inference](https://www.anchorterminal.com/compare/deepseek-api-vs-prism-inference.md)\n- [Gemini Developer API vs Prism Inference](https://www.anchorterminal.com/compare/gemini-api-vs-prism-inference.md)\n- [GroqCloud vs Prism Inference](https://www.anchorterminal.com/compare/groq-vs-prism-inference.md)\n- [Mistral AI API vs Prism Inference](https://www.anchorterminal.com/compare/mistral-api-vs-prism-inference.md)\n- [Novita AI vs Prism Inference](https://www.anchorterminal.com/compare/novita-ai-vs-prism-inference.md)\n- [OpenAI API vs Prism Inference](https://www.anchorterminal.com/compare/openai-api-vs-prism-inference.md)\n- [OpenRouter vs Prism Inference](https://www.anchorterminal.com/compare/openrouter-vs-prism-inference.md)\n- [Prism Inference vs SiliconFlow](https://www.anchorterminal.com/compare/prism-inference-vs-siliconflow.md)\n- [Prism Inference vs SambaCloud](https://www.anchorterminal.com/compare/prism-inference-vs-sambanova.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-10", "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": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Cohere Chat API (Command models) vs Prism Inference", "url": "" } ], "description": "Cohere Chat scores 64.7 (B) to Prism Inference's 60.1 (C) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Cohere Chat API (Command models) B 64.7", "Prism Inference C 60.1", "scores" ], "h1": "Cohere Chat API (Command models) vs Prism Inference", "image": "https://www.anchorterminal.com/assets/og/compare-cohere-chat-vs-prism-inference.png", "path": "/compare/cohere-chat-vs-prism-inference", "published": "2026-10-01", "section": "tools", "title": "Cohere Chat vs Prism Inference for AI agents (2026) | Anchor Terminal", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-prism-inference" }, "tokens": { "markdown": 2900, "slim": 730 }, "version": 1 }