{ "data": { "a": { "slug": "muse-ember", "name": "Muse Ember", "vendor": "Meta", "vendorUrl": "https://dev.meta.ai", "kind": "model", "category": "inference", "summary": "Muse Ember is Meta's smallest and most efficient hosted model, built for sub-agent tasks, tool calls, routing and work over large collections of files and images, taking text, images, video, audio and PDF with a 1M-token context.", "url": "https://www.anchorterminal.com/tools/muse-ember", "markdownUrl": "https://www.anchorterminal.com/tools/muse-ember.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/muse-ember.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/muse-ember.json", "dns": "muse-ember.grade.anchorterminal.com", "license": "Closed model, used through Meta Model API and Muse Code under the Meta Model API Terms of Service (last updated 9 October 2026). No open weights; Meta's open-weight models are Muse Spark Open and Muse Glimmer", "transports": [], "remoteUrl": "https://api.meta.ai/v1", "packages": [], "auth": "api-key", "authNotes": "A bearer key from the API keys tab of the Model API dashboard, read from MODEL_API_KEY in Meta's examples, after a browser sign-up with email, mobile number, Facebook, Google or GitHub. Keys belong to a team and share its limits, with no scopes found, per the meta-model-api listing.", "pricing": "usage", "pricingNotes": "$0.10 per million input tokens, $0.004 cached and $0.50 output for requests up to 200K input tokens, and $0.30, $0.012 and $1.50 for the whole request above that. Standard mode only, no Contributor discount. Web search grounding $2.50 per 1,000 queries. Included in every Muse Code plan. No free API allowance found (checked 2026-11-09).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 on Meta's pricing page, which bills tokens to a team account with a card (checked 2026-11-09).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-09" }, "docsUrl": "https://dev.meta.ai/docs/muse-ember", "llmsTxt": "https://dev.meta.ai/llms.txt", "capabilities": [ "inference.llm" ], "tags": [ "official", "hosted", "model", "multimodal", "vision", "reasoning", "long-context", "tool-calling", "openai-compatible", "anthropic-compatible", "usage-priced", "card-required", "closed-source", "llms-txt", "new" ], "lastRelease": "2026-11-09", "graded": true, "anchor": { "graded": true, "score": 51.8, "grade": "D", "agentReady": false, "rank": 1017, "ranked": true, "rankOf": 1515, "categoryRank": 36, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 72, "maintenance": 46, "payments": 20, "reliability": 40, "schema": 60, "security": 64, "transparency": 53 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-09" }, "negative": 0, "verdict": "A cheap, capable model for the repeated parts of agent work, at $0.10 and $0.50 per million tokens with a 1M context and Meta's figures putting it level with Claude Haiku 5.5 on fewer tokens. Launched today on an API with no readable status page, SLA or deprecation policy, and closed, with no weights.", "bestFor": "Agents that hand out many small, bounded tasks (sub-agents, tool loops, routing, extraction over thousands of files) and want a cheap multimodal model with a 1M context behind the same API as a bigger Muse model.", "strengths": [ "$0.10 input, $0.004 cached and $0.50 output per million tokens up to 200K input, published without a login", "Text, image, video, audio and PDF in, a 1,048,576-token context and up to 524,288 output tokens", "The same request body as Muse Spark and Muse Wonder on Responses, Chat Completions and Messages endpoints", "Tool calling, structured output, computer use and search grounding", "Reasoning effort from minimal to max, with clear guidance on what to hand it and what not to", "3,000 requests and 4,000,000 tokens a minute per team, published" ], "weaknesses": [ "No weights and no parameter count published, so it can't be run locally", "Requests over 200K input tokens are billed at three times the rate for the whole request", "Default reasoning effort is max, which spends output tokens on simple routing calls unless set lower", "No readable status page, SLA, deprecation policy or API changelog, per the meta-model-api listing", "Benchmark and cost figures are Meta's own, several on internal benchmarks" ], "agentNotes": [ "Call https://api.meta.ai/v1/responses (or /chat/completions or /messages) with model muse-ember-1.0 and a bearer MODEL_API_KEY", "Set the effort explicitly, reasoning.effort on Responses or reasoning_effort on Chat Completions. It defaults to max, and none isn't accepted; minimal or low suits classification and routing", "Keep input under 200K tokens a request, cached tokens and previous_response_id history included, or the whole request bills at the long-context rate", "Use it for sub-agents and bounded repeated tasks, and a larger Muse model for the plan, as Meta advises", "Use strict structured output for extraction and routing steps", "In Claude Code, map the haiku alias and sub-agent model to muse-ember-1.0, per Meta's guide" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 51.8 } ], "editorialScores": { "ergonomics": 72, "maintenance": 46, "payments": 20, "reliability": 40, "schema": 60, "security": 64, "transparency": 41 }, "provenanceScore": 64, "checked": { "categories": { "ergonomics": "2026-11-09", "maintenance": "2026-11-09", "payments": "2026-11-09", "reliability": "2026-11-09", "schema": "2026-11-09", "security": "2026-11-09", "transparency": "2026-11-09" }, "last": "2026-11-09", "oldest": "2026-11-09", "stale": false, "staleAfterDays": 90 } }, "connect": { "http": "curl -X POST \"https://api.meta.ai/v1/responses\" \\\n -H \"Authorization: Bearer $MODEL_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"model\": \"muse-ember-1.0\",\n \"input\": \"Classify this support ticket as billing, bug, or feature request.