{ "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", "dns": "cohere-chat.grade.anchorterminal.com", "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", "main": true }, { "registry": "npm", "name": "cohere-ai", "main": true }, { "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. The pricing page lists Command R at $0.15 and $0.60 and Command R7B at $0.0375 and $0.15 per million input and output tokens, Command R+ 08-2024 at $2.50 and $10.00 among legacy prices, and Command A+ as free. No price is published for Command A, Reasoning, Vision or Translate. Production keys stay at trial limits on Command A+, Reasoning, Translate and Vision (checked 2026-11-02).", "priceSummary": "from $0.0375 / 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": 65.6, "grade": "B", "agentReady": false, "rank": 407, "ranked": true, "rankOf": 1486, "categoryRank": 17, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 72, "maintenance": 72, "payments": 35, "reliability": 67, "schema": 84, "security": 55, "transparency": 75 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-02" }, "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 and prices 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 and Go, each tagged on 21 October 2026, and Java 1.12.0", "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", "The pricing page lists per-token prices for Command R, R7B and R+ only. Command A, Reasoning, Vision and Translate have no published price", "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, and only the R models have published prices", "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": 4, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 65.6 } ], "editorialScores": { "ergonomics": 72, "maintenance": 72, "payments": 35, "reliability": 67, "schema": 84, "security": 55, "transparency": 66 }, "provenanceScore": 84, "checked": { "categories": { "ergonomics": "2026-11-02", "maintenance": "2026-11-02", "payments": "2026-11-02", "reliability": "2026-11-02", "schema": "2026-11-02", "security": "2026-11-02", "transparency": "2026-11-02" }, "last": "2026-11-02", "lastMoved": "2026-11-02", "oldest": "2026-11-02", "stale": false, "staleAfterDays": 90 } }, "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-transcribe-03-2026", "cohere-north" ], "area": "models", "unitPrices": [ { "item": "Command R input", "unit": "1m-tokens", "usd": 0.15 }, { "item": "Command R output", "unit": "1m-tokens", "usd": 0.6 }, { "item": "Command R7B input", "unit": "1m-tokens", "usd": 0.0375 }, { "item": "Command R7B output", "unit": "1m-tokens", "usd": 0.15 }, { "item": "Command R+ 08-2024 input", "unit": "1m-tokens", "usd": 2.5, "note": "Listed among legacy prices" }, { "item": "Command R+ 08-2024 output", "unit": "1m-tokens", "usd": 10, "note": "Listed among legacy prices" } ], "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": 84 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/cohere-chat.json", "live": { "slug": "cohere-chat", "probe": { "target": "https://api.cohere.com/v2/chat", "method": "get", "lastAt": "2026-11-07T18:20:18.115200055Z", "lastOk": true, "lastStatus": 401, "lastMs": 189, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 147, "p95ms24h": 240, "samples24h": 239, "samples30d": 7205, "days": [ { "date": "2026-10-09", "probes": 85, "ok": 85 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 256, "ok": 256 }, { "date": "2026-10-19", "probes": 255, "ok": 255 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 253, "ok": 253 }, { "date": "2026-10-22", "probes": 253, "ok": 253 }, { "date": "2026-10-23", "probes": 248, "ok": 248 }, { "date": "2026-10-24", "probes": 251, "ok": 251 }, { "date": "2026-10-25", "probes": 250, "ok": 250 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 251, "ok": 251 }, { "date": "2026-10-29", "probes": 249, "ok": 249 }, { "date": "2026-10-30", "probes": 248, "ok": 248 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 248, "ok": 248 }, { "date": "2026-11-04", "probes": 246, "ok": 246 }, { "date": "2026-11-05", "probes": 185, "ok": 185 }, { "date": "2026-11-06", "probes": 241, "ok": 241 }, { "date": "2026-11-07", "probes": 187, "ok": 187 } ] }, "vendorStatus": { "page": "https://status.cohere.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-07T18:20:54.526327774Z" }, "versions": [ { "registry": "github", "name": "cohere-ai/cohere-python", "version": "7.3.2", "released": "2026-11-04", "seenAt": "2026-11-06T23:16:28.900178589Z" }, { "registry": "npm", "name": "cohere-ai", "version": "8.3.1", "seenAt": "2026-11-06T23:16:28.548336782Z" }, { "registry": "pypi", "name": "cohere", "version": "7.3.1", "released": "2026-11-04", "seenAt": "2026-11-06T23:16:28.43430084Z" } ], "githubStars": 407, "npmWeekly": 665965, "pypiWeekly": 2576815, "securityTxt": { "url": "https://cohere.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:21.413669602Z" }, "llmsTxt": { "url": "https://docs.cohere.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:06.118223513Z" }, "domain": { "domain": "cohere.com", "registered": "2000-03-07", "source": "https://rdap.verisign.com/com/v1/domain/cohere.com", "checkedAt": "2026-11-01T14:17:56.515021491Z" }, "pages": [ { "url": "https://docs.cohere.com/v2/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:05:42.882438737Z", "changedAt": "2026-11-05T12:29:46.428343553Z", "fingerprint": "de6e890a268c" }, { "url": "https://docs.cohere.com/docs/deprecations", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-07T14:05:40.811028032Z", "changedAt": "2026-11-05T12:29:44.384806051Z", "fingerprint": "a4d483f2b397" }, { "url": "https://cohere.com/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:01:41.226639318Z", "changedAt": "2026-11-06T13:24:23.148883162Z", "fingerprint": "1028bd69de2b" }, { "url": "https://cohere.com/saas-agreement", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:01:43.258823927Z", "changedAt": "2026-11-06T13:24:25.375763846Z", "fingerprint": "0bbd8836589f" } ], "models": { "command-r-08-2024": { "openrouterId": "cohere/command-r-08-2024", "tools": true, "structuredOutputs": true, "jsonMode": true, "reasoning": false, "input": [ "text" ], "promptCaching": false, "contextTokens": 128000, "maxOutput": 4000, "checkedAt": "2026-11-06T23:49:25.225778715Z" }, "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": "2026-11-06T23:49:25.225778715Z" }, "command-r7b-12-2024": { "openrouterId": "cohere/command-r7b-12-2024", "tools": false, "structuredOutputs": true, "jsonMode": true, "reasoning": false, "input": [ "text" ], "promptCaching": false, "contextTokens": 128000, "maxOutput": 4000, "checkedAt": "2026-11-06T23:49:25.225778715Z" } }, "github": { "repo": "cohere-ai/cohere-python", "checkedAt": "2026-11-02T08:40:26.40131968Z", "stars": 407, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-27T15:54:03Z", "openIssues": 0, "openPRs": 19, "issuesOpened90d": 10, "issuesClosed90d": 10, "prsMerged90d": 7, "ci": { "branch": "main", "runs": 43, "success": 34, "failure": 9, "other": 0, "latest": "failure", "latestAt": "2026-10-27T16:05:54Z" }, "replies": { "sampled": 25, "unanswered": 0, "medianDays": 9.2 } }, "updatedAt": "2026-11-07T18:20:18.115200055Z" } }, "answer": "xAI API (Grok) scores 71.7 (BB) on agent readiness against Cohere Chat API (Command models)'s 65.6 (B), and leads in 4 of 7 scored categories. Cohere Chat API (Command models) leads on reliability, payments \u0026 pricing and transparency \u0026 trust.", "b": { "slug": "xai-api", "name": "xAI API (Grok)", "vendor": "SpaceXSI (xAI)", "vendorUrl": "https://x.ai", "kind": "model", "category": "inference", "summary": "xAI's API for its Grok models (the docs now name the company SpaceXSI), with text, image, video and voice endpoints, server-side search and remote MCP tools, through an OpenAI-compatible REST API or gRPC.", "url": "https://www.anchorterminal.com/tools/xai-api", "markdownUrl": "https://www.anchorterminal.com/tools/xai-api.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/xai-api.