{ "data": { "a": { "slug": "hugging-face-inference-providers", "name": "Hugging Face Inference Providers", "vendor": "Hugging Face, Inc.", "vendorUrl": "https://huggingface.co", "kind": "router", "category": "inference", "summary": "Hugging Face's serverless router that sends model calls to partner inference providers such as Groq, Cerebras, Together and Fireworks through one Hugging Face token, with an OpenAI-compatible API at router.huggingface.co/v1 and Python and JavaScript clients.", "url": "https://www.anchorterminal.com/tools/hugging-face-inference-providers", "markdownUrl": "https://www.anchorterminal.com/tools/hugging-face-inference-providers.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/hugging-face-inference-providers.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/hugging-face-inference-providers.json", "dns": "hugging-face-inference-providers.grade.anchorterminal.com", "repo": "https://github.com/huggingface/huggingface_hub", "license": "Proprietary service under the Hugging Face Terms of Service, which name Inference Providers. The `huggingface_hub` Python client is Apache-2.0 and `@huggingface/inference` is MIT", "transports": [ "http" ], "remoteUrl": "https://router.huggingface.co/v1", "packages": [ { "registry": "pypi", "name": "huggingface_hub" }, { "registry": "npm", "name": "@huggingface/inference" } ], "auth": "api-key", "authNotes": "Hugging Face user access token sent as `Authorization: Bearer $HF_TOKEN`. The docs recommend a fine-grained token with only the `Make calls to Inference Providers` permission. Tokens are made in account settings in a browser, can be rotated and revoked, and a leaked token can be revoked by anyone through `POST /api/credentials/revoke`. A provider's own key can be stored in settings instead, and Hugging Face swaps it in when routing.", "pricing": "usage", "pricingNotes": "Pay as you go at each provider's own per-token rates with no Hugging Face markup, drawn from prepaid credits on the Hugging Face account. Free users get no included credits since 7 October 2026 and must buy credits. PRO users and Team or Enterprise seats get $2.00 a month of compute credits. Requests with a custom provider key are billed by the provider (https://huggingface.co/docs/inference-providers/pricing, checked 2026-11-06).", "priceSummary": "$2 / mo", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the Inference Providers docs, llms.txt or the router's model list. Calls draw on prepaid Hugging Face credits bought in the account's billing settings (checked 2026-11-06).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 483470, "pypiWeekly": 71518708, "asOf": "2026-11-06" }, "docsUrl": "https://huggingface.co/docs/inference-providers/index", "llmsTxt": "https://huggingface.co/docs/inference-providers/llms.txt", "capabilities": [ "inference.router", "inference.open-weights", "inference.llm" ], "tags": [ "hosted", "router", "usage", "prepaid", "openai-compatible", "llms-txt", "python", "javascript", "status-page", "soc2" ], "lastRelease": "2026-10-29", "graded": true, "anchor": { "graded": true, "score": 54, "grade": "C", "agentReady": false, "rank": 926, "ranked": true, "rankOf": 1510, "categoryRank": 28, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 58, "maintenance": 80, "payments": 20, "reliability": 25, "schema": 62, "security": 79, "transparency": 71 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "One Hugging Face token reaches open models on 18 partner providers at the providers' own prices, with a public model list that shows each provider's price, context and tool support. Router rate limits, error responses and its own status component were not found in the reviewed documentation, and free accounts have had no included credits since 7 October 2026.", "bestFor": "Agents and developers who want open-weight models from several hosts on one token and one bill, with a public price and capability list per provider.", "strengths": [ "router.huggingface.co/v1/models lists every routed model with each provider's price, context, tool support, latency and throughput, without a token", "Provider choice by suffix (`:fastest`, `:cheapest`, `:preferred` or a provider name) on an OpenAI-compatible endpoint", "Fine-grained tokens can be limited to the `Make calls to Inference Providers` permission and revoked at once", "No markup on provider rates, and request bodies and responses are not stored when routed", "Official clients in Python (`huggingface_hub` 2.4.0, 29 October 2026) and JavaScript (`@huggingface/inference` 4.13.32)" ], "weaknesses": [ "No rate limits, 429 behaviour or error responses documented for the router", "status.huggingface.co has no component for Inference Providers or the router", "Free users have had no included credits since 7 October 2026, and buying credits needs a person in the account settings", "No OpenAPI document for the router, no batch API, and the Responses API is beta", "Data handling past the router depends on each provider's own policy" ], "agentNotes": [ "Read https://router.huggingface.co/v1/models before choosing a provider; it shows price, context and `supports_tools` per provider", "Pin a provider with `model:\u003cprovider\u003e` when tool calling or structured output matters, since support varies by provider", "Use a fine-grained token with only the Inference Providers permission, and send `X-HF-Bill-To` to bill an organisation", "Back off on 429 without assuming a Retry-After header, since none is documented for the router" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 54 } ], "editorialScores": { "ergonomics": 58, "maintenance": 80, "payments": 20, "reliability": 25, "schema": 62, "security": 79, "transparency": 58 }, "provenanceScore": 84, "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 huggingface_hub # or: pip install openai, with base_url https://router.huggingface.co/v1", "http": "curl https://router.huggingface.co/v1/chat/completions \\\n -H \"Authorization: Bearer $HF_TOKEN\" -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"openai/gpt-oss-120b:fastest\",\"messages\":[{\"role\":\"user\",\"content\":\"How many Gs in huggingface?\"}]}'" }, "letme": { "capability": "https://letme.dev/inference.router", "tool": "https://letme.dev/hugging-face-inference-providers" }, "sameCompany": [ "hugging-face-inference-endpoints", "smolagents", "carbon-x", "smollm3-3b" ], "area": "models", "unitPrices": [ { "item": "openai/gpt-oss-120b input, cheapest provider listed (DeepInfra)", "unit": "1m-tokens", "usd": 0.037, "note": "Output $0.17. Groq lists $0.15/$0.75 and Cerebras $0.35/$0.75, per the router's model list of 6 November 2026" }, { "item": "PRO monthly compute credits", "unit": "month", "usd": 2, "note": "Also $2.00 per seat for Team and Enterprise organisations" } ], "provenance": { "legalEntity": "Hugging Face, Inc.", "domain": "huggingface.co", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://huggingface.co/terms-of-service", "privacy": "https://huggingface.co/privacy", "statusPage": "https://status.huggingface.co", "changelog": "https://huggingface.co/changelog", "securityTxt": "valid", "checked": "2026-11-06", "notes": [ "The Terms of Service (effective 15 September 2022) name Hugging Face, Inc. and define Inference Providers as a hosted service for running inference through an API on Hub models.", "huggingface.co/robots.txt and router.huggingface.co/robots.txt allow all. status.huggingface.co serves an empty robots.txt.", "status.huggingface.co is a Better Stack page with components for the Hub, git hosting, Inference Endpoints, Spaces, the CDNs and Jobs, and none for Inference Providers or the router.", "huggingface.co/changelog covers the whole Hub and had no Inference Providers entry on its first page on 6 November 2026. Dated changes to the docs are in the hub-docs repository's history.", "security.txt, privacy policy and subprocessor list as recorded on the Inference Endpoints listing (checked 8 October and 2 November 2026); not re-read for this listing." ], "score": 84 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/hugging-face-inference-providers.json", "live": { "slug": "hugging-face-inference-providers", "probe": { "target": "https://router.huggingface.co/v1", "method": "get", "lastAt": "2026-11-07T19:22:12.474650545Z", "lastOk": true, "lastStatus": 404, "lastMs": 145, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 109, "p95ms24h": 196, "samples24h": 210, "samples30d": 210, "days": [ { "date": "2026-11-06", "probes": 13, "ok": 13 }, { "date": "2026-11-07", "probes": 197, "ok": 197 } ] }, "vendorStatus": { "page": "https://status.huggingface.co", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-07T04:47:55.542550557Z" }, "versions": [ { "registry": "github", "name": "huggingface/huggingface_hub", "version": "v2.4.0", "released": "2026-10-29", "seenAt": "2026-11-06T23:33:27.894225298Z" }, { "registry": "npm", "name": "@huggingface/inference", "version": "4.13.32", "seenAt": "2026-11-06T23:33:27.102558197Z" }, { "registry": "pypi", "name": "huggingface_hub", "version": "2.4.0", "released": "2026-10-29", "seenAt": "2026-11-06T23:33:26.910773744Z" } ], "githubStars": 4034, "npmWeekly": 483470, "pypiWeekly": 71518708, "securityTxt": { "url": "https://huggingface.co/.well-known/security.txt", "state": "valid", "expires": "2030-07-01T08:42:00.000Z", "checkedAt": "2026-11-07T16:00:00.493446773Z" }, "llmsTxt": { "url": "https://huggingface.co/docs/inference-providers/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:44.910268229Z" }, "pages": [ { "url": "https://huggingface.co/docs/inference-providers/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:11:37.221950067Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "2cbe821ca9d2" } ], "updatedAt": "2026-11-07T19:22:12.474650545Z" } }, "answer": "Mistral AI API scores 65.7 (B) on agent readiness against Hugging Face Inference Providers's 54 (C), and leads in 5 of 7 scored categories. Hugging Face Inference Providers leads on security \u0026 auth.", "b": { "slug": "mistral-api", "name": "Mistral AI API", "vendor": "Mistral AI", "vendorUrl": "https://mistral.ai", "kind": "model", "category": "inference", "summary": "Mistral's API for its open-weight and proprietary models, with EU and US regional endpoints.", "url": "https://www.anchorterminal.com/tools/mistral-api", "markdownUrl": "https://www.anchorterminal.com/tools/mistral-api.