\",\n \"reasoning\": {\"effort\": \"low\"}\n}'" }, "letme": { "capability": "https://letme.dev/inference.llm", "tool": "https://letme.dev/muse-ember" }, "sameCompany": [ "muse-spark-open", "muse-code", "muse-glimmer-30b" ], "sameModel": [ "meta-model-api" ], "area": "models", "unitPrices": [ { "item": "Muse Ember input", "unit": "1m-tokens", "usd": 0.1, "note": "Up to 200K input tokens a request; $0.30 above, for the whole request" }, { "item": "Muse Ember cached input", "unit": "1m-tokens", "usd": 0.004, "note": "$0.012 above 200K input tokens" }, { "item": "Muse Ember output", "unit": "1m-tokens", "usd": 0.5, "note": "$1.50 above 200K input tokens" } ], "provenance": { "legalEntity": "Meta Platforms, Inc.", "domain": "meta.ai", "domainRegistered": "2017-12-16", "endpointOnVendorDomain": true, "terms": "https://dev.meta.ai/legal/terms-of-service", "privacy": "https://www.facebook.com/privacy/policy/", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-11-09", "notes": [ "Company and platform facts are the meta-model-api listing's (checked 4 November 2026): Meta Platforms, Inc., or Meta Platforms Ireland Limited in the European Region, under the 9 October 2026 terms; no readable status page; no Model API changelog; no security.txt on dev.meta.ai.", "dev.meta.ai's and research.meta.ai's robots.txt allow our reader on the pages read on 9 November. domainRegistered is carried from the meta-model-api listing's RDAP reading." ], "score": 64 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/muse-ember.json", "live": { "slug": "muse-ember", "probe": { "target": "https://api.meta.ai/v1", "method": "get", "lastAt": "2026-11-09T20:50:02.257490788Z", "lastOk": true, "lastStatus": 404, "lastMs": 46, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 48, "p95ms24h": 72, "samples24h": 10, "samples30d": 10, "days": [ { "date": "2026-11-09", "probes": 10, "ok": 10 } ], "since": "2026-11-09T19:55:51.172718582Z" }, "updatedAt": "2026-11-09T20:50:02.257490788Z" }, "streak": { "days": 0, "from": "2026-11-09", "sinceWatching": true, "best": 0 } }, "answer": "Vercel AI Gateway scores 67.8 (B) on agent readiness against Muse Ember's 51.8 (D), and leads in 6 of 7 scored categories.", "b": { "slug": "vercel-ai-gateway", "name": "Vercel AI Gateway", "vendor": "Vercel Inc.", "vendorUrl": "https://vercel.com", "kind": "router", "category": "inference", "summary": "Vercel AI Gateway is a hosted router for model APIs. One API key or Vercel OIDC token reaches models from OpenAI, Anthropic, Google and others through OpenAI-compatible, Anthropic-compatible and AI SDK interfaces, with budgets, request logs and provider failover.", "url": "https://www.anchorterminal.com/tools/vercel-ai-gateway", "markdownUrl": "https://www.anchorterminal.com/tools/vercel-ai-gateway.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/vercel-ai-gateway.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/vercel-ai-gateway.json", "dns": "vercel-ai-gateway.grade.anchorterminal.com", "repo": "https://github.com/vercel/ai", "license": "Proprietary service under Vercel's Terms of Service and AI Product Terms, with Token Pass terms on its docs page. Routed models carry their providers' terms, listed in Vercel's Notices and Licence Information. The `@ai-sdk/gateway` provider is Apache-2.0", "transports": [ "http" ], "remoteUrl": "https://ai-gateway.vercel.sh/v1", "packages": [ { "registry": "npm", "name": "@ai-sdk/gateway" }, { "registry": "npm", "name": "ai" }, { "registry": "pypi", "name": "ai" } ], "auth": "mixed", "authNotes": "An AI Gateway API key as a Bearer token from any environment, or a Vercel OIDC token on Vercel deployments (12 hours locally, refreshed with `vercel env pull`). Keys belong to a team, can be limited to one project and given an expiry and a budget, and are created in the dashboard, with the Vercel CLI or by `POST /v1/api-keys` with a Vercel access token. A person creates the Vercel account in a browser. Token Pass needs its own Token Pass API key, and OIDC tokens cannot spend Token Pass credit.", "pricing": "usage", "pricingNotes": "Prepaid AI Gateway Credits at each provider's list price, with no markup or platform fee, including BYOK. A monthly free credit covers a subset of models and needs a valid payment method on the team. Credits expire a year after purchase. Add-ons are billed separately, and Token Pass is $30 a team a month on Pro for $80 of credit on two models, in early access (https://vercel.com/docs/ai-gateway/pricing, https://vercel.com/docs/ai-gateway/token-pass, checked 2026-10-17).", "priceSummary": "$30 / mo", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the AI Gateway docs, the pricing page, the Token Pass pages or the AI Gateway entries of the changelog sitemap. Payment is by prepaid credits bought with a card, or by invoice on Enterprise (checked 2026-10-17).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 29597661, "pypiWeekly": null, "asOf": "2026-10-17" }, "docsUrl": "https://vercel.com/docs/ai-gateway", "llmsTxt": "https://vercel.com/llms.txt", "openapi": "https://vercel.com/openapi.json", "capabilities": [ "inference.router", "inference.llm", "inference.fast", "inference.decision", "obs.gateway", "obs.traces", "embed.text", "image.generate", "video.generate" ], "tags": [ "hosted", "router", "usage-based", "prepaid", "free-tier", "openai-compatible", "anthropic-compatible", "llms-txt", "openapi", "typescript", "python", "oidc", "cli", "early-access", "status-page", "bug-bounty", "soc2", "iso27001" ], "lastRelease": "2026-10-30", "graded": true, "anchor": { "graded": true, "score": 67.8, "grade": "B", "agentReady": false, "rank": 303, "ranked": true, "rankOf": 1515, "categoryRank": 14, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 83, "maintenance": 79, "payments": 20, "reliability": 79, "schema": 74, "security": 79, "transparency": 71 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": -3, "negativeNotes": [ "April 2026. Vercel's security bulletin says an attacker took over an employee's account through a compromised third-party AI tool, reached internal systems and decrypted non-sensitive environment variables of a limited subset of customers. AI Gateway was