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/xai-api.json", "dns": "xai-api.grade.anchorterminal.com", "repo": "https://github.com/xai-org/xai-sdk-python", "license": "Proprietary service under xAI's enterprise terms of service. The Python SDK is Apache-2.0", "transports": [ "http" ], "remoteUrl": "https://api.x.ai/v1", "packages": [ { "registry": "pypi", "name": "xai-sdk" } ], "auth": "api-key", "authNotes": "`Authorization: Bearer` with a team API key from console.x.ai. Keys can be limited to endpoints and models by ACL, capped by QPM and TPM, given an expiry, and rotated or disabled through the Management API. mTLS is documented as an option, and GitHub secret scanning disables leaked keys.", "pricing": "usage", "pricingNotes": "Prepaid credits, then the default payment method at month end. Grok 4.7 costs $2 input, $0.50 cached input and $6 output per 1M tokens below 200K prompt tokens, and $4/$1/$12 above, applied to the whole request. Batch is 20% off on grok-4.7, 4.6, 4.5, 4.3 and the grok-4.20 models. Priority processing 2x, the US regional endpoint 1.1x. Web search, code execution and attachment search $5 per 1,000 calls, collections search $2.50, X search $5 per 1,000 posts. $0.05 fee for a request blocked before generation for a usage-policy violation (https://docs.x.ai/developers/pricing, checked 2026-11-06).", "priceSummary": "from $1.25 / 1M in", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, llms.txt or the OpenAPI spec. Access needs a console account loaded with prepaid credits (checked 2026-11-06).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 597, "npmWeekly": null, "pypiWeekly": 912149, "asOf": "2026-11-06" }, "docsUrl": "https://docs.x.ai", "rateLimitsUrl": "https://docs.x.ai/developers/rate-limits", "llmsTxt": "https://docs.x.ai/llms.txt", "openapi": "https://docs.x.ai/openapi.json", "capabilities": [ "inference.llm" ], "tags": [ "official", "hosted", "model", "prepaid", "openapi", "llms-txt", "openai-compatible", "closed-source", "python", "batch", "status-page", "bug-bounty", "soc2" ], "lastRelease": "2026-11-02", "graded": true, "anchor": { "graded": true, "score": 71.7, "grade": "BB", "agentReady": true, "rank": 151, "ranked": true, "rankOf": 1486, "categoryRank": 8, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 90, "maintenance": 77, "payments": 20, "reliability": 55, "schema": 88, "security": 97, "transparency": 63 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "Grok 4.7 at $2/$6 per million tokens, now 20% off in batch, with a public OpenAPI spec, llms.txt, API keys limited by endpoint and model, and self-serve zero data retention. The API endpoints had a 3 hour 40 minute models outage on 3 September 2026, no SLA was found, and there's no free tier or first-party SDK beyond Python.", "bestFor": "Agents that want a capable model at a low per-token price with built-in web and X search, remote MCP and voice, and teams that need self-serve ZDR or US-only processing.", "strengths": [ "Grok 4.7 at $2/$6 per million tokens below 200K prompt tokens, with a 500K context and 20% off through the Batch API", "API keys restricted by endpoint and model ACLs, with QPM and TPM caps, expiry and a rotate endpoint", "Self-serve team-wide zero data retention, confirmed on every response by an `x-zero-data-retention` header", "OpenAPI 3.1 spec, llms.txt and a Markdown twin of every docs page", "security.txt valid to 2027-06-29 and a HackerOne bug bounty" ], "weaknesses": [ "API models outage of about 3 hours 40 minutes on 3 September 2026, and high error rates on grok-4.6 and grok-4.5 on 17 August", "No SLA, no free tier for the text API, and no Retry-After header documented for 429s", "No stated minimum notice for retirements, and retired slugs are served by a different model at its price", "Remote MCP doesn't support `require_approval`, so server-side tool calls run without an approval step", "The terms, privacy policy and DPA at x.ai/legal answered a Cloudflare block on 6 October and 6 November 2026, so they weren't read" ], "agentNotes": [ "Build on the Responses API at https://api.x.ai/v1. Chat Completions is labelled deprecated and the Anthropic-compatible endpoint fully deprecated", "Pin a dated model slug. A retired slug keeps answering from a replacement model, billed at the replacement's price", "Back off exponentially on 429. The per-second cap is the per-minute budget divided by 48, with a minimum of 2", "Set `allowed_tools` on remote MCP servers. There's no approval step, and every exposed tool enters the context", "Use https://us.api.x.ai/v1 when processing must stay in the US. It costs 1.1x and serves only grok-4.7 and grok-4.6" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 71.7 } ], "editorialScores": { "ergonomics": 90, "maintenance": 77, "payments": 20, "reliability": 55, "schema": 88, "security": 97, "transparency": 52 }, "provenanceScore": 73, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install xai-sdk # or: pip install openai, with base_url https://api.x.ai/v1", "http": "curl https://api.x.ai/v1/responses \\\n -H \"Authorization: Bearer $XAI_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"grok-4.7\",\"input\":\"What is the meaning of life?\"}'" }, "letme": { "capability": "https://letme.dev/inference.llm", "tool": "https://letme.dev/xai-api" }, "area": "models", "unitPrices": [ { "item": "Web search tool", "unit": "1k-requests", "usd": 5 }, { "item": "Code execution tool", "unit": "1k-requests", "usd": 5 }, { "item": "Collections search tool", "unit": "1k-requests", "usd": 2.5 } ], "provenance": { "legalEntity": "", "domain": "x.ai", "domainRegistered": "2017-12-16", "domainNote": "x.ai was registered in 2017, before the company, and transferred on 2026-06-02 per RDAP. Every x.ai page except robots.txt and security.txt answered a Cloudflare block page (403) on 2026-11-06, as the legal pages did on 2026-10-06, so the contracting entity wasn't confirmed. The docs now use the name SpaceXSI and the status page SpaceXAI.", "endpointOnVendorDomain": true, "terms": "https://x.ai/legal/terms-of-service-enterprise", "privacy": "https://x.ai/legal/privacy-policy", "statusPage": "https://status.x.ai", "changelog": "https://docs.x.ai/developers/release-notes", "securityTxt": "valid", "checked": "2026-11-06", "notes": [ "x.ai/robots.txt allows all but /tools/, with Content-Signal ai-train=yes, search=yes, ai-input=yes. docs.x.ai allows all with ai-input=yes. The x.ai pages that robots.txt allows answered a Cloudflare 'Attention Required' page, which we did not try to get past.", "security.txt at x.ai/.well-known/security.txt is valid to 2027-06-29, with vulnerabilities@x.ai and abuse@x.ai." ], "score": 73 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/xai-api.json", "live": { "slug": "xai-api", "probe": { "target": "https://api.x.ai/v1", "method": "get", "lastAt": "2026-11-07T18:21:06.440217402Z", "lastOk": true, "lastStatus": 404, "lastMs": 122, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 178, "p95ms24h": 276, "samples24h": 200, "samples30d": 200, "days": [ { "date": "2026-11-06", "probes": 13, "ok": 13 }, { "date": "2026-11-07", "probes": 187, "ok": 187 } ] }, "vendorStatus": { "page": "https://status.x.ai", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-07T04:49:01.143662157Z" }, "versions": [ { "registry": "github", "name": "xai-org/xai-sdk-python", "version": "v1.21.0", "released": "2026-10-23", "seenAt": "2026-11-07T00:18:15.193708838Z" }, { "registry": "pypi", "name": "xai-sdk", "version": "1.21.0", "released": "2026-10-23", "seenAt": "2026-11-07T00:18:15.09038487Z" } ], "githubStars": 598, "pypiWeekly": 912149, "securityTxt": { "url": "https://x.ai/.well-known/security.txt", "state": "valid", "expires": "2027-06-29T00:00:00.000Z", "checkedAt": "2026-11-07T16:01:43.978620532Z" }, "llmsTxt": { "url": "https://docs.x.