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/mistral-api.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/mistral-api.json", "dns": "mistral-api.grade.anchorterminal.com", "repo": "https://github.com/mistralai/client-python", "license": "Apache-2.0 (SDKs)", "transports": [ "http" ], "remoteUrl": "https://api.mistral.ai/v1", "packages": [ { "registry": "pypi", "name": "mistralai", "main": true }, { "registry": "npm", "name": "@mistralai/mistralai", "main": true } ], "auth": "api-key", "authNotes": "Bearer key. Regional EU and US endpoints are opt-in.", "pricing": "freemium", "pricingNotes": "Free Experiment tier with no card, but a phone number, and its data may be used for training. Cached input 10% of the input price, batch half price, regional endpoints 1.1x. Mistral Large 4 (preview) is $0.70/$2.10 per million tokens, cached input $0.07, on 1 November. Also resells Z.ai GLM 5.3 at $1.40/$4.40, GLM 5.3 Flash at $0.15/$0.50 and DeepSeek V4.1 Flash 1017 (preview) at $0.30/$1.20 (https://mistral.ai/pricing/api/).", "priceSummary": "from $0.10 / 1M in", "where": "hosted", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 769, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-09-26" }, "docsUrl": "https://docs.mistral.ai", "rateLimitsUrl": "https://docs.mistral.ai/admin/user-management-finops/tier", "llmsTxt": "https://docs.mistral.ai/llms.txt", "openapi": "https://docs.mistral.ai/openapi.yaml", "capabilities": [ "inference.llm", "inference.open-weights" ], "tags": [ "official", "hosted", "model", "eu", "open-weights", "free-tier", "openapi", "llms-txt" ], "lastRelease": "2026-10-28", "graded": true, "anchor": { "graded": true, "score": 65.7, "grade": "B", "agentReady": false, "rank": 407, "ranked": true, "rankOf": 1510, "categoryRank": 16, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 91, "maintenance": 80, "payments": 40, "reliability": 50, "schema": 93, "security": 73, "transparency": 80 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": -6, "negativeNotes": [ "2026-05-12. The `mistralai` 2.4.6 package on PyPI, one of this listing's two official SDKs, ran a credential-harvesting script on import for about three hours, and `@mistralai/mistralai` 2.2.2 to 2.2.4 on npm were replaced too. Mistral published advisory MAI-2026-002, removed the packages and closed its investigation on 14 May. Fixed and documented, so 3 points, as mistral-voxtral-transcribe carries for the same advisory (https://docs.mistral.ai/resources/security-advisories/MAI-2026-002). -3", "2026-10-20 to 2026-10-27. Minor releases of both official SDKs list \"Breaking changes\" with no advance notice found. Python 3.3.0 (20 October) and TypeScript 3.1.0 change the `type` field in `chat.complete()` and `agents.complete()` and remove `expressiveness` and `phoneme_hints` from audio agent configuration. Python 3.4.0 (23 October) makes `configuration` required on `audio.agents.create()` and renames `models.Format` to `FormatEnum`. Python 3.6.0 and TypeScript 3.4.0 (27 October) remove usage fields from speech responses. One term at the floor, as svix's several breaking minors were read (https://github.com/mistralai/client-python/blob/main/RELEASES.md). -3" ], "verdict": "Public OpenAPI document and an llms.txt with Markdown twins. Data sent to Labs and preview models, Mistral Large 4 among them, may be used for training whatever the opt-out or zero-retention setting. The default model, Medium 3.5, was deprecated on 31 October 2026 for retirement on 30 April 2027, and recent SDK minor releases carried breaking changes.", "bestFor": "Teams that need EU processing, open-weight models they can later run themselves, or an API an agent can read from an OpenAPI file.", "strengths": [ "Public OpenAPI 3.1.0 document at docs.mistral.ai/openapi.yaml and an llms.txt with Markdown twins", "Minimum 6 months' notice before a GA model retires, kept for Medium 3.5 and Large 3, and retired ids return 404", "Workspace-scoped API keys with expiry dates, and service accounts bound to workspace roles", "Three dated security advisories published in the docs in 2026, with affected versions and remediation", "Free Experiment tier with no card, and Batch at half price" ], "weaknesses": [ "Labs and preview models, Large 4 among them, may train on data sent from 2026-09-25, whatever the opt-out or zero-retention setting", "Mistral Medium 3 and 3.1, both GA, retired on 31 August 2026 after 101 days' notice against a published 6-month minimum", "SDK minor releases from 20 to 27 October 2026 removed and changed fields, marked breaking on release day", "The `mistralai` 2.4.6 PyPI release of 12 May 2026 harvested credentials on import for about three hours", "Rate-limit numbers are only in the console, no SLA found, and the status page blocks automated readers" ], "agentNotes": [ "Stay off `labs-*` and preview models, `mistral-large-4` included while it is in preview, for anything confidential", "Plan a move off `mistral-medium-3-5` and `mistral-large-2512` before 30 April 2027. `mistral-medium-latest` still points to Medium 3.5", "Pin each SDK to one version. Minor releases of `mistralai` and `@mistralai/mistralai` have removed fields without notice", "Treat a 404 on a model id as retirement and read the models page for the replacement", "Set `tool_choice` to any to force a tool call, and `strict` on the JSON schema for structured output" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 4, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 65.7 } ], "editorialScores": { "ergonomics": 91, "maintenance": 80, "payments": 40, "reliability": 50, "schema": 93, "security": 73, "transparency": 68 }, "provenanceScore": 92, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "lastMoved": "2026-11-01", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install mistralai # or: npm i @mistralai/mistralai", "http": "curl https://api.mistral.ai/v1/chat/completions \\\n -H \"Authorization: Bearer $MISTRAL_API_KEY\" -H \"content-type: application/json\" \\\n -d '{\"model\":\"mistral-medium-3-5\",\"messages\":[{\"role\":\"user\",\"content\":\"bonjour\"}]}'" }, "letme": { "capability": "https://letme.dev/inference.llm", "tool": "https://letme.dev/mistral-api" }, "sameCompany": [ "mistral-embeddings", "mistral-moderation", "mistral-voxtral-transcribe", "voxtral-mini-4b-realtime-2602", "mistral-ocr", "mistral-vibe-cli" ], "sameModel": [ "mistral-large-4" ], "area": "models", "provenance": { "legalEntity": "Mistral AI (RCS Paris 952 418 325)", "domain": "mistral.ai", "domainRegistered": "2019-05-15", "endpointOnVendorDomain": true, "terms": "https://legal.mistral.ai/terms/commercial-terms-of-service", "privacy": "https://legal.mistral.ai/terms/privacy-policy", "statusPage": "https://status.mistral.ai", "changelog": "https://docs.mistral.ai/resources/changelogs", "securityTxt": "valid", "checked": "2026-11-01", "notes": [ "security.txt read on 2026-11-01, Contact security@mistral.ai, Expires 2027-05-05, Policy a HackerOne submission form", "Commercial terms effective 2026-09-25 and DPA effective 2026-07-27, both re-read on 2026-11-01", "status.mistral.ai answered robots.txt and its pages with a Cloudflare bot check on 2026-11-01" ], "score": 92 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/mistral-api.json", "live": { "slug": "mistral-api", "probe": { "target": "https://api.mistral.ai/v1", "method": "get", "lastAt": "2026-11-07T19:22:20.293432283Z", "lastOk": true, "lastStatus": 404, "lastMs": 145, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 73, "p95ms24h": 145, "samples24h": 238, "samples30d": 7920, "days": [ { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "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": 248, "ok": 248 }, { "date": "2026-10-30", "probes": 249, "ok": 249 }, { "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": 197, "ok": 197 } ] }, "vendorStatus": { "page": "https://status.mistral.ai", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-07T19:22:29.94992289Z" }, "versions": [ { "registry": "github", "name": "mistralai/client-python", "version": "v3.7.0", "released": "2026-11-01", "seenAt": "2026-11-06T23:46:16.644469996Z" }, { "registry": "npm", "name": "@mistralai/mistralai", "version": "3.5.0", "seenAt": "2026-11-06T23:46:15.214784483Z" }, { "registry": "pypi", "name": "mistralai", "version": "3.7.0", "released": "2026-11-01", "seenAt": "2026-11-06T23:46:15.034450618Z" } ], "githubStars": 773, "npmWeekly": 6411114, "pypiWeekly": 3498549, "securityTxt": { "url": "https://mistral.ai/.well-known/security.txt", "state": "valid", "expires": "2027-05-05T23:59:59.000Z", "checkedAt": "2026-11-07T16:00:05.953035328Z" }, "llmsTxt": { "url": "https://docs.mistral.