generally available then, and its docs have deployments keep AI Gateway and Token Pass API keys as environment variables. The bulletin documents remediation and marks the incident closed on 16 October 2026, so 3 of a possible 15 is taken, as for vercel-connect (https://vercel.com/kb/bulletin/vercel-april-2026-security-incident)." ], "verdict": "Token prices pass through with no markup, prompts are not stored by the gateway, and budgets, provider failover and per-request logs are built in. The free monthly credit needs a card on file, rate limits are not published as numbers, no SLA covers the API, and the contractual promise not to train on content applies to Enterprise subscriptions only.", "bestFor": "Teams that want one key, one bill, budgets and failover in front of many model providers, especially on Vercel with OIDC.", "strengths": [ "Token prices are each provider's list price with no markup or platform fee, including requests made with the customer's own provider keys", "The model list at `GET /v1/models` needs no key and gives prices, context windows, supported parameters and ZDR and no-training flags for 498 models", "Budgets per team, project, API key or team member reject spend with a 402, distinct from a 429 rate limit", "The gateway logs request metadata only. Prompt and response content is deleted when the request completes, per the FAQ and the ZDR page", "Failed provider attempts are retried on a model's other providers, and every routing attempt appears in the request logs" ], "weaknesses": [ "The free monthly credit needs a valid payment method on the team, and its amount is not stated in the reviewed docs", "No rate-limit numbers are published, and the Enterprise SLA excludes the APIs, so the inference API carries no uptime commitment", "The contractual promise not to train on AI Gateway content covers Enterprise subscriptions only. Provider no-training and ZDR filters are opt-in per request", "A failed BYOK request falls back to Vercel's credentials and is billed to credits, and the no-training filter is not applied to BYOK", "Token Pass is early access for Pro teams only, covers two models, has no failover and fails with a 403 once the $80 credit is spent" ], "agentNotes": [ "Read `GET https://ai-gateway.vercel.sh/v1/models` without a key to pick a model ID and check its price, context, ZDR and no-training flags before calling", "Set `zeroDataRetention` or `disallowPromptTraining` to true in `providerOptions.gateway` on sensitive requests. Default routing ignores provider retention and training policies", "Treat a 429 as retryable and honour `retry-after` when present. A 402 with `quota_for_entity_exceeded` is a spent budget, so do not retry it", "On a Token Pass key, a 403 with `no_providers_available` means spent credit or a model outside the pass. Retry with a standard AI Gateway key, which bills credits", "Set `inferenceRegion` when data residency matters. The default `global` may run inference outside the user's jurisdiction" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 67.8 } ], "editorialScores": { "ergonomics": 83, "maintenance": 79, "payments": 20, "reliability": 79, "schema": 74, "security": 79, "transparency": 55 }, "provenanceScore": 86, "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": "pnpm add ai@latest", "http": "curl https://ai-gateway.vercel.sh/v1/chat/completions \\\n -H \"Authorization: Bearer $AI_GATEWAY_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"model\": \"openai/gpt-6-astra\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Explain AI Gateway in one sentence.\"\n }\n ]\n }'" }, "letme": { "capability": "https://letme.dev/inference.router", "tool": "https://letme.dev/vercel-ai-gateway" }, "sameCompany": [ "vercel-sandbox", "vercel-connect" ], "area": "models", "unitPrices": [ { "item": "Token Pass subscription (Pro teams)", "unit": "month", "usd": 30, "note": "$80 of monthly credit on two featured models. Early access" }, { "item": "Team-wide Zero Data Retention", "unit": "1k-requests", "usd": 0.1, "note": "Pro and Enterprise. Per-request ZDR is free" }, { "item": "Team-wide provider allowlist", "unit": "1k-requests", "usd": 0.1, "note": "Successful requests, Pro and Enterprise" }, { "item": "Custom Reporting query", "unit": "1k-requests", "usd": 5, "note": "Queries to the reporting endpoint" }, { "item": "Custom Reporting write of a tag, user ID or quota entity ID", "unit": "1k-requests", "usd": 0.075, "note": "Each unique value in a request counts as one write" }, { "item": "AI Gateway trace delivered to a drain", "unit": "1k-requests", "usd": 0.05, "note": "Listed per 1,000 traces, Pro and Enterprise" }, { "item": "Trace egress", "unit": "gb", "usd": 0.5, "note": "Billed through Drains usage" } ], "provenance": { "legalEntity": "Vercel Inc.", "domain": "vercel.com", "domainRegistered": "1999-10-04", "endpointOnVendorDomain": false, "terms": "https://vercel.com/legal/terms", "privacy": "https://vercel.com/legal/privacy-policy", "statusPage": "https://www.vercel-status.com", "changelog": "https://vercel.com/changelog", "securityTxt": "valid", "checked": "2026-11-01", "notes": [ "The Terms of Service (last updated 19 October 2026) name Vercel Inc. The AI Product Terms (last updated 17 March 2026, effective 31 March 2026) have a section for AI Gateway and form part of those terms.", "The Privacy Notice is effective from 1 June 2026. The DPA (effective 31 March 2026) applies to Pro and Enterprise plans.", "https://vercel.com/.well-known/security.txt points to HackerOne and responsible.disclosure@vercel.com and expires 2027-09-28 (re-read 1 November 2026).", "The API answers at ai-gateway.vercel.sh, a Vercel domain other than vercel.com. Management calls go to api.vercel.com.", "RDAP gives vercel.com a registration date of 1999-10-04, long before Vercel, so the domain was bought later.", "AI Gateway is a component on the status page at www.vercel-status.com." ], "score": 86 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/vercel-ai-gateway.json", "live": { "slug": "vercel-ai-gateway", "probe": { "target": "https://ai-gateway.vercel.sh/v1", "method": "get", "lastAt": "2026-11-09T20:50:22.433276589Z", "lastOk": true, "lastStatus": 404, "lastMs": 35, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 38, "p95ms24h": 137, "samples24h": 244, "samples30d": 5656, "days": [ { "date": "2026-10-17", "probes": 21, "ok": 21 }, { "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": 250, "ok": 250 }, { "date": "2026-10-29", "probes": 249, "ok": 249 }, { "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": 243, "ok": 243 }, { "date": "2026-11-08", "probes": 243, "ok": 243 }, { "date": "2026-11-09", "probes": 212, "ok": 212 } ], "since": "2026-10-17T00:00:00Z" }, "vendorStatus": { "page": "https://www.vercel-status.