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:34:24.762831371Z" }, "pages": [ { "url": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-07T14:08:46.034096807Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "1238569c8142" }, { "url": "https://docs.x.ai/developers/migration/may-15-retirement", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-07T14:08:48.207542223Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "813d0e188a0e" }, { "url": "https://docs.x.ai/developers/release-notes", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-07T14:08:52.143682141Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "7b37cfaf2576" }, { "url": "https://docs.x.ai/developers/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:08:50.158330981Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "a563de9617fe" }, { "url": "https://x.ai/legal/privacy-policy", "kind": "privacy", "status": 403, "checkedAt": "2026-11-07T14:38:04.991061235Z", "changedAt": "0001-01-01T00:00:00Z" }, { "url": "https://x.ai/legal/terms-of-service-enterprise", "kind": "terms", "status": 403, "checkedAt": "2026-11-07T14:38:09.200382604Z", "changedAt": "0001-01-01T00:00:00Z" } ], "updatedAt": "2026-11-07T18:21:06.440217402Z" } }, "edges": [ { "by": 42, "category": "security", "leads": "xai-api", "name": "Security \u0026 auth", "reasons": { "a": "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, per the 9 October check. cohere.com/.well-known/security.txt still answers 404 on 2 November and no public advisories were found, so the line takes 15, as cohere-embed and cohere-north read the same programme (15 of 20).", "b": "Model reading. Team API keys with ACLs per endpoint and per model, QPM and TPM caps, expiry, and create, rotate, disable and delete through the Management API, plus documented mTLS. GitHub secret scanning disables leaked keys and emails the owner (30). The security FAQ says SpaceXSI never trains on API inputs or outputs without explicit permission (20). Requests and responses are kept 30 days for abuse auditing, then deleted, and team admins can switch on zero data retention themselves, confirmed by an `x-zero-data-retention` header on every response (15). Console audit log and a Management API audit-events endpoint, plus optional per-key request logging (15). security.txt valid to 2027-06-29 with a HackerOne bug bounty and a separate safety contact for prompt-injection issues. SOC 2 Type 2 is claimed in the security FAQ with the reports behind an NDA in the trust centre, so 17 of 20. Remote MCP doesn't support `require_approval`, which the model checklist doesn't score but reviewers should see. New in October, a `guidelines` array lets the caller make the model decline nsfw, violence or profanity content, which the checklist doesn't score." }, "scores": { "a": 55, "b": 97 } }, { "by": 18, "category": "ergonomics", "leads": "xai-api", "name": "Agent ergonomics", "reasons": { "a": "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).", "b": "Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Function calling with parallel calls on by default and `tool_choice` of auto, required, none or a named function (20). Guaranteed structured outputs (15). Automatic prompt caching, cached input at 0.25x on grok-4.7 ($0.50 per million) and 0.16x on grok-4.3 (15). 500,000-token context on grok-4.7 and 1,000,000 on grok-4.3, 13 of 15 for the default model's 500K. The Batch API is now 20% off on grok-4.7, 4.6 and 4.5 as well as the older models, with batch requests outside the rate limits (10 of 10, up from 5 on 6 October). One first-party SDK, `xai-sdk` for Python, with the OpenAI SDKs and Vercel's AI SDK documented as alternatives (5 of 10). Status codes documented with fixes, no Retry-After header found (12 of 15)." }, "scores": { "a": 72, "b": 90 } }, { "by": 15, "category": "payments", "leads": "cohere-chat", "name": "Payments \u0026 pricing", "reasons": { "a": "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. The pricing page, read on 2 November 2026, now carries per-unit prices in its own page data, Command R at $0.15 input and $0.60 output and Command R7B at $0.0375 and $0.15 per million tokens, with Command R+ 08-2024 at $2.50 and $10.00 among legacy prices and Command A+ shown as free. No price is published for Command A, Reasoning, Vision or Translate, so the line takes 15 rather than the full 20 (15 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).", "b": "No x402, MPP or L402 (0). Per-token and per-call prices published without a login on docs.x.ai/developers/pricing (20). No free tier found for the text API, and the quickstart says to load the account with credits (0). Sign-up is in the browser at console.x.ai. The Management API can create keys and top up prepaid credit, but only with a management key made by a person in the console, so no line credit (0)." }, "scores": { "a": 35, "b": 20 } }, { "by": 12, "category": "reliability", "leads": "cohere-chat", "name": "Reliability", "reasons": { "a": "Hosted lines. status.cohere.com (incident.io) lists each Command model and the endpoints as components (20). Its feed, read on 2 November 2026, shows two incidents in the 90 days from 4 August. 'Multiple Endpoint Disruptions' on 1 September 2026, from 15:41 to 19:47 UTC, degraded the embeddings endpoint, embed-v4.0, two rerank models and `command-a-reasoning-08-2025` during a Google Cloud outage, rated minor and partial, and docs loading failed on 5 August. Nothing has been posted since 1 September, so 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 example messages that say to wait and try again later and links to the rate limits, with no Retry-After header, backoff timing or idempotency key, the reading cohere-embed takes of the same page (8 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).", "b": "Status page at status.x.ai with components for the global and US API endpoints, voice, the consumer apps and, since the Cursor merger, Cursor's services, with an RSS feed (20). The feed, read on 6 November, now holds 267 incidents back to 11 August, so the whole 90-day window is readable. On the API components there were high error rates on grok-4.6 and grok-4.5 from 21:57 to 23:28 UTC on 17 August (about 90 minutes) and a models outage on the global and US endpoints from 13:30 to 17:09 UTC on 3 September (about 3 hours 40 minutes), so several majors. A 26-minute datacenter outage across the API on 22 September, voice disruptions of 12 and 28 minutes on 10 September and 6 October, a 63-minute voice and Imagine degradation on 30 October and a 37-second model degradation on 24 October add to the record (0). Rate limits published per model and tier, grok-4.7 at Tier 0 is 150 requests a second and 50M TPM, with the per-second cap derived as RPM divided by 48 (15). The rate-limits page shows exponential backoff on 429, but no Retry-After header or overload guidance was found (10 of 15). No SLA found in the docs or llms.txt (0). The Responses API has been GA since September 2025 and grok-4.7 carries no preview label (10)." }, "scores": { "a": 67, "b": 55 } }, { "by": 12, "category": "transparency", "leads": "cohere-chat", "name": "Transparency \u0026 trust", "reasons": { "a": "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, and nothing newer than 4 April 2026 on 2 November, read at 15 as cohere-embed reads the same page (15 of 20). The trust centre names nine sub-processors with a location for each, all in the US, and Google Cloud US-Central as the data location, read at 20 as cohere-embed reads the same list (20 of 20).", "b": "Closed service under xAI's enterprise terms, with the Python SDK under Apache-2.0 (15). The docs agree with each other on no training, 30-day abuse retention, 30-day storage of stateful responses and the ZDR route, but the privacy policy, enterprise terms and DPA at x.ai/legal answered a Cloudflare block page on 6 October and again on 6 November, so they couldn't be compared (15 of 30). Dated migration guides and redirect tables for each retirement, but no written deprecation policy, and Chat Completions, Anthropic compatibility and grok-voice-2.0 are labelled deprecated with no date (12 of 20). The US regional endpoint states what stays in the US, the global endpoint guarantees no region, and no subprocessor list was readable (10 of 20)." }, "scores": { "a": 75, "b": 63 } }, { "by": 5, "category": "maintenance", "leads": "xai-api", "name": "Maintenance \u0026 community", "reasons": { "a": "Model reading. The last dated release on the Chat endpoint is still North Small Translate on 9 September 2026, 54 days before this check. The last Command model is Command A+ on 20 May 2026. Rerank 5 (21 October) and Embed 5 (30 September) aren't chat changes, 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 or announced for retirement in the last 90 