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:33:07.713253236Z" }, "domain": { "domain": "mistral.ai", "registered": "2019-05-15", "source": "https://rdap.identitydigital.services/rdap/domain/mistral.ai", "checkedAt": "2026-11-01T14:21:43.304217994Z" }, "pages": [ { "url": "https://docs.mistral.ai/models.md", "kind": "deprecations", "status": 304, "checkedAt": "2026-11-07T14:07:06.93917887Z", "changedAt": "2026-11-06T13:29:25.955541081Z", "fingerprint": "47c11be3c457" }, { "url": "https://docs.mistral.ai/resources/changelogs", "kind": "deprecations", "status": 304, "checkedAt": "2026-11-07T14:07:14.906275127Z", "changedAt": "2026-10-23T01:45:57.577340637Z", "fingerprint": "a6e40e62ddee" }, { "url": "https://legal.mistral.ai/terms/commercial-terms-of-service", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-07T14:12:59.466425194Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "227daf1e9929" }, { "url": "https://raw.githubusercontent.com/mistralai/client-python/main/RELEASES.md", "kind": "deprecations", "status": 304, "checkedAt": "2026-11-07T14:21:47.957091397Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "5c6b09386d51" }, { "url": "https://mistral.ai/pricing/api/", "kind": "pricing", "status": 304, "checkedAt": "2026-11-07T14:14:23.157989409Z", "changedAt": "2026-11-05T12:37:30.141983295Z", "fingerprint": "ebe78a915333" }, { "url": "https://legal.mistral.ai/terms/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:13:01.891707132Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e74211012ef6" } ], "models": { "ministral-3b-2512": { "openrouterId": "mistralai/ministral-3b-2512", "tools": true, "structuredOutputs": true, "jsonMode": true, "reasoning": false, "input": [ "image", "text" ], "promptCaching": true, "contextTokens": 131072, "maxOutput": 104857, "checkedAt": "2026-11-06T23:49:25.225778715Z" }, "mistral-large-2512": { "openrouterId": "mistralai/mistral-large-2512", "tools": true, "structuredOutputs": true, "jsonMode": true, "reasoning": false, "input": [ "file", "image", "text" ], "promptCaching": true, "contextTokens": 262144, "maxOutput": 209715, "checkedAt": "2026-11-06T23:49:25.225778715Z" }, "mistral-large-4": { "openrouterId": "mistralai/mistral-large-4-0", "tools": true, "structuredOutputs": true, "jsonMode": true, "reasoning": true, "input": [ "image", "text" ], "promptCaching": true, "contextTokens": 1048576, "maxOutput": 262144, "checkedAt": "2026-11-06T23:49:25.225778715Z" }, "mistral-medium-3-5": { "openrouterId": "mistralai/mistral-medium-3-5", "tools": true, "structuredOutputs": true, "jsonMode": true, "reasoning": true, "input": [ "file", "image", "text" ], "promptCaching": false, "contextTokens": 262144, "maxOutput": 209715, "checkedAt": "2026-11-06T23:49:25.225778715Z" }, "mistral-small-2603": { "openrouterId": "mistralai/mistral-small-2603", "tools": true, "structuredOutputs": true, "jsonMode": true, "reasoning": true, "input": [ "image", "text" ], "promptCaching": true, "contextTokens": 262144, "maxOutput": 209715, "checkedAt": "2026-11-06T23:49:25.225778715Z" } }, "github": { "repo": "mistralai/client-python", "checkedAt": "2026-11-02T09:07:39.340819862Z", "stars": 774, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-01T20:09:32Z", "openIssues": 39, "openPRs": 3, "issuesOpened90d": 20, "issuesClosed90d": 2, "prsMerged90d": 23, "ci": { "branch": "main", "runs": 50, "success": 37, "failure": 13, "other": 0, "latest": "failure", "latestAt": "2026-11-01T20:33:28Z" }, "advisories": [ { "ghsa": "GHSA-wx9m-wx4f-4cmg", "severity": "critical", "published": "2026-05-12T12:57:44Z" } ], "replies": { "sampled": 25, "unanswered": 23, "medianDays": 21.9 } }, "updatedAt": "2026-11-07T19:22:20.293432283Z" } }, "edges": [ { "by": 33, "category": "ergonomics", "leads": "mistral-api", "name": "Agent ergonomics", "reasons": { "a": "Router reading of the model checklist (tool use, structured output, caching, context, batch, SDKs, errors), as for openrouter. Tool calling through the OpenAI-compatible API with `tool_choice`, support flagged per provider in /v1/models (15 of 20). Structured output documented, support flagged per provider and false on some (10 of 15). No prompt caching guidance found, though the Enterprise usage API counts cached input tokens (3 of 15). Routes to models with up to 1,048,576 tokens of context per the model list, a judgement call since a router has no default model (15). No batch API (0 of 10). Official clients in Python and JavaScript, plus any OpenAI SDK (10). Errors not documented (5 of 15).", "b": "Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors), per the 2 and 12 October checks. Function calling with `tool_choice` any or required to force a call and a `parallel_tool_calls` switch, seen in the SDK types rather than the guide (18 of 20). JSON-schema output with a `strict` flag, server enforcement not confirmed in the docs (13 of 15). Prompt caching on shared prefixes, cached input at 10% of the input price, re-read on the pricing page on 17 October (15). 256,000-token context on Medium 3.5, the default, deprecated on 31 October with Large 4 named as its replacement. Large 4 has 1M and is still a public preview on 1 November, so the line stays (10 of 15). A stateless Responses API (`/v1/responses`) arrived in the 23 October SDKs. Batch at half price (10). Official SDKs for Python and TypeScript (10). Error glossary (15). 18+13+15+10+10+10+15 = 91." }, "scores": { "a": 58, "b": 91 } }, { "by": 31, "category": "schema", "leads": "mistral-api", "name": "Schema \u0026 documentation", "reasons": { "a": "No OpenAPI document for the router (openapi.json paths answer 404). The task reference pages are generated from typed JSON Schema specs in huggingface.js, and the router's /v1/models gives a machine-readable catalogue, so 12 of 25. llms.txt for the Inference Providers docs and a Markdown twin of every page via `.md` (10). Guides say what each task and policy is for, with a quick setup page for coding agents (14 of 20). Parameter tables with types for chat completion, though `response_format` and `tool_choice` show as unknown types (9 of 15). Examples in Python, JavaScript and curl on every task page, but no documented error responses for the router (9 of 15). No changelog of its own; the Hub changelog doesn't cover it and dated changes are only in the hub-docs history (8 of 15).", "b": "Public OpenAPI 3.1.0 document at docs.mistral.ai/openapi.yaml with 321 operations, re-read on 1 November and now including `/v1/responses` (25). llms.txt with Markdown twins of every page, re-read on 1 November (10). Reference not read in full (15 of 20). Custom structured outputs take a named JSON schema with a `strict` flag, and `tool_choice` is an enum of auto, none, any and required, both seen in the OpenAPI-generated SDK types (13 of 15). Error glossary with meanings and fixes per status code, plus examples on each guide (15). Release notes and dated model versions (15). 25+10+15+13+15+15 = 93." }, "scores": { "a": 62, "b": 93 } }, { "by": 25, "category": "reliability", "leads": "mistral-api", "name": "Reliability", "reasons": { "a": "Hosted lines. status.huggingface.co is a Better Stack page with 90-day component history for the Hub, Inference Endpoints, Spaces, the CDNs and Jobs, but no component for Inference Providers or the router (10 of 20). With no component, there is no readable incident history for the surface agents call, and the feed's 23 items from 10 June to 7 October 2026 don't name it (5). No rate limits for the router were found; the Hub rate-limits page gives numbers for Hub APIs, resolvers and pages only (0). No 429 or overload guidance for the router was found (0). No SLA found (0). Chat completions on the router is generally available; the Responses API is labelled beta (10). Routing between providers with `:fastest` or `:cheapest` softens a single provider's outage, which this checklist doesn't score.", "b": "Status page at status.mistral.ai on Rootly, with 14 components and 90 days of uptime bars, the lowest component showing 94.36% on 1 October (20). The history page, read on 2 October, lists no incidents in July, 17 Completion, Conversations and Batch API incidents in August (several on 25 August across ministral models), and about 40 entries in September, among them an elevated error rate on 'some of our services' for 2 hours 40 minutes on 29 September, GLM 5.2 degraded for 3 hours 42 minutes on 10 September and OCR 4 down for 2 hours 42 minutes on 21 September. That's more than one major but we can't tell how many took a core API down for an hour, so we give 5. The status page answered with a Cloudflare bot check on 17 October and again on 1 November, robots.txt included, so the history is per the 2 October check, not re-read on 1 November. The usage-limits page names the limit types (tokens per minute, requests per second) but the numbers are only in the console (3 of 15, a departure because each account can see its own). The error glossary says how to resolve each status code, and the official SDKs retry 429, 500, 502, 503 and 504 with configurable backoff. No Retry-After header confirmed (12 of 15). A Priority Tier for queueing exists, no SLA found (0). Chat completions on GA models is GA (10). 20+5+3+12+0+10 = 50." }, "scores": { "a": 25, "b": 50 } }, { "by": 20, "category": "payments", "leads": "mistral-api", "name": "Payments \u0026 pricing", "reasons": { "a": "No x402, MPP or L402 (0). Per-token prices for every model and provider published without a login in the router's /v1/models and on model pages (20). No free tier since 7 October 2026, when free users lost their included monthly credits; PRO's $2.00 of credits needs a subscription (0). Sign-up, token creation and credit purchase are browser steps (0).", "b": "No machine payment protocol (0). Per-token prices published without a login, re-read on 1 November. Mistral Large 4 is now listed at $0.70/$2.10 with cached input at $0.07 (the 17 October check read $1.36/$4.18 with a launch sale), and cached input is 10% across the range (20). Timestral has no API price because it isn't served on the API. Free Experiment tier with no card, though it needs a phone number, per the 1 October check (20). Browser sign-up (0). 