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-09T20:47:04.923898375Z" }, "versions": [ { "registry": "github", "name": "vercel/ai", "version": "@ai-sdk/vue@3.0.326", "released": "2026-11-09", "seenAt": "2026-11-09T03:10:22.913568116Z" }, { "registry": "npm", "name": "@ai-sdk/gateway", "version": "4.0.139", "seenAt": "2026-11-09T03:10:20.530550965Z" }, { "registry": "npm", "name": "ai", "version": "7.0.166", "seenAt": "2026-11-09T03:10:20.742312959Z" }, { "registry": "pypi", "name": "ai", "version": "0.9.0", "released": "2026-11-04", "seenAt": "2026-11-09T03:10:22.723401789Z" } ], "githubStars": 27818, "npmWeekly": 44010319, "pypiWeekly": 39896, "securityTxt": { "url": "https://vercel.com/.well-known/security.txt", "state": "valid", "expires": "2027-09-28T12:00:00.000Z", "checkedAt": "2026-11-09T16:05:24.872958074Z" }, "llmsTxt": { "url": "https://vercel.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-09T15:41:18.66353259Z" }, "domain": { "domain": "vercel.com", "registered": "1999-10-04", "source": "https://rdap.verisign.com/com/v1/domain/vercel.com", "checkedAt": "2026-11-08T15:11:10.088686399Z" }, "pages": [ { "url": "https://vercel.com/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-11-09T15:54:11.140864139Z", "changedAt": "2026-11-08T15:15:14.532326852Z", "fingerprint": "ea7fcfa97129" }, { "url": "https://ai-gateway.vercel.sh/v1/models", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-09T15:30:18.968914784Z", "changedAt": "0001-01-01T00:00:00Z" }, { "url": "https://vercel.com/changelog/laya-decision-model-now-available-on-ai-gateway-free-through-october-31", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-09T15:54:13.322003155Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "6bbbff189272" }, { "url": "https://vercel.com/changelog/tako-search-is-free-on-ai-gateway-through-september-30th", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-09T15:54:15.330735795Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "196bc432bb9c" }, { "url": "https://vercel.com/docs/ai-gateway/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-09T15:54:17.346814331Z", "changedAt": "2026-11-08T15:15:23.859461119Z", "fingerprint": "f0fe41c0ebfa" }, { "url": "https://vercel.com/legal/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-09T15:54:23.349989329Z", "changedAt": "2026-10-28T04:46:11.674155692Z", "fingerprint": "c545eb853c20" }, { "url": "https://vercel.com/legal/terms", "kind": "terms", "status": 200, "checkedAt": "2026-11-09T15:54:25.452449614Z", "changedAt": "2026-10-28T04:46:13.475126487Z", "fingerprint": "100a29fa0aba" } ], "github": { "repo": "vercel/ai", "checkedAt": "2026-11-09T09:55:49.824362486Z", "stars": 27827, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-09T02:57:28Z", "openIssues": 480, "openPRs": 1033, "issuesOpened90d": 1082, "issuesClosed90d": 1417, "prsMerged90d": 2739, "ci": { "branch": "main", "runs": 50, "success": 50, "failure": 0, "other": 0, "latest": "success", "latestAt": "2026-11-09T02:56:36Z" }, "advisories": [ { "ghsa": "GHSA-g3x3-7q3h-gmhj", "severity": "medium", "published": "2026-10-01T19:22:11Z" }, { "ghsa": "GHSA-4mqq-99j3-3hmv", "severity": "high", "published": "2026-09-28T17:44:55Z" }, { "ghsa": "GHSA-222v-gj5h-ff73", "severity": "high", "published": "2026-08-20T21:21:04Z" }, { "ghsa": "GHSA-vmqp-7rwf-cq3w", "severity": "medium", "published": "2026-08-14T01:39:36Z" }, { "ghsa": "GHSA-qw9h-448j-6rph", "cve": "CVE-2026-64650", "severity": "medium", "published": "2026-07-20T20:16:06Z" }, { "ghsa": "GHSA-g48p-5rr5-8rgq", "cve": "CVE-2026-64651", "severity": "medium", "published": "2026-07-20T20:15:50Z" } ], "replies": { "sampled": 25, "unanswered": 12, "medianDays": 0.8 } }, "updatedAt": "2026-11-09T20:50:22.433276589Z" }, "streak": { "days": 4, "from": "2026-11-05", "last": { "kind": "shutdown", "date": "2026-11-05", "what": "`spacexai/grok-voice-think-fast-2.0` is retired from AI Gateway (`deprecated_at` in the model list)", "source": "https://ai-gateway.vercel.sh/v1/models" }, "next": { "kind": "shutdown", "date": "2026-11-13", "what": "`poolside/laguna-s-2.1` is retired from AI Gateway (`deprecated_at` in the model list)", "source": "https://ai-gateway.vercel.sh/v1/models" }, "best": 14 } }, "edges": [ { "by": 39, "category": "reliability", "leads": "vercel-ai-gateway", "name": "Reliability", "reasons": { "a": "Model reading, for the surface it's called on, Meta Model API. No status page with readable history, per the meta-model-api listing's 4 November check (0), so no readable incident history (5). Rate limits published per team and per model, 3,000 RPM and 4,000,000 TPM for muse-ember-1.0, read 9 November (15). 429 and 503 with Retry-After, backoff guidance and rate-limit headers, per the meta-model-api listing (15). No SLA found (0). Muse Ember carries no preview label, but the API opened as a public preview in July and no general-availability notice was found, so half, as for the platform (5). 