days. The newest entry on the page is still two Aya models retired on 4 April 2026 (8 of 8). Dated changelog with four entries since 4 August (27 August, 9 September, 30 September, 21 October), one of them for a chat model (12 of 15). SDK issue replies not sampled (5 of 10). Python SDK 7.2.0 and 7.3.0, TypeScript 8.2.0 (19 October) and 8.3.0, and Go v2.20.0 tagged on 21 October 2026, Java at 1.12.0 (15). The Python SDK is generated from the OpenAPI file and has a CI workflow, whose runs we did not read (6 of 10).", "b": "Model reading. grok-imagine-image-quality and grok-imagine-image-pro retired on 2 November 2026 as announced in September, Grok Voice 3.0 and custom moderation controls in October, Grok 4.7 on 21 September (30). No minimum notice period found. Retirements come as dated migration guides, retired slugs redirect to a replacement rather than failing, billed at the replacement's price, and grok-voice-2.0 was deprecated in October with no end date (4 of 12). Shutdowns in the last 90 days with dates given in advance, `grok-voice-transcribe-1.0` on 2 October and `grok-imagine-image-quality` on 2 November (8 of 8). Release notes several times a month but dated only by month, support by email and a Discord #help channel, not tested. On xai-sdk-python a collaborator commented on 2 of the 16 most recent threads with replies, and most outside pull requests since 23 October are open without a maintainer reply (10 of 15, down from 12). The repository has CI, release and version-bump workflows (5 of 10). One current first-party SDK, `xai-sdk` 1.21.0 tagged on 23 October, Python only (10 of 15). Supported runtimes stated, Python 3.10 or later (10)." }, "scores": { "a": 72, "b": 77 } } ], "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Cohere", "b": "SpaceXSI (xAI)", "name": "Vendor" }, { "a": "https://api.cohere.com/v2/chat", "b": "https://api.x.ai/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 xAI's enterprise terms of service. The Python SDK is Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-09-09", "b": "2026-11-02", "name": "Last release" }, { "a": "2025-04-08", "b": "2026-10-27", "name": "Terms last updated" }, { "a": "2026-05-01", "b": "2026-10-27", "name": "Privacy policy last updated" }, { "a": "yes", "b": "yes", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "not found in the text", "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" }, { "a": "none", "b": "597 stars, 912k PyPI/wk", "name": "Popularity" }, { "a": "3/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "xAI API (Grok) scores 71.7 (BB) on agent readiness against Cohere Chat API (Command models)'s 65.6 (B), and leads in 4 of 7 scored categories. Cohere Chat API (Command models) leads on reliability, payments \u0026 pricing and transparency \u0026 trust.", "question": "Which is better for AI agents, Cohere Chat API (Command models) or xAI API (Grok)?" }, { "answer": "Both need an API key.", "question": "Do Cohere Chat API (Command models) and xAI API (Grok) need an API key?" }, { "answer": "Yes. Cohere Chat API (Command models) has a hosted endpoint at https://api.cohere.com/v2/chat and xAI API (Grok) at https://api.x.ai/v1.", "question": "Can an agent call Cohere Chat API (Command models) and xAI API (Grok) without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 67 against 55", "Payments \u0026 pricing, 35 against 20", "Transparency \u0026 trust, 75 against 63" ], "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": [ "Agent ergonomics, 90 against 72", "Security \u0026 auth, 97 against 55", "Maintenance \u0026 community, 77 against 72" ], "also": [ "Agent-ready, a grade of BB or better" ], "goodFor": "Agents that want a capable model at a low per-token price with built-in web and X search, remote MCP and voice, and teams that need self-serve ZDR or US-only processing.", "slug": "xai-api", "watchFor": "API models outage of about 3 hours 40 minutes on 3 September 2026, and high error rates on grok-4.6 and grok-4.5 on 17 August" } ], "history": { "cohere-chat": [ { "causes": [ "evidence", "correction" ], "date": "2026-11-02", "delta": 0.9, "from": 64.7, "fromGrade": "B", "to": 65.6, "toGrade": "B" }, { "causes": [ "method" ], "date": "2026-10-28", "delta": 0, "from": 64.7, "fromGrade": "B", "to": 64.7, "toGrade": "B" } ], "xai-api": null }, "job": { "capability": "inference.llm", "name": "LLM inference" }, "others": [ { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-cohere-chat.json", "title": "Amazon Bedrock vs Cohere Chat API (Command models)", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-cohere-chat" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-xai-api.json", "title": "Amazon Bedrock vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-xai-api" }, { "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-xai-api.json", "title": "Claude API vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-xai-api" }, { "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-xai-api.json", "title": "Antseed vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/antseed-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-cohere-chat.json", "title": "Azure OpenAI in Foundry Models vs Cohere Chat API (Command models)", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-cohere-chat" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-xai-api.json", "title": "Azure OpenAI in Foundry Models vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-xai-api" }, { "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-xai-api.json", "title": "BlockRun.AI vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/cerebras-inference-vs-cohere-chat.json", "title": "Cerebras Inference vs Cohere Chat API (Command models)", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-cohere-chat" }, { "json": "https://www.anchorterminal.com/compare/cerebras-inference-vs-xai-api.json", "title": "Cerebras Inference vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-xai-api" }, { "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-xai-api.json", "title": "Cloudflare AI Gateway vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-xai-api" }, { "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-xai-api.json", "title": "Cloudflare Workers AI vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-xai-api" }, { "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-eden-ai.json", "title": "Cohere Chat API (Command models) vs Eden AI", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-eden-ai" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-elorian-glimpse.json", "title": "Cohere Chat API (Command models) vs Glimpse", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-elorian-glimpse" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-fireworks-inference.json", "title": "Cohere Chat API (Command models) vs Fireworks AI Inference", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-fireworks-inference" }, { "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-hugging-face-inference-providers.json", "title": "Cohere Chat API (Command models) vs Hugging Face Inference Providers", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-hugging-face-inference-providers" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-inkling-2-small.json", "title": "Cohere Chat API (Command models) vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-jais-3.json", "title": "Cohere Chat API (Command models) vs Jais 3", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-meta-model-api.json", "title": "Cohere Chat API (Command models) vs Meta Model API", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-minimax-api.json", "title": "Cohere Chat API (Command models) vs MiniMax API", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-minimax-api" }, { "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-muse-spark-open.json", "title": "Cohere Chat API (Command models) vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-muse-spark-open" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-nemotron-3-5-super-vl.json", "title": "Cohere Chat API (Command models) vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-nemotron-3-5-super-vl" }, { "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-prism-inference.json", "title": "Cohere