0+20+20+0 = 40." }, "scores": { "a": 20, "b": 40 } }, { "by": 9, "category": "transparency", "leads": "mistral-api", "name": "Transparency \u0026 trust", "reasons": { "a": "Closed service under Terms of Service that name Inference Providers, with an Apache-2.0 Python client and an MIT JavaScript client (20). The security page and the docs agree on no training, no stored bodies and 30-day logs, but the privacy policy dates from 28 March 2023 and each provider's own data policy governs the rest (18 of 30). No deprecation policy found. Provider support changes and the 7 October removal of free credits are dated only in the docs repository history (5 of 20). The privacy policy lists 11 subprocessors with countries per the Inference Endpoints check, and the docs name every provider a request can reach, though not where each runs (15 of 20).", "b": "Closed service with clear terms, SDKs Apache-2.0, and several models published as open weights. Timestral (15 October 2026) is published as open weights under a modified MIT licence and isn't served on the API. Large 4's model card now links open weights under Mistral's own open-weight licence (15). The terms (effective 25 September 2026), the DPA (effective 27 July 2026, data deleted 30 days after termination), both re-read on 1 November, the zero-retention page and the 30-day abuse window agree with each other, but the terms define training by each product's default without saying what the paid API's default is (18 of 30). Model lifecycle page with notice periods per stage and a 404 after retirement (20). The DPA points to a subprocessor list at trust.mistral.ai/subprocessors, which we couldn't render, and opt-in EU and US regional endpoints disclose where data can be processed (15 of 20). 15+18+20+15 = 68." }, "scores": { "a": 71, "b": 80 } }, { "by": 6, "category": "security", "leads": "hugging-face-inference-providers", "name": "Security \u0026 auth", "reasons": { "a": "Model reading. Fine-grained user access tokens that can be limited to the `Make calls to Inference Providers` permission, rotated and revoked, plus a public revocation endpoint for leaked tokens, and organisation approval of fine-grained tokens on paid plans (30). Hugging Face says it doesn't store user data for training, but data handling past the router follows each provider's policy, with no per-request filter to exclude providers that train or retain (12 of 20). Request bodies and responses aren't stored when routed and debug logs are kept up to 30 days without user data or tokens, with provider retention outside that statement (10 of 15). Usage by model and provider in account settings, an Enterprise usage API, and Team and Enterprise admins can disable providers and set a spending limit (13 of 15). SOC 2 Type 2 for the Hub, of which the docs say Inference Providers is a feature, and security.txt valid to 2030 per the Inference Endpoints check; no bug bounty found (14 of 20).", "b": "Model reading. Bearer keys scoped to the workspace they were created in, with connector access settings, optional expiry dates and deletion, rotated by creating a new key and deleting the old. Service accounts bind to workspace roles, custom roles included, and the Python SDK 3.0.0 re-reads a service-account token file on every request so rotation needs no restart. Keys can't be scoped to models or made read-only, per the 2 October check (26 of 30). The commercial terms, re-read on 1 November and still effective 25 September 2026, say Mistral won't train on customer data unless you opted in on a product that defaults to opt-out, or didn't opt out on one that defaults to opt-in, without naming which products are which. Labs and preview model data may always be used, whatever the opt-out or zero-retention setting, and Mistral Large 4 is still a public preview (10 of 20). 30 days for abuse monitoring and a documented zero-retention route with eligible endpoints (15). Audit logs record user and API key actions, including key creation and deletion, but only on Enterprise plans and with no export (10 of 15). security.txt re-read on 1 November, with a security@mistral.ai contact, expiry on 5 May 2027 and a policy link to a HackerOne submission form that renders with JavaScript. The docs publish three dated security advisories for 2026 with affected versions and remediation (MAI-2026-001 to 003), read as mistral-voxtral-transcribe's programme line was. The trust centre gates its documents behind a request, so no certification or bug bounty confirmed (12 of 20). 26+10+15+10+12 = 73." }, "scores": { "a": 79, "b": 73 } } ], "facts": [ { "a": "Model router", "b": "Model API", "name": "Kind" }, { "a": "Hugging Face, Inc.", "b": "Mistral AI", "name": "Vendor" }, { "a": "https://router.huggingface.co/v1", "b": "https://api.mistral.ai/v1", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "API key", "b": "API key", "name": "Auth" }, { "a": "Pay per use", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under the Hugging Face Terms of Service, which name Inference Providers. The `huggingface_hub` Python client is Apache-2.0 and `@huggingface/inference` is MIT", "b": "Apache-2.0 (SDKs)", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-29", "b": "2026-10-28", "name": "Last release" }, { "a": "2022-09-15", "b": "2026-09-25", "name": "Terms last updated" }, { "a": "2023-03-28", "b": "2026-09-03", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "yes, with an opt-out", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "yes", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "483k npm/wk, 71.5M PyPI/wk", "b": "769 stars", "name": "Popularity" }, { "a": "none", "b": "4/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Mistral AI API scores 65.7 (B) on agent readiness against Hugging Face Inference Providers's 54 (C), and leads in 5 of 7 scored categories. Hugging Face Inference Providers leads on security \u0026 auth.", "question": "Which is better for AI agents, Hugging Face Inference Providers or Mistral AI API?" }, { "answer": "Both need an API key.", "question": "Do Hugging Face Inference Providers and Mistral AI API need an API key?" }, { "answer": "Yes. Hugging Face Inference Providers has a hosted endpoint at https://router.huggingface.co/v1 and Mistral AI API at https://api.mistral.ai/v1.", "question": "Can an agent call Hugging Face Inference Providers and Mistral AI API without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Security \u0026 auth, 79 against 73" ], "also": [ "No incidents deducted, where Mistral AI API loses 6 points for them" ], "goodFor": "Agents and developers who want open-weight models from several hosts on one token and one bill, with a public price and capability list per provider.", "slug": "hugging-face-inference-providers", "watchFor": "No rate limits, 429 behaviour or error responses documented for the router" }, { "aheadOn": [ "Reliability, 50 against 25", "Schema \u0026 documentation, 93 against 62", "Agent ergonomics, 91 against 58", "Payments \u0026 pricing, 40 against 20", "Transparency \u0026 trust, 80 against 71" ], "also": null, "goodFor": "Teams that need EU processing, open-weight models they can later run themselves, or an API an agent can read from an OpenAPI file.", "slug": "mistral-api", "watchFor": "Labs and preview models, Large 4 among them, may train on data sent from 2026-09-25, whatever the opt-out or zero-retention setting" } ], "history": { "hugging-face-inference-providers": null, "mistral-api": [ { "causes": [ "correction", "event" ], "date": "2026-11-01", "delta": -5.5, "from": 71.2, "fromGrade": "BB", "to": 65.7, "toGrade": "B" }, { "causes": [ "method" ], "date": "2026-10-08", "delta": -0.1, "from": 71.3, "fromGrade": "BB", "to": 71.2, "toGrade": "BB" } ] }, "job": { "capability": "inference.llm", "name": "LLM inference" }, "others": [ { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-hugging-face-inference-providers.json", "title": "Amazon Bedrock vs Hugging Face Inference Providers", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-hugging-face-inference-providers" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-mistral-api.json", "title": "Amazon Bedrock vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-hugging-face-inference-providers.json", "title": "Claude API vs Hugging Face Inference Providers", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-hugging-face-inference-providers" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-mistral-api.json", "title": "Claude API vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/antseed-vs-mistral-api.json", "title": "Antseed vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/antseed-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-hugging-face-inference-providers.json", "title": "Azure OpenAI in Foundry Models vs Hugging Face Inference Providers", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-hugging-face-inference-providers" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-mistral-api.json", "title": "Azure OpenAI in Foundry Models vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-hugging-face-inference-providers.json", "title": "BlockRun.AI vs Hugging Face Inference Providers", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-hugging-face-inference-providers" }, { "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-mistral-api.json", "title": "BlockRun.AI vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/cerebras-inference-vs-hugging-face-inference-providers.json", "title": "Cerebras Inference vs Hugging Face Inference Providers", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-hugging-face-inference-providers" }, { "json": "https://www.anchorterminal.com/compare/cerebras-inference-vs-mistral-api.json", "title": "Cerebras Inference vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-hugging-face-inference-providers.json", "title": "Cloudflare AI Gateway vs Hugging Face Inference Providers", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-hugging-face-inference-providers" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-mistral-api.json", "title": "Cloudflare AI Gateway vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-hugging-face-inference-providers.json", "title": "Cloudflare Workers AI vs Hugging Face Inference Providers", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-hugging-face-inference-providers" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-mistral-api.json", "title": "Cloudflare Workers AI vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-mistral-api" }, { "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-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/deepinfra-vs-hugging-face-inference-providers.json", "title": "DeepInfra vs Hugging Face Inference Providers", "url": "https://www.anchorterminal.com/compare/deepinfra-vs-hugging-face-inference-providers" }, { "json": "https://www.anchorterminal.com/compare/deepinfra-vs-mistral-api.json", "title": "DeepInfra vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/deepinfra-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/deepseek-api-vs-hugging-face-inference-providers.json", "title": "DeepSeek API vs Hugging Face Inference Providers", "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-hugging-face-inference-providers" }, { "json": "https://www.anchorterminal.com/compare/deepseek-api-vs-mistral-api.json", "title": "DeepSeek API vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/eden-ai-vs-mistral-api.json", "title": "Eden AI vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/eden-ai-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-hugging-face-inference-providers.json", "title": "Glimpse vs Hugging Face Inference Providers", "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-hugging-face-inference-providers" }, { "json": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-mistral-api.json", "title": "Glimpse vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-hugging-face-inference-providers.json", "title": "Fireworks AI Inference vs Hugging Face Inference Providers", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-hugging-face-inference-providers" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-mistral-api.json", "title": "Fireworks AI Inference vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/gemini-api-vs-hugging-face-inference-providers.json", "title": "Gemini Developer API vs Hugging Face Inference Providers", "url": "https://www.anchorterminal.com/compare/gemini-api-vs-hugging-face-inference-providers" }, { "json": "https://www.anchorterminal.com/compare/gemini-api-vs-mistral-api.json", "title": "Gemini Developer API vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/gemini-api-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/groq-vs-hugging-face-inference-providers.json", "title": "GroqCloud vs Hugging Face Inference Providers", "url": "https://www.anchorterminal.com/compare/groq-vs-hugging-face-inference-providers" }, { "json": "https://www.anchorterminal.com/compare/groq-vs-mistral-api.json", "title": "GroqCloud vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/groq-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-inkling-2-small.json", "title": "Hugging Face Inference Providers vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-jais-3.json", "title": "Hugging Face Inference Providers vs Jais 3", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-meta-model-api.json", "title": "Hugging Face Inference Providers vs Meta Model API", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-minimax-api.json", "title": "Hugging Face Inference Providers vs MiniMax API", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-minimax-api" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-muse-spark-open.json", "title": "Hugging Face Inference Providers vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-muse-spark-open" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-novita-ai.json", "title": "Hugging Face Inference Providers vs Novita AI", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-novita-ai" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-openai-api.json", "title": "Hugging Face Inference Providers vs OpenAI API", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-openai-api" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-reflection-beam.json", "title": "Hugging Face Inference Providers vs Beam 1.0", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-reflection-beam" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-sambanova.json", "title": "Hugging Face Inference Providers vs SambaCloud", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-sambanova" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-siliconflow.json", "title": "Hugging Face Inference Providers vs SiliconFlow", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-siliconflow" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-simplismart.json", "title": "Hugging Face Inference Providers vs Simplismart", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-simplismart" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-stepfun-api.json", "title": "Hugging Face Inference Providers vs StepFun API", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-stepfun-api" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-swe-2-flash.json", "title": "Hugging Face Inference Providers vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-together-inference.json", "title": "Hugging Face Inference Providers vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-together-inference" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-vertex-ai.json", "title": "Hugging Face Inference Providers vs Vertex AI (Gemini Enterprise Agent Platform)", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-vertex-ai" }, { "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-mistral-api.json", "title": "Inkling 2 Small vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-mistral-api.json", "title": "Jais 3 vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/jais-3-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-mistral-api.json", "title": "Meta Model API vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/minimax-api-vs-mistral-api.json", "title": "MiniMax API vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/minimax-api-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-muse-spark-open.json", "title": "Mistral AI API vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-muse-spark-open" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-nemotron-3-5-super-vl.json", "title": "Mistral AI API vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-novita-ai.json", "title": "Mistral AI API vs Novita AI", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-novita-ai" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-openai-api.json", "title": "Mistral AI API vs OpenAI API", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-openai-api" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-openrouter.json", "title": "Mistral AI API vs OpenRouter", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-openrouter" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-prism-inference.json", "title": "Mistral AI API vs Prism Inference", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-ramp-router.json", "title": "Mistral AI API vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-reflection-beam.json", "title": "Mistral AI API vs Beam 1.0", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-reflection-beam" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-routerplus.json", "title": "Mistral AI API vs RouterPlus", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-routerplus" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-sambanova.json", "title": "Mistral AI API vs SambaCloud", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-sambanova" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-siliconflow.json", "title": "Mistral AI API vs SiliconFlow", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-siliconflow" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-simplismart.json", "title": "Mistral AI API vs Simplismart", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-simplismart" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-stepfun-api.json", "title": "Mistral AI API vs StepFun API", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-stepfun-api" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-swe-2-flash.json", "title": "Mistral AI API vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-tencent-tokenhub.json", "title": "Mistral AI API vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-together-inference.json", "title": "Mistral AI API vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-together-inference" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-vercel-ai-gateway.json", "title": "Mistral AI API vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-vertex-ai.json", "title": "Mistral AI API vs Vertex AI (Gemini Enterprise Agent Platform)", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-vertex-ai" }, { "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/antseed-vs-hugging-face-inference-providers.json", "title": "Antseed vs Hugging Face Inference Providers", "url": "https://www.anchorterminal.com/compare/antseed-vs-hugging-face-inference-providers" }, { "json": "https://www.anchorterminal.com/compare/eden-ai-vs-hugging-face-inference-providers.json", "title": "Eden AI vs Hugging Face Inference Providers", "url": "https://www.anchorterminal.com/compare/eden-ai-vs-hugging-face-inference-providers" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-litellm.json", "title": "Hugging Face Inference Providers vs LiteLLM", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-litellm" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-openrouter.json", "title": "Hugging Face Inference Providers vs OpenRouter", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-openrouter" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-ramp-router.json", "title": "Hugging Face Inference Providers vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-routerplus.json", "title": "Hugging Face Inference Providers vs RouterPlus", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-routerplus" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-tencent-tokenhub.json", "title": "Hugging Face Inference Providers vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-vercel-ai-gateway.json", "title": "Hugging Face Inference Providers vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-nemotron-3-5-super-vl.json", "title": "Hugging Face Inference Providers vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-prism-inference.json", "title": "Hugging Face Inference Providers vs Prism Inference", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-prism-inference" } ], "panel": null, "scores": [ { "by": 25, "edge": "mistral-api", "hugging-face-inference-providers": 25, "key": "reliability", "mistral-api": 50, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 31, "edge": "mistral-api", "hugging-face-inference-providers": 62, "key": "schema", "mistral-api": 93, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 33, "edge": "mistral-api", "hugging-face-inference-providers": 58, "key": "ergonomics", "mistral-api": 91, "name": "Agent ergonomics", "weight": 13 }, { "by": 6, "edge": "hugging-face-inference-providers", "hugging-face-inference-providers": 79, "key": "security", "mistral-api": 73, "name": "Security \u0026 auth", "weight": 14 }, { "by": 20, "edge": "mistral-api", "hugging-face-inference-providers": 20, "key": "payments", "mistral-api": 40, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 0, "edge": "", "hugging-face-inference-providers": 80, "key": "maintenance", "mistral-api": 80, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 9, "edge": "mistral-api", "hugging-face-inference-providers": 71, "key": "transparency", "mistral-api": 80, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Mistral AI API scores 65.7 (B) on agent readiness against Hugging Face Inference Providers's 54 (C), and leads in 5 of 7 scored categories. Hugging Face Inference Providers leads on security \u0026 auth. Both do llm inference.", "tasks": null, "tutorials": [], "verdicts": { "hugging-face-inference-providers": "One Hugging Face token reaches open models on 18 partner providers at the providers' own prices, with a public model list that shows each provider's price, context and tool support. Router rate limits, error responses and its own status component were not found in the reviewed documentation, and free accounts have had no included credits since 7 October 2026.", "mistral-api": "Public OpenAPI document and an llms.txt with Markdown twins. Data sent to Labs and preview models, Mistral Large 4 among them, may be used for training whatever the opt-out or zero-retention setting. The default model, Medium 3.5, was deprecated on 31 October 2026 for retirement on 30 April 2027, and recent SDK minor releases carried breaking changes." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-mistral-api", "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-mistral-api.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-mistral-api.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-mistral-api.min.md" }, "markdown": "Mistral AI API scores 65.7 (B) on agent readiness against Hugging Face Inference Providers's 54 (C), and leads in 5 of 7 scored categories. Hugging Face Inference Providers leads on security \u0026 auth. Both do llm inference.\n\n- Hugging Face Inference Providers: grade C, 54/100, rank #926 of 1510. Markdown https://www.anchorterminal.com/tools/hugging-face-inference-providers.md · JSON https://www.anchorterminal.com/api/v1/tools/hugging-face-inference-providers.json\n- Mistral AI API: grade B, 65.7/100, rank #407 of 1510. Markdown https://www.anchorterminal.com/tools/mistral-api.md · JSON https://www.anchorterminal.com/api/v1/tools/mistral-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### Hugging Face Inference Providers (C)\n\nGood for: Agents and developers who want open-weight models from several hosts on one token and one bill, with a public price and capability list per provider.\n\nAhead on:\n- Security \u0026 auth, 79 against 73\n\nAlso in its favour:\n- No incidents deducted, where Mistral AI API loses 6 points for them\n\nWatch for: No rate limits, 429 behaviour or error responses documented for the router\n\n### Mistral AI API (B)\n\nGood for: Teams that need EU processing, open-weight models they can later run themselves, or an API an agent can read from an OpenAPI file.\n\nAhead on:\n- Reliability, 50 against 25\n- Schema \u0026 documentation, 93 against 62\n- Agent ergonomics, 91 against 58\n- Payments \u0026 pricing, 40 against 20\n- Transparency \u0026 trust, 80 against 71\n\nWatch for: Labs and preview models, Large 4 among them, may train on data sent from 2026-09-25, whatever the opt-out or zero-retention setting\n\n\n## Why the edge\n\n### Agent ergonomics: Mistral AI API +33\n\n- Hugging Face Inference Providers (58): Router reading of the model checklist (tool use, structured output, caching, context, batch, SDKs, errors), as for openrouter. Tool calling through the OpenAI-compatible API with `tool_choice`, support flagged per provider in /v1/models (15 of 20). Structured output documented, support flagged per provider and false on some (10 of 15). No prompt caching guidance found, though the Enterprise usage API counts cached input tokens (3 of 15). Routes to models with up to 1,048,576 tokens of context per the model list, a judgement call since a router has no default model (15). No batch API (0 of 10). Official clients in Python and JavaScript, plus any OpenAI SDK (10). Errors not documented (5 of 15).\n- Mistral AI API (91): Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors), per the 2 and 12 October checks. Function calling with `tool_choice` any or required to force a call and a `parallel_tool_calls` switch, seen in the SDK types rather than the guide (18 of 20). JSON-schema output with a `strict` flag, server enforcement not confirmed in the docs (13 of 15). Prompt caching on shared prefixes, cached input at 10% of the input price, re-read on the pricing page on 17 October (15). 256,000-token context on Medium 3.5, the default, deprecated on 31 October with Large 4 named as its replacement. Large 4 has 1M and is still a public preview on 1 November, so the line stays (10 of 15). A stateless Responses API (`/v1/responses`) arrived in the 23 October SDKs. Batch at half price (10). Official SDKs for Python and TypeScript (10). Error glossary (15). 18+13+15+10+10+10+15 = 91.\n\n### Schema \u0026 documentation: Mistral AI API +31\n\n- Hugging Face Inference Providers (62): No OpenAPI document for the router (openapi.json paths answer 404). The task reference pages are generated from typed JSON Schema specs in huggingface.js, and the router's /v1/models gives a machine-readable catalogue, so 12 of 25. llms.txt for the Inference Providers docs and a Markdown twin of every page via `.md` (10). Guides say what each task and policy is for, with a quick setup page for coding agents (14 of 20). Parameter tables with types for chat completion, though `response_format` and `tool_choice` show as unknown types (9 of 15). Examples in Python, JavaScript and curl on every task page, but no documented error responses for the router (9 of 15). No changelog of its own; the Hub changelog doesn't cover it and dated changes are only in the hub-docs history (8 of 15).\n- Mistral AI API (93): Public OpenAPI 3.1.0 document at docs.mistral.ai/openapi.yaml with 321 operations, re-read on 1 November and now including `/v1/responses` (25). llms.txt with Markdown twins of every page, re-read on 1 November (10). Reference not read in full (15 of 20). Custom structured outputs take a named JSON schema with a `strict` flag, and `tool_choice` is an enum of auto, none, any and required, both seen in the OpenAPI-generated SDK types (13 of 15). Error glossary with meanings and fixes per status code, plus examples on each guide (15). Release notes and dated model versions (15). 25+10+15+13+15+15 = 93.\n\n### Reliability: Mistral AI API +25\n\n- Hugging Face Inference Providers (25): Hosted lines. status.huggingface.co is a Better Stack page with 90-day component history for the Hub, Inference Endpoints, Spaces, the CDNs and Jobs, but no component for Inference Providers or the router (10 of 20). With no component, there is no readable incident history for the surface agents call, and the feed's 23 items from 10 June to 7 October 2026 don't name it (5). No rate limits for the router were found; the Hub rate-limits page gives numbers for Hub APIs, resolvers and pages only (0). No 429 or overload guidance for the router was found (0). No SLA found (0). Chat completions on the router is generally available; the Responses API is labelled beta (10). Routing between providers with `:fastest` or `:cheapest` softens a single provider's outage, which this checklist doesn't score.\n- Mistral AI API (50): Status page at status.mistral.ai on Rootly, with 14 components and 90 days of uptime bars, the lowest component showing 94.36% on 1 October (20). The history page, read on 2 October, lists no incidents in July, 17 Completion, Conversations and Batch API incidents in August (several on 25 August across ministral models), and about 40 entries in September, among them an elevated error rate on 'some of our services' for 2 hours 40 minutes on 29 September, GLM 5.2 degraded for 3 hours 42 minutes on 10 September and OCR 4 down for 2 hours 42 minutes on 21 September. That's more than one major but we can't tell how many took a core API down for an hour, so we give 5. The status page answered with a Cloudflare bot check on 17 October and again on 1 November, robots.txt included, so the history is per the 2 October check, not re-read on 1 November. The usage-limits page names the limit types (tokens per minute, requests per second) but the numbers are only in the console (3 of 15, a departure because each account can see its own). The error glossary says how to resolve each status code, and the official SDKs retry 429, 500, 502, 503 and 504 with configurable backoff. No Retry-After header confirmed (12 of 15). A Priority Tier for queueing exists, no SLA found (0). Chat completions on GA models is GA (10). 20+5+3+12+0+10 = 50.\n\n### Payments \u0026 pricing: Mistral AI API +20\n\n- Hugging Face Inference Providers (20): No x402, MPP or L402 (0). Per-token prices for every model and provider published without a login in the router's /v1/models and on model pages (20). No free tier since 7 October 2026, when free users lost their included monthly credits; PRO's $2.00 of credits needs a subscription (0). Sign-up, token creation and credit purchase are browser steps (0).