0 + 5 + 15 + 15 + 0 + 5 = 40.", "b": "Hosted reading. AI Gateway is a component on www.vercel-status.com (20). The history feed, re-read on 1 November 2026, has 25 entries from 23 July to 23 October, so it covers the whole 90 days from 3 August. None names AI Gateway in its title or text. The Drains, Logs and Observability incidents (6, 17 and 20 August, 16 to 17 September, 10 October in Washington, which names delayed logs, metrics and traces in general, and 23 October) name no AI Gateway surface, and none reports requests failing. Component tags sit in the status API, which robots.txt disallows, so they were not used. A readable page that posts incidents, none touching the product, is a clean record, as vercel-connect's incidents were read from the same feed (30). The rate-limit page, re-read on 1 November, says it describes behaviour rather than fixed numbers. The paid tier has no gateway limit, and the free tier's per-model limits are not published (5 of 15). A 429 has a documented JSON body, some carry `retry-after`, the docs give backoff code and separate a 429 from a 402 budget rejection, and failed provider attempts are retried on other providers (14 of 15). The Enterprise SLA excludes the APIs and CLI, and no SLA naming AI Gateway was found (0). Generally available since 21 August 2025. Token Pass is early access and the Python SDK is in beta (10)." }, "scores": { "a": 40, "b": 79 } }, { "by": 33, "category": "maintenance", "leads": "vercel-ai-gateway", "name": "Maintenance \u0026 community", "reasons": { "a": "Model reading. Released 9 November 2026 (30). No deprecation policy or notice period found, per the platform reading (0 of 12). Dated launches on the API, the latest Muse Wonder on 12 October and Muse Ember on 9 November (8 of 8). No Model API changelog; a help centre with tickets (8 of 15). No SDK of Meta's own (0 of 15, 0 of 10). 30 + 0 + 8 + 8 + 0 = 46.", "b": "Closed service, read on the model lines. The newest changelog entry naming AI Gateway is dated 30 October 2026 (30). Twelve models in the model list carry a `deprecated_at` date on 1 November, from 5 November 2026 (4 days ahead) to 26 February 2027. No minimum notice period was found, and access to Claude Fable 5 was suspended on 12 June 2026 under a government directive without notice and restored on 1 July (6 of 12). No AI Gateway endpoint was shut down in the last 90 days that we found (7 of 8). 95 changelog entries name AI Gateway from 3 August to 30 October 2026, and support runs from the dashboard (13 of 15). Replies to issues on vercel/ai were not read, because GitHub's pages refuse our reader (3 of 10). `@ai-sdk/gateway` is at 4.0.132 in vercel/ai, versioned on 30 October 2026, and had 29,597,661 npm downloads in the week to 12 October per the 17 October check. The Python SDK is in beta (14 of 15). Three runtime dependencies and a test file beside most modules. CI was not checked (6 of 10)." }, "scores": { "a": 46, "b": 79 } }, { "by": 18, "category": "transparency", "leads": "vercel-ai-gateway", "name": "Transparency \u0026 trust", "reasons": { "a": "Editorial half. Closed model under the Model API terms, with clear terms and law; no weights and no parameter count, unlike Muse Spark Open and Muse Glimmer (15). Standard content isn't used for training, retention periods not stated outside zero retention (18 of 30). No deprecation policy or dated notices (0). A subprocessor list linked but not read, no data locations (8 of 20). 15 + 18 + 0 + 8 = 41.", "b": "Closed service under the Terms of Service last updated 19 October 2026, the AI Product Terms with an AI Gateway section, and Token Pass terms on its docs page. Routed models carry the terms of 64 providers listed in the Notices and Licence Information, and the SDK is Apache-2.0 (18 of 30). The FAQ, the ZDR page and the logs page agree that prompt and response content is not kept. The terms place content sent to providers under the providers' own terms, give the no-training warranty only to Enterprise and bar sensitive personal information in Input. The DPA covers Pro and Enterprise, not Hobby, and the privacy notice gives retention criteria, not periods (17 of 30). No deprecation policy found. Model retirements carry dates in the model list, and the AI Product Terms let Vercel change fees, change or end anything in beta without notice, and end Token Pass with a pro-rata refund (8 of 20). Provider terms are listed per provider and regional inference names four regions, while the gateway itself may process a request in any Vercel region. The subprocessor list on security.vercel.com was not read (12 of 20)." }, "scores": { "a": 53, "b": 71 } }, { "by": 15, "category": "security", "leads": "vercel-ai-gateway", "name": "Security \u0026 auth", "reasons": { "a": "Platform readings are the meta-model-api listing's of 4 November. Team keys, named, revocable, no scopes (20 of 30). Standard mode only, so content isn't used to train Meta models under the terms, with safety use reserved (17 of 20). Retention 'as needed' with zero retention through sales (10 of 15). Usage dashboard by model, no per-call log (5 of 15). No security.txt on dev.meta.ai, a bug bounty and a security commitments page, no named certification (12 of 20). 20 + 17 + 10 + 5 + 12 = 64.", "b": "Router, read on the model lines. AI Gateway API keys belong to a team, can be limited to one project and given an expiry and a budget, are deactivated when their creator leaves the team, and can be revoked without authentication by reporting a leaked key. Keys carry no per-model or read-only scope apart from the Token Pass key type. On Vercel, project OIDC tokens replace long-lived keys (24 of 30). Vercel says it does not train on prompts, and the AI Product Terms make that a warranty only for Enterprise subscriptions. Provider training is filtered only when `disallowPromptTraining` or ZDR is set, the filter does not apply to BYOK, and the terms say Stealth Model providers may train on inputs (12 of 20). The gateway does not keep prompt or response content. Provider ZDR is free per request on Pro and Enterprise and not available on Hobby, and BYOK keys are skipped under ZDR unless marked (12 of 15). Per-request logs record status, provider attempts, tokens, cost and authentication method, with routing