Chat API (Command models) vs Prism Inference", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-ramp-router.json", "title": "Cohere Chat API (Command models) vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-reflection-beam.json", "title": "Cohere Chat API (Command models) vs Beam 1.0", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-reflection-beam" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-routerplus.json", "title": "Cohere Chat API (Command models) vs RouterPlus", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-routerplus" }, { "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/cohere-chat-vs-simplismart.json", "title": "Cohere Chat API (Command models) vs Simplismart", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-simplismart" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-stepfun-api.json", "title": "Cohere Chat API (Command models) vs StepFun API", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-stepfun-api" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-swe-2-flash.json", "title": "Cohere Chat API (Command models) vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-tencent-tokenhub.json", "title": "Cohere Chat API (Command models) vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-together-inference.json", "title": "Cohere Chat API (Command models) vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-together-inference" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-vercel-ai-gateway.json", "title": "Cohere Chat API (Command models) vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-vertex-ai.json", "title": "Cohere Chat API (Command models) vs Vertex AI (Gemini Enterprise Agent Platform)", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-vertex-ai" }, { "json": "https://www.anchorterminal.com/compare/deepinfra-vs-xai-api.json", "title": "DeepInfra vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/deepinfra-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/deepseek-api-vs-xai-api.json", "title": "DeepSeek API vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/eden-ai-vs-xai-api.json", "title": "Eden AI vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/eden-ai-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-xai-api.json", "title": "Glimpse vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-xai-api.json", "title": "Fireworks AI Inference vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/gemini-api-vs-xai-api.json", "title": "Gemini Developer API vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/gemini-api-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/groq-vs-xai-api.json", "title": "GroqCloud vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/groq-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-xai-api.json", "title": "Hugging Face Inference Providers vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-xai-api.json", "title": "Inkling 2 Small vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-xai-api.json", "title": "Jais 3 vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/jais-3-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-xai-api.json", "title": "Meta Model API vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/minimax-api-vs-xai-api.json", "title": "MiniMax API vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/minimax-api-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-xai-api.json", "title": "Mistral AI API vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-xai-api.json", "title": "Muse Spark Open vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-xai-api.json", "title": "Nemotron 3.5 Super VL vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/novita-ai-vs-xai-api.json", "title": "Novita AI vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/novita-ai-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/openai-api-vs-xai-api.json", "title": "OpenAI API vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/openai-api-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/openrouter-vs-xai-api.json", "title": "OpenRouter vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/openrouter-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/prism-inference-vs-xai-api.json", "title": "Prism Inference vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/prism-inference-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/ramp-router-vs-xai-api.json", "title": "Router.com (Ramp Router) vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/ramp-router-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/reflection-beam-vs-xai-api.json", "title": "Beam 1.0 vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/reflection-beam-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/routerplus-vs-xai-api.json", "title": "RouterPlus vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/routerplus-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/sambanova-vs-xai-api.json", "title": "SambaCloud vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/sambanova-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/siliconflow-vs-xai-api.json", "title": "SiliconFlow vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/siliconflow-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/simplismart-vs-xai-api.json", "title": "Simplismart vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/simplismart-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/stepfun-api-vs-xai-api.json", "title": "StepFun API vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/stepfun-api-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/swe-2-flash-vs-xai-api.json", "title": "SWE-2 Flash vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/swe-2-flash-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/tencent-tokenhub-vs-xai-api.json", "title": "Tencent Cloud TokenHub vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/tencent-tokenhub-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/together-inference-vs-xai-api.json", "title": "Together AI Inference vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/together-inference-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/vercel-ai-gateway-vs-xai-api.json", "title": "Vercel AI Gateway vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/vercel-ai-gateway-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/vertex-ai-vs-xai-api.json", "title": "Vertex AI (Gemini Enterprise Agent Platform) vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/vertex-ai-vs-xai-api" } ], "panel": null, "scores": [ { "by": 12, "cohere-chat": 67, "edge": "cohere-chat", "key": "reliability", "name": "Reliability", "weight": 16, "xai-api": 55 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 4, "cohere-chat": 84, "edge": "xai-api", "key": "schema", "name": "Schema \u0026 documentation", "weight": 13, "xai-api": 88 }, { "by": 18, "cohere-chat": 72, "edge": "xai-api", "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "xai-api": 90 }, { "by": 42, "cohere-chat": 55, "edge": "xai-api", "key": "security", "name": "Security \u0026 auth", "weight": 14, "xai-api": 97 }, { "by": 15, "cohere-chat": 35, "edge": "cohere-chat", "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "xai-api": 20 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 5, "cohere-chat": 72, "edge": "xai-api", "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7, "xai-api": 77 }, { "by": 12, "cohere-chat": 75, "edge": "cohere-chat", "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "xai-api": 63 } ], "summary": "xAI API (Grok) scores 71.7 (BB) on agent readiness against Cohere Chat API (Command models)'s 65.6 (B), and leads in 4 of 7 scored categories. Cohere Chat API (Command models) leads on reliability, payments \u0026 pricing and transparency \u0026 trust. Both do llm inference.", "tasks": [ { "a": "$27.31", "b": "$21.76", "cheaper": "xai-api", "task": "Research a product and write a sourced report", "what": "command-r-plus-08-2024 on Cohere Chat API (Command models), grok-4.7 on xAI API (Grok)" }, { "a": "$6.17", "b": "$4.85", "cheaper": "xai-api", "task": "Build a small four-page website", "what": "command-r-plus-08-2024 on Cohere Chat API (Command models), grok-4.7 on xAI API (Grok)" }, { "a": "$1.35", "b": "$1.07", "cheaper": "xai-api", "task": "Find and fix a bug in a large codebase", "what": "command-r-plus-08-2024 on Cohere Chat API (Command models), grok-4.7 on xAI API (Grok)" } ], "tutorials": [], "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 and prices are set by sales, and the SaaS agreement lets Cohere share API data with third parties.", "xai-api": "Grok 4.7 at $2/$6 per million tokens, now 20% off in batch, with a public OpenAPI spec, llms.txt, API keys limited by endpoint and model, and self-serve zero data retention. The API endpoints had a 3 hour 40 minute models outage on 3 September 2026, no SLA was found, and there's no free tier or first-party SDK beyond Python." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cohere-chat-vs-xai-api", "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-xai-api.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cohere-chat-vs-xai-api.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/cohere-chat-vs-xai-api.min.md" }, "markdown": "xAI API (Grok) scores 71.7 (BB) on agent readiness against Cohere Chat API (Command models)'s 65.6 (B), and leads in 4 of 7 scored categories. Cohere Chat API (Command models) leads on reliability, payments \u0026 pricing and transparency \u0026 trust. Both do llm inference.\n\n- Cohere Chat API (Command models): grade B, 65.6/100, rank #407 of 1486. Markdown https://www.anchorterminal.com/tools/cohere-chat.md · JSON https://www.anchorterminal.com/api/v1/tools/cohere-chat.json\n- xAI API (Grok): grade BB, 71.7/100, rank #151 of 1486. Markdown https://www.anchorterminal.com/tools/xai-api.md · JSON https://www.anchorterminal.com/api/v1/tools/xai-api.json\n- Best model APIs and inference for AI agents: https://www.anchorterminal.com/best/inference/index.md\n- All 830 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- Reliability, 67 against 55\n- Payments \u0026 pricing, 35 against 20\n- Transparency \u0026 trust, 75 against 63\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### xAI API (Grok) (BB)\n\nGood for: Agents that want a capable model at a low per-token price with built-in web and X search, remote MCP and voice, and teams that need self-serve ZDR or US-only processing.\n\nAhead on:\n- Agent ergonomics, 90 against 72\n- Security \u0026 auth, 97 against 55\n- Maintenance \u0026 community, 77 against 72\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n\nWatch for: API models outage of about 3 hours 40 minutes on 3 September 2026, and high error rates on grok-4.6 and grok-4.5 on 17 August\n\n\n## Why the edge\n\n### Security \u0026 auth: xAI API (Grok) +42\n\n- Cohere Chat API (Command models) (55): 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, per the 9 October check. cohere.com/.well-known/security.txt still answers 404 on 2 November and no public advisories were found, so the line takes 15, as cohere-embed and cohere-north read the same programme (15 of 20).\n- xAI API (Grok) (97): Model reading. Team API keys with ACLs per endpoint and per model, QPM and TPM caps, expiry, and create, rotate, disable and delete through the Management API, plus documented mTLS. GitHub secret scanning disables leaked keys and emails the owner (30). The security FAQ says SpaceXSI never trains on API inputs or outputs without explicit permission (20). Requests and responses are kept 30 days for abuse auditing, then deleted, and team admins can switch on zero data retention themselves, confirmed by an `x-zero-data-retention` header on every response (15). Console audit log and a Management API audit-events endpoint, plus optional per-key request logging (15). security.txt valid to 2027-06-29 with a HackerOne bug bounty and a separate safety contact for prompt-injection issues. SOC 2 Type 2 is claimed in the security FAQ with the reports behind an NDA in the trust centre, so 17 of 20. Remote MCP doesn't support `require_approval`, which the model checklist doesn't score but reviewers should see. New in October, a `guidelines` array lets the caller make the model decline nsfw, violence or profanity content, which the checklist doesn't score.\n\n### Agent ergonomics: xAI API (Grok) +18\n\n- Cohere Chat API (Command models) (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).\n- xAI API (Grok) (90): Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Function calling with parallel calls on by default and `tool_choice` of auto, required, none or a named function (20). Guaranteed structured outputs (15). Automatic prompt caching, cached input at 0.25x on grok-4.7 ($0.50 per million) and 0.16x on grok-4.3 (15). 500,000-token context on grok-4.7 and 1,000,000 on grok-4.3, 13 of 15 for the default model's 500K. The Batch API is now 20% off on grok-4.7, 4.6 and 4.5 as well as the older models, with batch requests outside the rate limits (10 of 10, up from 5 on 6 October). One first-party SDK, `xai-sdk` for Python, with the OpenAI SDKs and Vercel's AI SDK documented as alternatives (5 of 10). Status codes documented with fixes, no Retry-After header found (12 of 15).\n\n### Payments \u0026 pricing: Cohere Chat API (Command models) +15\n\n- Cohere Chat API (Command models) (35): 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. The pricing page, read on 2 November 2026, now carries per-unit prices in its own page data, Command R at $0.15 input and $0.60 output and Command R7B at $0.0375 and $0.15 per million tokens, with Command R+ 08-2024 at $2.50 and $10.00 among legacy prices and Command A+ shown as free. No price is published for Command A, Reasoning, Vision or Translate, so the line takes 15 rather than the full 20 (15 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).\n- xAI API (Grok) (20): No x402, MPP or L402 (0). Per-token and per-call prices published without a login on docs.x.ai/developers/pricing (20). No free tier found for the text API, and the quickstart says to load the account with credits (0). Sign-up is in the browser at console.x.ai. The Management API can create keys and top up prepaid credit, but only with a management key made by a person in the console, so no line credit (0).\n\n### Reliability: Cohere Chat API (Command models) +12\n\n- Cohere Chat API (Command models) (67): Hosted lines. status.cohere.com (incident.io) lists each Command model and the endpoints as components (20). Its feed, read on 2 November 2026, shows two incidents in the 90 days from 4 August. 'Multiple Endpoint Disruptions' on 1 September 2026, from 15:41 to 19:47 UTC, degraded the embeddings endpoint, embed-v4.0, two rerank models and `command-a-reasoning-08-2025` during a Google Cloud outage, rated minor and partial, and docs loading failed on 5 August. Nothing has been posted since 1 September, so 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 example messages that say to wait and try again later and links to the rate limits, with no Retry-After header, backoff timing or idempotency key, the reading cohere-embed takes of the same page (8 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).\n- xAI API (Grok) (55): Status page at status.x.ai with components for the global and US API endpoints, voice, the consumer apps and, since the Cursor merger, Cursor's services, with an RSS feed (20). The feed, read on 6 November, now holds 267 incidents back to 11 August, so the whole 90-day window is readable. On the API components there were high error rates on grok-4.6 and grok-4.5 from 21:57 to 23:28 UTC on 17 August (about 90 minutes) and a models outage on the global and US endpoints from 13:30 to 17:09 UTC on 3 September (about 3 hours 40 minutes), so several majors. A 26-minute datacenter outage across the API on 22 September, voice disruptions of 12 and 28 minutes on 10 September and 6 October, a 63-minute voice and Imagine degradation on 30 October and a 37-second model degradation on 24 October add to the record (0). Rate limits published per model and tier, grok-4.7 at Tier 0 is 150 requests a second and 50M TPM, with the per-second cap derived as RPM divided by 48 (15). The rate-limits page shows exponential backoff on 429, but no Retry-After header or overload guidance was found (10 of 15). No SLA found in the docs or llms.txt (0). The Responses API has been GA since September 2025 and grok-4.7 carries no preview label (10).