\n- Mistral AI API (40): No machine payment protocol (0). Per-token prices published without a login, re-read on 1 November. Mistral Large 4 is now listed at $0.70/$2.10 with cached input at $0.07 (the 17 October check read $1.36/$4.18 with a launch sale), and cached input is 10% across the range (20). Timestral has no API price because it isn't served on the API. Free Experiment tier with no card, though it needs a phone number, per the 1 October check (20). Browser sign-up (0). 0+20+20+0 = 40.\n\n### Transparency \u0026 trust: Mistral AI API +9\n\n- Hugging Face Inference Providers (71): Closed service under Terms of Service that name Inference Providers, with an Apache-2.0 Python client and an MIT JavaScript client (20). The security page and the docs agree on no training, no stored bodies and 30-day logs, but the privacy policy dates from 28 March 2023 and each provider's own data policy governs the rest (18 of 30). No deprecation policy found. Provider support changes and the 7 October removal of free credits are dated only in the docs repository history (5 of 20). The privacy policy lists 11 subprocessors with countries per the Inference Endpoints check, and the docs name every provider a request can reach, though not where each runs (15 of 20).\n- Mistral AI API (80): Closed service with clear terms, SDKs Apache-2.0, and several models published as open weights. Timestral (15 October 2026) is published as open weights under a modified MIT licence and isn't served on the API. Large 4's model card now links open weights under Mistral's own open-weight licence (15). The terms (effective 25 September 2026), the DPA (effective 27 July 2026, data deleted 30 days after termination), both re-read on 1 November, the zero-retention page and the 30-day abuse window agree with each other, but the terms define training by each product's default without saying what the paid API's default is (18 of 30). Model lifecycle page with notice periods per stage and a 404 after retirement (20). The DPA points to a subprocessor list at trust.mistral.ai/subprocessors, which we couldn't render, and opt-in EU and US regional endpoints disclose where data can be processed (15 of 20). 15+18+20+15 = 68.\n\n### Security \u0026 auth: Hugging Face Inference Providers +6\n\n- Hugging Face Inference Providers (79): Model reading. Fine-grained user access tokens that can be limited to the `Make calls to Inference Providers` permission, rotated and revoked, plus a public revocation endpoint for leaked tokens, and organisation approval of fine-grained tokens on paid plans (30). Hugging Face says it doesn't store user data for training, but data handling past the router follows each provider's policy, with no per-request filter to exclude providers that train or retain (12 of 20). Request bodies and responses aren't stored when routed and debug logs are kept up to 30 days without user data or tokens, with provider retention outside that statement (10 of 15). Usage by model and provider in account settings, an Enterprise usage API, and Team and Enterprise admins can disable providers and set a spending limit (13 of 15). SOC 2 Type 2 for the Hub, of which the docs say Inference Providers is a feature, and security.txt valid to 2030 per the Inference Endpoints check; no bug bounty found (14 of 20).\n- Mistral AI API (73): Model reading. Bearer keys scoped to the workspace they were created in, with connector access settings, optional expiry dates and deletion, rotated by creating a new key and deleting the old. Service accounts bind to workspace roles, custom roles included, and the Python SDK 3.0.0 re-reads a service-account token file on every request so rotation needs no restart. Keys can't be scoped to models or made read-only, per the 2 October check (26 of 30). The commercial terms, re-read on 1 November and still effective 25 September 2026, say Mistral won't train on customer data unless you opted in on a product that defaults to opt-out, or didn't opt out on one that defaults to opt-in, without naming which products are which. Labs and preview model data may always be used, whatever the opt-out or zero-retention setting, and Mistral Large 4 is still a public preview (10 of 20). 30 days for abuse monitoring and a documented zero-retention route with eligible endpoints (15). Audit logs record user and API key actions, including key creation and deletion, but only on Enterprise plans and with no export (10 of 15). security.txt re-read on 1 November, with a security@mistral.ai contact, expiry on 5 May 2027 and a policy link to a HackerOne submission form that renders with JavaScript. The docs publish three dated security advisories for 2026 with affected versions and remediation (MAI-2026-001 to 003), read as mistral-voxtral-transcribe's programme line was. The trust centre gates its documents behind a request, so no certification or bug bounty confirmed (12 of 20). 26+10+15+10+12 = 73.\n\n## Score by category\n\n| Category | Weight | Hugging Face Inference Providers | Mistral AI API | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 25 | 50 | Mistral AI API +25 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 62 | 93 | Mistral AI API +31 |\n| Agent ergonomics | 13% (16.2 this run) | 58 | 91 | Mistral AI API +33 |\n| Security \u0026 auth | 14% (17.5 this run) | 79 | 73 | Hugging Face Inference Providers +6 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 40 | Mistral AI API +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 80 | 80 | even |\n| Transparency \u0026 trust | 7% (8.8 this run) | 71 | 80 | Mistral AI API +9 |\n| Negative events | ≤15 | 0 | -6 | |\n| **Total** | | **54 · C** | **65.7 · B** | |\n\n## Facts side by side\n\n| Fact | Hugging Face Inference Providers | Mistral AI API |\n| --- | --- | --- |\n| Kind | Model router | Model API |\n| Vendor | Hugging Face, Inc. | Mistral AI |\n| Hosted endpoint | `https://router.huggingface.co/v1` | `https://api.mistral.ai/v1` |\n| Transports | HTTP | HTTP |\n| Auth | API key | API key |\n| Pricing | Pay per use | Freemium |\n| x402 | no | no |\n| Licence | Proprietary service under the Hugging Face Terms of Service, which name Inference Providers. The `huggingface_hub` Python client is Apache-2.0 and `@huggingface/inference` is MIT | Apache-2.0 (SDKs) |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-29 | 2026-10-28 |\n| Terms last updated | 2022-09-15 | 2026-09-25 |\n| Privacy policy last updated | 2023-03-28 | 2026-09-03 |\n| Customer content may train models | not found in the text | yes, with an opt-out |\n| Terms restrict automated access | not found in the text | not found in the text |\n| Terms restrict benchmarking | not found in the text | yes |\n| Terms or service can change without notice | yes | yes |\n| Arbitration or class-action waiver | not found in the text | not found in the text |\n| Popularity | 483k npm/wk, 71.5M PyPI/wk | 769 stars |\n| Agent reviews | none | 4/5 (2) |\n\n## How the scores have moved\n\n### Hugging Face Inference Providers\n\nNo score change since it was listed.\n\n### Mistral AI API\n\n- -5.5 on 1 November 2026 (BB to B): correction, negative event\n- -0.1 on 8 October 2026: checklist\n\n## Verdicts\n\n**Hugging Face Inference Providers.** One Hugging Face token reaches open models on 18 partner providers at the providers' own prices, with a public model list that shows each provider's price, context and tool support. Router rate limits, error responses and its own status component were not found in the reviewed documentation, and free accounts have had no included credits since 7 October 2026.\n\n**Mistral AI API.** Public OpenAPI document and an llms.txt with Markdown twins. Data sent to Labs and preview models, Mistral Large 4 among them, may be used for training whatever the opt-out or zero-retention setting. The default model, Medium 3.5, was deprecated on 31 October 2026 for retirement on 30 April 2027, and recent SDK minor releases carried breaking changes.\n\n## Before you call either\n\n### Hugging Face Inference Providers\n\n1. Read https://router.huggingface.co/v1/models before choosing a provider; it shows price, context and `supports_tools` per provider\n2. Pin a provider with `model:\u003cprovider\u003e` when tool calling or structured output matters, since support varies by provider\n3. Use a fine-grained token with only the Inference Providers permission, and send `X-HF-Bill-To` to bill an organisation\n4. Back off on 429 without assuming a Retry-After header, since none is documented for the router\n\n### Mistral AI API\n\n1. Stay off `labs-*` and preview models, `mistral-large-4` included while it is in preview, for anything confidential\n2. Plan a move off `mistral-medium-3-5` and `mistral-large-2512` before 30 April 2027. `mistral-medium-latest` still points to Medium 3.5\n3. Pin each SDK to one version. Minor releases of `mistralai` and `@mistralai/mistralai` have removed fields without notice\n4. Treat a 404 on a model id as retirement and read the models page for the replacement\n5. Set `tool_choice` to any to force a tool call, and `strict` on the JSON schema for structured output\n\n## Questions\n\n### Which is better for AI agents, Hugging Face Inference Providers or Mistral AI API?\n\nMistral AI API scores 65.7 (B) on agent readiness against Hugging Face Inference Providers's 54 (C), and leads in 5 of 7 scored categories. Hugging Face Inference Providers leads on security \u0026 auth.\n\n### Do Hugging Face Inference Providers and Mistral AI API need an API key?\n\nBoth need an API key.\n\n### Can an agent call Hugging Face Inference Providers and Mistral AI API without installing anything?\n\nYes. Hugging Face Inference Providers has a hosted endpoint at https://router.huggingface.co/v1 and Mistral AI API at https://api.mistral.ai/v1.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-mistral-api.json, and with the fewest tokens: https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-mistral-api.