details kept 30 days and Trace Drains and spend reports on paid plans (13 of 15). Valid security.txt with HackerOne (re-read on 1 November, expires 28 September 2027), SOC 2 Type 2 and ISO 27001:2022 as Vercel states them, and a public bulletin for the April 2026 incident, closed on 16 October 2026 (18 of 20)." }, "scores": { "a": 64, "b": 79 } }, { "by": 14, "category": "schema", "leads": "vercel-ai-gateway", "name": "Schema \u0026 documentation", "reasons": { "a": "Model reading. No OpenAPI file; the Markdown reference is the contract, per the meta-model-api listing (0). llms.txt and Markdown copies of every page (10). The Muse Ember page and choose-a-model page say what to hand it and what not to (hard single-shot coding, knowledge-heavy questions, visual coding), with model ID, inputs, context, max output and effort range (18 of 20). JSON Schema tools and output, reasoning effort an enum, per the platform reading (12 of 15). Curl, Python and TypeScript examples and the platform's error guide (15). A versioned model ID and a dated launch post, with no API changelog (5 of 15). 0 + 10 + 18 + 12 + 15 + 5 = 60.", "b": "Router, scored on the API lines. Vercel's OpenAPI 3.0.3 document has AI Gateway management paths (budgets, routing rules, virtual model configs, routers) and `POST /api-keys`. It does not cover the inference routes on ai-gateway.vercel.sh or `/v1/models`, `/v1/credits`, `/v1/generation` and `/v1/report`, which follow the OpenAI and Anthropic formats and the REST reference page (12 of 25). Every docs page is served as Markdown, and vercel.com/llms.txt lists AI Gateway and the keyless model list (10). The docs say when to use AI Gateway, which API format suits which client, and what each control leaves out, such as BYOK spend outside budgets (16 of 20). `providerOptions.gateway` fields are documented in tables with types, and the model list names each model's supported parameters. The request bodies have no published schema of their own (9 of 15). cURL, TypeScript and Python examples on most pages, and error tables in the FAQ, the REST reference and the Token Pass pages. The Chat Completions error list omits 402 (13 of 15). Paths carry `/v1`, the changelog is dated, with 95 entries naming AI Gateway from 3 August to 30 October 2026, and `@ai-sdk/gateway` keeps a CHANGELOG. The changelog sitemap dates one AI Gateway entry to 25 March 2025, before the alpha (14 of 15)." }, "scores": { "a": 60, "b": 74 } }, { "by": 11, "category": "ergonomics", "leads": "vercel-ai-gateway", "name": "Agent ergonomics", "reasons": { "a": "Model reading. Tool calls, parallel calls, computer use and search grounding, with tool_choice limited to auto per the platform reading (15 of 20). Strict structured output (15). Automatic prompt caching, cached input at 4% of the input price (15). A 1,048,576-token context, but requests over 200K input tokens bill at three times the rate for the whole request (12 of 15). No batch endpoint (0). No SDK of Meta's own; OpenAI and Anthropic SDKs against compatible endpoints (0). OpenAI-style errors with fixes and retryable codes (15). 15 + 15 + 15 + 12 + 0 + 0 + 15 = 72.", "b": "Router, read on the model lines. Tool calling is documented on all six surfaces and 303 of 498 models carry the tool-use tag on 1 November, with behaviour depending on the model routed (16 of 20). Structured output is documented per surface and tagged on 278 models (13 of 15). `caching: 'auto'` adds Anthropic cache markers, `cache_ttl` asks for one-hour entries, `x-session-affinity` keeps a conversation on one provider, and cache-read prices are listed per model (14 of 15). 162 models list a context of one million tokens or more, a judgement call since a router has no default model (15). The SDK source has a `gateway-batch.ts` file, but no batch endpoint or batch discount was found in the docs (2 of 10). The AI SDK for TypeScript, the AI SDK for Python in beta, and the OpenAI and Anthropic SDKs with a changed base URL (10). Errors return `message` and `type`, an exceeded budget answers 402 apart from a 429, the SDK has ten typed `Gateway*Error` classes, and the FAQ maps each status to a fix (13 of 15)." }, "scores": { "a": 72, "b": 83 } } ], "facts": [ { "a": "Model API", "b": "Model router", "name": "Kind" }, { "a": "Meta", "b": "Vercel Inc.", "name": "Vendor" }, { "a": "https://api.meta.ai/v1", "b": "https://ai-gateway.vercel.sh/v1", "name": "Hosted endpoint" }, { "a": "", "b": "HTTP", "name": "Transports" }, { "a": "API key", "b": "OAuth or key", "name": "Auth" }, { "a": "Pay per use", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Closed model, used through Meta Model API and Muse Code under the Meta Model API Terms of Service (last updated 9 October 2026). No open weights; Meta's open-weight models are Muse Spark Open and Muse Glimmer", "b": "Proprietary service under Vercel's Terms of Service and AI Product Terms, with Token Pass terms on its docs page. Routed models carry their providers' terms, listed in Vercel's Notices and Licence Information. The `@ai-sdk/gateway` provider is Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-11-09", "b": "2026-10-30", "name": "Last release" }, { "a": "2026-10-02", "b": "2026-06-01", "name": "Terms last updated" }, { "a": "couldn't be read", "b": "2026-06-01", "name": "Privacy policy last updated" }, { "a": "yes", "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": "yes", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "29.6M npm/wk", "name": "Popularity" }, { "a": "none", "b": "3/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Vercel AI Gateway scores 67.8 (B) on agent readiness against Muse Ember's 51.8 (D), and leads in 6 of 7 scored categories.", "question": "Which is better for AI agents, Muse Ember or Vercel AI Gateway?" }, { "answer": "Muse Ember needs an API key. Vercel AI Gateway takes an API key or an OAuth sign-in.", "question": "Do Muse Ember and Vercel AI Gateway need an API key?" }, { "answer": "Yes. Muse Ember has a hosted endpoint