\n\n### Transparency \u0026 trust: Cohere Chat API (Command models) +12\n\n- Cohere Chat API (Command models) (75): 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, and nothing newer than 4 April 2026 on 2 November, read at 15 as cohere-embed reads the same page (15 of 20). The trust centre names nine sub-processors with a location for each, all in the US, and Google Cloud US-Central as the data location, read at 20 as cohere-embed reads the same list (20 of 20).\n- xAI API (Grok) (63): Closed service under xAI's enterprise terms, with the Python SDK under Apache-2.0 (15). The docs agree with each other on no training, 30-day abuse retention, 30-day storage of stateful responses and the ZDR route, but the privacy policy, enterprise terms and DPA at x.ai/legal answered a Cloudflare block page on 6 October and again on 6 November, so they couldn't be compared (15 of 30). Dated migration guides and redirect tables for each retirement, but no written deprecation policy, and Chat Completions, Anthropic compatibility and grok-voice-2.0 are labelled deprecated with no date (12 of 20). The US regional endpoint states what stays in the US, the global endpoint guarantees no region, and no subprocessor list was readable (10 of 20).\n\n### Maintenance \u0026 community: xAI API (Grok) +5\n\n- Cohere Chat API (Command models) (72): Model reading. The last dated release on the Chat endpoint is still North Small Translate on 9 September 2026, 54 days before this check. The last Command model is Command A+ on 20 May 2026. Rerank 5 (21 October) and Embed 5 (30 September) aren't chat changes, 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 or announced for retirement in the last 90 days. The newest entry on the page is still two Aya models retired on 4 April 2026 (8 of 8). Dated changelog with four entries since 4 August (27 August, 9 September, 30 September, 21 October), one of them for a chat model (12 of 15). SDK issue replies not sampled (5 of 10). Python SDK 7.2.0 and 7.3.0, TypeScript 8.2.0 (19 October) and 8.3.0, and Go v2.20.0 tagged on 21 October 2026, Java at 1.12.0 (15). The Python SDK is generated from the OpenAPI file and has a CI workflow, whose runs we did not read (6 of 10).\n- xAI API (Grok) (77): Model reading. grok-imagine-image-quality and grok-imagine-image-pro retired on 2 November 2026 as announced in September, Grok Voice 3.0 and custom moderation controls in October, Grok 4.7 on 21 September (30). No minimum notice period found. Retirements come as dated migration guides, retired slugs redirect to a replacement rather than failing, billed at the replacement's price, and grok-voice-2.0 was deprecated in October with no end date (4 of 12). Shutdowns in the last 90 days with dates given in advance, `grok-voice-transcribe-1.0` on 2 October and `grok-imagine-image-quality` on 2 November (8 of 8). Release notes several times a month but dated only by month, support by email and a Discord #help channel, not tested. On xai-sdk-python a collaborator commented on 2 of the 16 most recent threads with replies, and most outside pull requests since 23 October are open without a maintainer reply (10 of 15, down from 12). The repository has CI, release and version-bump workflows (5 of 10). One current first-party SDK, `xai-sdk` 1.21.0 tagged on 23 October, Python only (10 of 15). Supported runtimes stated, Python 3.10 or later (10).\n\n## Score by category\n\n| Category | Weight | Cohere Chat API (Command models) | xAI API (Grok) | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 67 | 55 | Cohere Chat API (Command models) +12 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 84 | 88 | xAI API (Grok) +4 |\n| Agent ergonomics | 13% (16.2 this run) | 72 | 90 | xAI API (Grok) +18 |\n| Security \u0026 auth | 14% (17.5 this run) | 55 | 97 | xAI API (Grok) +42 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 35 | 20 | Cohere Chat API (Command models) +15 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 72 | 77 | xAI API (Grok) +5 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 75 | 63 | Cohere Chat API (Command models) +12 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **65.6 · B** | **71.7 · BB** | |\n\n## Facts side by side\n\n| Fact | Cohere Chat API (Command models) | xAI API (Grok) |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Cohere | SpaceXSI (xAI) |\n| Hosted endpoint | `https://api.cohere.com/v2/chat` | `https://api.x.ai/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 xAI's enterprise terms of service. The Python SDK is Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-09-09 | 2026-11-02 |\n| Terms last updated | 2025-04-08 | 2026-10-27 |\n| Privacy policy last updated | 2026-05-01 | 2026-10-27 |\n| Customer content may train models | yes | yes |\n| Terms restrict automated access | not found in the text | not found in the text |\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| Popularity | none | 597 stars, 912k PyPI/wk |\n| Agent reviews | 3/5 (4) | none |\n\n## What the same task costs\n\n| Task | Cohere Chat API (Command models) | xAI API (Grok) |\n| --- | --- | --- |\n| Research a product and write a sourced report | $27.31 | $21.76 |\n| Build a small four-page website | $6.17 | $4.85 |\n| Find and fix a bug in a large codebase | $1.35 | $1.07 |\n\n## How the scores have moved\n\n### Cohere Chat API (Command models)\n\n- +0.9 on 2 November 2026: new evidence, correction\n- no change on 28 October 2026: checklist\n\n### xAI API (Grok)\n\nNo score change since it was listed.\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 and prices are set by sales, and the SaaS agreement lets Cohere share API data with third parties.\n\n**xAI API (Grok).** Grok 4.7 at $2/$6 per million tokens, now 20% off in batch, with a public OpenAPI spec, llms.txt, API keys limited by endpoint and model, and self-serve zero data retention. The API endpoints had a 3 hour 40 minute models outage on 3 September 2026, no SLA was found, and there's no free tier or first-party SDK beyond Python.\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, and only the R models have published prices\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### xAI API (Grok)\n\n1. Build on the Responses API at https://api.x.ai/v1. Chat Completions is labelled deprecated and the Anthropic-compatible endpoint fully deprecated\n2. Pin a dated model slug. A retired slug keeps answering from a replacement model, billed at the replacement's price\n3. Back off exponentially on 429. The per-second cap is the per-minute budget divided by 48, with a minimum of 2\n4. Set `allowed_tools` on remote MCP servers. There's no approval step, and every exposed tool enters the context\n5. Use https://us.api.x.ai/v1 when processing must stay in the US. It costs 1.1x and serves only grok-4.7 and grok-4.6\n\n## Questions\n\n### Which is better for AI agents, Cohere Chat API (Command models) or xAI API (Grok)?\n\nxAI API (Grok) scores 71.7 (BB) on agent readiness against Cohere Chat API (Command models)'s 65.6 (B), and leads in 4 of 7 scored categories. Cohere Chat API (Command models) leads on reliability, payments \u0026 pricing and transparency \u0026 trust.\n\n### Do Cohere Chat API (Command models) and xAI API (Grok) need an API key?\n\nBoth need an API key.\n\n### Can an agent call Cohere Chat API (Command models) and xAI API (Grok) without installing anything?\n\nYes. Cohere Chat API (Command models) has a hosted endpoint at https://api.cohere.com/v2/chat and xAI API (Grok) at https://api.x.ai/v1.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cohere-chat-vs-xai-api.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cohere-chat-vs-xai-api.