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"hugging-face-inference-providers\", \"b\": \"mistral-api\"}`. From a terminal: `anchor compare hugging-face-inference-providers mistral-api`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/hugging-face-inference-providers.json and https://www.anchorterminal.com/api/v1/tools/mistral-api.json\n\n## Other comparisons with Hugging Face Inference Providers or Mistral AI API\n\n- [Amazon Bedrock vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/amazon-bedrock-vs-hugging-face-inference-providers.md)\n- [Amazon Bedrock vs Mistral AI API](https://www.anchorterminal.com/compare/amazon-bedrock-vs-mistral-api.md)\n- [Claude API vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/anthropic-api-vs-hugging-face-inference-providers.md)\n- [Claude API vs Mistral AI API](https://www.anchorterminal.com/compare/anthropic-api-vs-mistral-api.md)\n- [Antseed vs Mistral AI API](https://www.anchorterminal.com/compare/antseed-vs-mistral-api.md)\n- [Azure OpenAI in Foundry Models vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/azure-openai-vs-hugging-face-inference-providers.md)\n- [Azure OpenAI in Foundry Models vs Mistral AI API](https://www.anchorterminal.com/compare/azure-openai-vs-mistral-api.md)\n- [BlockRun.AI vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/blockrun-ai-vs-hugging-face-inference-providers.md)\n- [BlockRun.AI vs Mistral AI API](https://www.anchorterminal.com/compare/blockrun-ai-vs-mistral-api.md)\n- [Cerebras Inference vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/cerebras-inference-vs-hugging-face-inference-providers.md)\n- [Cerebras Inference vs Mistral AI API](https://www.anchorterminal.com/compare/cerebras-inference-vs-mistral-api.md)\n- [Cloudflare AI Gateway vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-hugging-face-inference-providers.md)\n- [Cloudflare AI Gateway vs Mistral AI API](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-mistral-api.md)\n- [Cloudflare Workers AI vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-hugging-face-inference-providers.md)\n- [Cloudflare Workers AI vs Mistral AI API](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-mistral-api.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 Mistral AI API](https://www.anchorterminal.com/compare/cohere-chat-vs-mistral-api.md)\n- [DeepInfra vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/deepinfra-vs-hugging-face-inference-providers.md)\n- [DeepInfra vs Mistral AI API](https://www.anchorterminal.com/compare/deepinfra-vs-mistral-api.md)\n- [DeepSeek API vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/deepseek-api-vs-hugging-face-inference-providers.md)\n- [DeepSeek API vs Mistral AI API](https://www.anchorterminal.com/compare/deepseek-api-vs-mistral-api.md)\n- [Eden AI vs Mistral AI API](https://www.anchorterminal.com/compare/eden-ai-vs-mistral-api.md)\n- [Glimpse vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/elorian-glimpse-vs-hugging-face-inference-providers.md)\n- [Glimpse vs Mistral AI API](https://www.anchorterminal.com/compare/elorian-glimpse-vs-mistral-api.md)\n- [Fireworks AI Inference vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/fireworks-inference-vs-hugging-face-inference-providers.md)\n- [Fireworks AI Inference vs Mistral AI API](https://www.anchorterminal.com/compare/fireworks-inference-vs-mistral-api.md)\n- [Gemini Developer API vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/gemini-api-vs-hugging-face-inference-providers.md)\n- [Gemini Developer API vs Mistral AI API](https://www.anchorterminal.com/compare/gemini-api-vs-mistral-api.md)\n- [GroqCloud vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/groq-vs-hugging-face-inference-providers.md)\n- [GroqCloud vs Mistral AI API](https://www.anchorterminal.com/compare/groq-vs-mistral-api.md)\n- [Hugging Face Inference Providers vs Inkling 2 Small](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-inkling-2-small.md)\n- [Hugging Face Inference Providers vs Jais 3](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-jais-3.md)\n- [Hugging Face Inference Providers vs Meta Model API](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-meta-model-api.md)\n- [Hugging Face Inference Providers vs MiniMax API](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-minimax-api.md)\n- [Hugging Face Inference Providers vs Muse Spark Open](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-muse-spark-open.md)\n- [Hugging Face Inference Providers vs Novita AI](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-novita-ai.md)\n- [Hugging Face Inference Providers vs OpenAI API](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-openai-api.md)\n- [Hugging Face Inference Providers vs Beam 1.0](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-reflection-beam.md)\n- [Hugging Face Inference Providers vs SambaCloud](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-sambanova.md)\n- [Hugging Face Inference Providers vs SiliconFlow](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-siliconflow.md)\n- [Hugging Face Inference Providers vs Simplismart](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-simplismart.md)\n- [Hugging Face Inference Providers vs StepFun API](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-stepfun-api.md)\n- [Hugging Face Inference Providers vs SWE-2 Flash](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-swe-2-flash.md)\n- [Hugging Face Inference Providers vs Together AI Inference](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-together-inference.md)\n- [Hugging Face Inference Providers vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-vertex-ai.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 Mistral AI API](https://www.anchorterminal.com/compare/inkling-2-small-vs-mistral-api.md)\n- [Jais 3 vs Mistral AI API](https://www.anchorterminal.com/compare/jais-3-vs-mistral-api.md)\n- [Meta Model API vs Mistral AI API](https://www.anchorterminal.com/compare/meta-model-api-vs-mistral-api.md)\n- [MiniMax API vs Mistral AI API](https://www.anchorterminal.com/compare/minimax-api-vs-mistral-api.md)\n- [Mistral AI API vs Muse Spark Open](https://www.anchorterminal.com/compare/mistral-api-vs-muse-spark-open.md)\n- [Mistral AI API vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/mistral-api-vs-nemotron-3-5-super-vl.md)\n- [Mistral AI API vs Novita AI](https://www.anchorterminal.com/compare/mistral-api-vs-novita-ai.md)\n- [Mistral AI API vs OpenAI API](https://www.anchorterminal.com/compare/mistral-api-vs-openai-api.md)\n- [Mistral AI API vs OpenRouter](https://www.anchorterminal.com/compare/mistral-api-vs-openrouter.md)\n- [Mistral AI API vs Prism Inference](https://www.anchorterminal.com/compare/mistral-api-vs-prism-inference.md)\n- [Mistral AI API vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/mistral-api-vs-ramp-router.md)\n- [Mistral AI API vs Beam 1.0](https://www.anchorterminal.com/compare/mistral-api-vs-reflection-beam.md)\n- [Mistral AI API vs RouterPlus](https://www.anchorterminal.com/compare/mistral-api-vs-routerplus.md)\n- [Mistral AI API vs SambaCloud](https://www.anchorterminal.com/compare/mistral-api-vs-sambanova.md)\n- [Mistral AI API vs SiliconFlow](https://www.anchorterminal.com/compare/mistral-api-vs-siliconflow.md)\n- [Mistral AI API vs Simplismart](https://www.anchorterminal.com/compare/mistral-api-vs-simplismart.md)\n- [Mistral AI API vs StepFun API](https://www.anchorterminal.com/compare/mistral-api-vs-stepfun-api.md)\n- [Mistral AI API vs SWE-2 Flash](https://www.anchorterminal.com/compare/mistral-api-vs-swe-2-flash.md)\n- [Mistral AI API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/mistral-api-vs-tencent-tokenhub.md)\n- [Mistral AI API vs Together AI Inference](https://www.anchorterminal.com/compare/mistral-api-vs-together-inference.md)\n- [Mistral AI API vs Vercel AI Gateway](https://www.anchorterminal.com/compare/mistral-api-vs-vercel-ai-gateway.md)\n- [Mistral AI API vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/mistral-api-vs-vertex-ai.md)\n- [Mistral AI API vs xAI API (Grok)](https://www.anchorterminal.com/compare/mistral-api-vs-xai-api.md)\n- [Antseed vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/antseed-vs-hugging-face-inference-providers.md)\n- [Eden AI vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/eden-ai-vs-hugging-face-inference-providers.md)\n- [Hugging Face Inference Providers vs LiteLLM](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-litellm.md)\n- [Hugging Face Inference Providers vs OpenRouter](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-openrouter.md)\n- [Hugging Face Inference Providers vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-ramp-router.md)\n- [Hugging Face Inference Providers vs RouterPlus](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-routerplus.md)\n- [Hugging Face Inference Providers vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-tencent-tokenhub.md)\n- [Hugging Face Inference Providers vs Vercel AI Gateway](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-vercel-ai-gateway.md)\n- [Hugging Face Inference Providers vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-nemotron-3-5-super-vl.md)\n- [Hugging Face Inference Providers vs Prism Inference](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-prism-inference.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": "Hugging Face Inference Providers vs Mistral AI API", "url": "" } ], "description": "Mistral AI scores 65.7 (B) to Hugging Face Inference Providers's 54 (C) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Hugging Face Inference Providers C 54", "Mistral AI API B 65.7", "scores" ], "h1": "Hugging Face Inference Providers vs Mistral AI API", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/hugging-face-inference-providers-vs-mistral-api", "published": "2026-10-01", "section": "tools", "title": "Hugging Face Inference Providers vs Mistral AI for AI agents (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-mistral-api" }, "tokens": { "markdown": 7300, "slim": 3430 }, "version": 1 }