at https://api.meta.ai/v1 and Vercel AI Gateway at https://ai-gateway.vercel.sh/v1.", "question": "Can an agent call Muse Ember and Vercel AI Gateway without installing anything?" } ], "goodFor": [ { "aheadOn": null, "also": [ "No incidents deducted, where Vercel AI Gateway loses 3 points for them" ], "goodFor": "Agents that hand out many small, bounded tasks (sub-agents, tool loops, routing, extraction over thousands of files) and want a cheap multimodal model with a 1M context behind the same API as a bigger Muse model.", "slug": "muse-ember", "watchFor": "No weights and no parameter count published, so it can't be run locally" }, { "aheadOn": [ "Reliability, 79 against 40", "Schema \u0026 documentation, 74 against 60", "Agent ergonomics, 83 against 72", "Security \u0026 auth, 79 against 64", "Maintenance \u0026 community, 79 against 46", "Transparency \u0026 trust, 71 against 53" ], "also": null, "goodFor": "Teams that want one key, one bill, budgets and failover in front of many model providers, especially on Vercel with OIDC.", "slug": "vercel-ai-gateway", "watchFor": "The free monthly credit needs a valid payment method on the team, and its amount is not stated in the reviewed docs" } ], "history": { "muse-ember": null, "vercel-ai-gateway": [ { "causes": [ "correction" ], "date": "2026-11-01", "delta": 1, "from": 66.8, "fromGrade": "B", "to": 67.8, "toGrade": "B" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 66.7, "fromGrade": "B", "to": 66.8, "toGrade": "B" } ] }, "job": { "capability": "inference.llm", "name": "LLM inference" }, "others": [ { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-muse-ember.json", "title": "Amazon Bedrock vs Muse Ember", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-vercel-ai-gateway.json", "title": "Amazon Bedrock vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-muse-ember.json", "title": "Claude API vs Muse Ember", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-vercel-ai-gateway.json", "title": "Claude API vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/antseed-vs-muse-ember.json", "title": "Antseed vs Muse Ember", "url": "https://www.anchorterminal.com/compare/antseed-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-muse-ember.json", "title": "Azure OpenAI in Foundry Models vs Muse Ember", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-vercel-ai-gateway.json", "title": "Azure OpenAI in Foundry Models vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-muse-ember.json", "title": "BlockRun.AI vs Muse Ember", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-vercel-ai-gateway.json", "title": "BlockRun.AI vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/cerebras-inference-vs-muse-ember.json", "title": "Cerebras Inference vs Muse Ember", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/cerebras-inference-vs-vercel-ai-gateway.json", "title": "Cerebras Inference vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-muse-ember.json", "title": "Cloudflare AI Gateway vs Muse Ember", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-vercel-ai-gateway.json", "title": "Cloudflare AI Gateway vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-muse-ember.json", "title": "Cloudflare Workers AI vs Muse Ember", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-vercel-ai-gateway.json", "title": "Cloudflare Workers AI vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-muse-ember.json", "title": "Cohere Chat API (Command models) vs Muse Ember", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-vercel-ai-gateway.json", "title": "Cohere Chat API (Command models) vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/deepinfra-vs-muse-ember.json", "title": "DeepInfra vs Muse Ember", "url": "https://www.anchorterminal.com/compare/deepinfra-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/deepinfra-vs-vercel-ai-gateway.json", "title": "DeepInfra vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/deepinfra-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/deepseek-api-vs-muse-ember.json", "title": "DeepSeek API vs Muse Ember", "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/deepseek-api-vs-vercel-ai-gateway.json", "title": "DeepSeek API vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/eden-ai-vs-muse-ember.json", "title": "Eden AI vs Muse Ember", "url": "https://www.anchorterminal.com/compare/eden-ai-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-muse-ember.json", "title": "Glimpse vs Muse Ember", "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-vercel-ai-gateway.json", "title": "Glimpse vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-muse-ember.json", "title": "Fireworks AI Inference vs Muse Ember", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-vercel-ai-gateway.json", "title": "Fireworks AI Inference vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/gemini-api-vs-muse-ember.json", "title": "Gemini Developer API vs Muse Ember", "url": "https://www.anchorterminal.com/compare/gemini-api-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/gemini-api-vs-vercel-ai-gateway.json", "title": "Gemini Developer API vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/gemini-api-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/groq-vs-muse-ember.json", "title": "GroqCloud vs Muse Ember", "url": "https://www.anchorterminal.com/compare/groq-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/groq-vs-vercel-ai-gateway.json", "title": "GroqCloud vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/groq-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-muse-ember.json", "title": "Hugging Face Inference Providers vs Muse Ember", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-ember.json", "title": "Inkling 2 Small vs Muse Ember", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-vercel-ai-gateway.json", "title": "Inkling 2 Small vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-muse-ember.json", "title": "Jais 3 vs Muse