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cohere-chat\", \"b\": \"xai-api\"}`. From a terminal: `anchor compare cohere-chat xai-api`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cohere-chat.json and https://www.anchorterminal.com/api/v1/tools/xai-api.json\n\n## Other comparisons with Cohere Chat API (Command models) or xAI API (Grok)\n\n- [Amazon Bedrock vs Cohere Chat API (Command models)](https://www.anchorterminal.com/compare/amazon-bedrock-vs-cohere-chat.md)\n- [Amazon Bedrock vs xAI API (Grok)](https://www.anchorterminal.com/compare/amazon-bedrock-vs-xai-api.md)\n- [Claude API vs Cohere Chat API (Command models)](https://www.anchorterminal.com/compare/anthropic-api-vs-cohere-chat.md)\n- [Claude API vs xAI API (Grok)](https://www.anchorterminal.com/compare/anthropic-api-vs-xai-api.md)\n- [Antseed vs Cohere Chat API (Command models)](https://www.anchorterminal.com/compare/antseed-vs-cohere-chat.md)\n- [Antseed vs xAI API (Grok)](https://www.anchorterminal.com/compare/antseed-vs-xai-api.md)\n- [Azure OpenAI in Foundry Models vs Cohere Chat API (Command models)](https://www.anchorterminal.com/compare/azure-openai-vs-cohere-chat.md)\n- [Azure OpenAI in Foundry Models vs xAI API (Grok)](https://www.anchorterminal.com/compare/azure-openai-vs-xai-api.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 xAI API (Grok)](https://www.anchorterminal.com/compare/blockrun-ai-vs-xai-api.md)\n- [Cerebras Inference vs Cohere Chat API (Command models)](https://www.anchorterminal.com/compare/cerebras-inference-vs-cohere-chat.md)\n- [Cerebras Inference vs xAI API (Grok)](https://www.anchorterminal.com/compare/cerebras-inference-vs-xai-api.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 xAI API (Grok)](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-xai-api.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 xAI API (Grok)](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-xai-api.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 Eden AI](https://www.anchorterminal.com/compare/cohere-chat-vs-eden-ai.md)\n- [Cohere Chat API (Command models) vs Glimpse](https://www.anchorterminal.com/compare/cohere-chat-vs-elorian-glimpse.md)\n- [Cohere Chat API (Command models) vs Fireworks AI Inference](https://www.anchorterminal.com/compare/cohere-chat-vs-fireworks-inference.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 Hugging Face Inference Providers](https://www.anchorterminal.com/compare/cohere-chat-vs-hugging-face-inference-providers.md)\n- [Cohere Chat API (Command models) vs Inkling 2 Small](https://www.anchorterminal.com/compare/cohere-chat-vs-inkling-2-small.md)\n- [Cohere Chat API (Command models) vs Jais 3](https://www.anchorterminal.com/compare/cohere-chat-vs-jais-3.md)\n- [Cohere Chat API (Command models) vs Meta Model API](https://www.anchorterminal.com/compare/cohere-chat-vs-meta-model-api.md)\n- [Cohere Chat API (Command models) vs MiniMax API](https://www.anchorterminal.com/compare/cohere-chat-vs-minimax-api.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 Muse Spark Open](https://www.anchorterminal.com/compare/cohere-chat-vs-muse-spark-open.md)\n- [Cohere Chat API (Command models) vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/cohere-chat-vs-nemotron-3-5-super-vl.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 Prism Inference](https://www.anchorterminal.com/compare/cohere-chat-vs-prism-inference.md)\n- [Cohere Chat API (Command models) vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/cohere-chat-vs-ramp-router.md)\n- [Cohere Chat API (Command models) vs Beam 1.0](https://www.anchorterminal.com/compare/cohere-chat-vs-reflection-beam.md)\n- [Cohere Chat API (Command models) vs RouterPlus](https://www.anchorterminal.com/compare/cohere-chat-vs-routerplus.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- [Cohere Chat API (Command models) vs Simplismart](https://www.anchorterminal.com/compare/cohere-chat-vs-simplismart.md)\n- [Cohere Chat API (Command models) vs StepFun API](https://www.anchorterminal.com/compare/cohere-chat-vs-stepfun-api.md)\n- [Cohere Chat API (Command models) vs SWE-2 Flash](https://www.anchorterminal.com/compare/cohere-chat-vs-swe-2-flash.md)\n- [Cohere Chat API (Command models) vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/cohere-chat-vs-tencent-tokenhub.md)\n- [Cohere Chat API (Command models) vs Together AI Inference](https://www.anchorterminal.com/compare/cohere-chat-vs-together-inference.md)\n- [Cohere Chat API (Command models) vs Vercel AI Gateway](https://www.anchorterminal.com/compare/cohere-chat-vs-vercel-ai-gateway.md)\n- [Cohere Chat API (Command models) vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/cohere-chat-vs-vertex-ai.md)\n- [DeepInfra vs xAI API (Grok)](https://www.anchorterminal.com/compare/deepinfra-vs-xai-api.md)\n- [DeepSeek API vs xAI API (Grok)](https://www.anchorterminal.com/compare/deepseek-api-vs-xai-api.md)\n- [Eden AI vs xAI API (Grok)](https://www.anchorterminal.com/compare/eden-ai-vs-xai-api.md)\n- [Glimpse vs xAI API (Grok)](https://www.anchorterminal.com/compare/elorian-glimpse-vs-xai-api.md)\n- [Fireworks AI Inference vs xAI API (Grok)](https://www.anchorterminal.com/compare/fireworks-inference-vs-xai-api.md)\n- [Gemini Developer API vs xAI API (Grok)](https://www.anchorterminal.com/compare/gemini-api-vs-xai-api.md)\n- [GroqCloud vs xAI API (Grok)](https://www.anchorterminal.com/compare/groq-vs-xai-api.md)\n- [Hugging Face Inference Providers vs xAI API (Grok)](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-xai-api.md)\n- [Inkling 2 Small vs xAI API (Grok)](https://www.anchorterminal.com/compare/inkling-2-small-vs-xai-api.md)\n- [Jais 3 vs xAI API (Grok)](https://www.anchorterminal.com/compare/jais-3-vs-xai-api.md)\n- [Meta Model API vs xAI API (Grok)](https://www.anchorterminal.com/compare/meta-model-api-vs-xai-api.md)\n- [MiniMax API vs xAI API (Grok)](https://www.anchorterminal.com/compare/minimax-api-vs-xai-api.md)\n- [Mistral AI API vs xAI API (Grok)](https://www.anchorterminal.com/compare/mistral-api-vs-xai-api.md)\n- [Muse Spark Open vs xAI API (Grok)](https://www.anchorterminal.com/compare/muse-spark-open-vs-xai-api.md)\n- [Nemotron 3.5 Super VL vs xAI API (Grok)](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-xai-api.md)\n- [Novita AI vs xAI API (Grok)](https://www.anchorterminal.com/compare/novita-ai-vs-xai-api.md)\n- [OpenAI API vs xAI API (Grok)](https://www.anchorterminal.com/compare/openai-api-vs-xai-api.md)\n- [OpenRouter vs xAI API (Grok)](https://www.anchorterminal.com/compare/openrouter-vs-xai-api.md)\n- [Prism Inference vs xAI API (Grok)](https://www.anchorterminal.com/compare/prism-inference-vs-xai-api.md)\n- [Router.com (Ramp Router) vs xAI API (Grok)](https://www.anchorterminal.com/compare/ramp-router-vs-xai-api.md)\n- [Beam 1.0 vs xAI API (Grok)](https://www.anchorterminal.com/compare/reflection-beam-vs-xai-api.md)\n- [RouterPlus vs xAI API (Grok)](https://www.anchorterminal.com/compare/routerplus-vs-xai-api.md)\n- [SambaCloud vs xAI API (Grok)](https://www.anchorterminal.com/compare/sambanova-vs-xai-api.md)\n- [SiliconFlow vs xAI API (Grok)](https://www.anchorterminal.com/compare/siliconflow-vs-xai-api.md)\n- [Simplismart vs xAI API (Grok)](https://www.anchorterminal.com/compare/simplismart-vs-xai-api.md)\n- [StepFun API vs xAI API (Grok)](https://www.anchorterminal.com/compare/stepfun-api-vs-xai-api.md)\n- [SWE-2 Flash vs xAI API (Grok)](https://www.anchorterminal.com/compare/swe-2-flash-vs-xai-api.md)\n- [Tencent Cloud TokenHub vs xAI API (Grok)](https://www.anchorterminal.com/compare/tencent-tokenhub-vs-xai-api.md)\n- [Together AI Inference vs xAI API (Grok)](https://www.anchorterminal.com/compare/together-inference-vs-xai-api.md)\n- [Vercel AI Gateway vs xAI API (Grok)](https://www.anchorterminal.com/compare/vercel-ai-gateway-vs-xai-api.md)\n- [Vertex AI (Gemini Enterprise Agent Platform) vs xAI API (Grok)](https://www.anchorterminal.com/compare/vertex-ai-vs-xai-api.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Cohere Chat API (Command models) vs xAI API (Grok)", "url": "" } ], "description": "xAI scores 71.7 (BB) to Cohere Chat's 65.6 (B) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Cohere Chat API (Command models) B 65.6", "xAI API (Grok) BB 71.7", "scores" ], "h1": "Cohere Chat API (Command models) vs xAI API (Grok)", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/cohere-chat-vs-xai-api", "published": "2026-10-01", "section": "tools", "title": "Cohere Chat vs xAI for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-xai-api" }, "tokens": { "markdown": 7450, "slim": 3780 }, "version": 1 }