Ember", "url": "https://www.anchorterminal.com/compare/jais-3-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-vercel-ai-gateway.json", "title": "Jais 3 vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/jais-3-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-muse-ember.json", "title": "Meta Model API vs Muse Ember", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-vercel-ai-gateway.json", "title": "Meta Model API vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/minimax-api-vs-muse-ember.json", "title": "MiniMax API vs Muse Ember", "url": "https://www.anchorterminal.com/compare/minimax-api-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/minimax-api-vs-vercel-ai-gateway.json", "title": "MiniMax API vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/minimax-api-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-muse-ember.json", "title": "Mistral AI API vs Muse Ember", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-muse-ember" }, { "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/muse-ember-vs-muse-spark-open.json", "title": "Muse Ember vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-muse-spark-open" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-nemotron-3-5-super-vl.json", "title": "Muse Ember vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-novita-ai.json", "title": "Muse Ember vs Novita AI", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-novita-ai" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-openai-api.json", "title": "Muse Ember vs OpenAI API", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-openai-api" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-openrouter.json", "title": "Muse Ember vs OpenRouter", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-openrouter" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-prism-inference.json", "title": "Muse Ember vs Prism Inference", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-ramp-router.json", "title": "Muse Ember vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-reflection-beam.json", "title": "Muse Ember vs Beam 1.0", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-reflection-beam" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-routerplus.json", "title": "Muse Ember vs RouterPlus", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-routerplus" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-sambanova.json", "title": "Muse Ember vs SambaCloud", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-sambanova" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-siliconflow.json", "title": "Muse Ember vs SiliconFlow", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-siliconflow" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-simplismart.json", "title": "Muse Ember vs Simplismart", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-simplismart" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-stepfun-api.json", "title": "Muse Ember vs StepFun API", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-stepfun-api" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-swe-2-flash.json", "title": "Muse Ember vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-tencent-tokenhub.json", "title": "Muse Ember vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-together-inference.json", "title": "Muse Ember vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-together-inference" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-vertex-ai.json", "title": "Muse Ember vs Vertex AI (Gemini Enterprise Agent Platform)", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-vertex-ai" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-xai-api.json", "title": "Muse Ember vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-vercel-ai-gateway.json", "title": "Muse Spark Open vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-vercel-ai-gateway.json", "title": "Nemotron 3.5 Super VL vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/novita-ai-vs-vercel-ai-gateway.json", "title": "Novita AI vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/novita-ai-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/openai-api-vs-vercel-ai-gateway.json", "title": "OpenAI API vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/openai-api-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/openrouter-vs-vercel-ai-gateway.json", "title": "OpenRouter vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/openrouter-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/reflection-beam-vs-vercel-ai-gateway.json", "title": "Beam 1.0 vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/reflection-beam-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/sambanova-vs-vercel-ai-gateway.json", "title": "SambaCloud vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/sambanova-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/siliconflow-vs-vercel-ai-gateway.json", "title": "SiliconFlow vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/siliconflow-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/simplismart-vs-vercel-ai-gateway.json", "title": "Simplismart vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/simplismart-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/stepfun-api-vs-vercel-ai-gateway.json", "title": "StepFun API vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/stepfun-api-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/swe-2-flash-vs-vercel-ai-gateway.json", "title": "SWE-2 Flash vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/swe-2-flash-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/together-inference-vs-vercel-ai-gateway.json", "title": "Together AI Inference vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/together-inference-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/vercel-ai-gateway-vs-vertex-ai.json", "title": "Vercel AI Gateway vs Vertex AI (Gemini Enterprise Agent Platform)", "url": "https://www.anchorterminal.com/compare/vercel-ai-gateway-vs-vertex-ai" }, { "json": "https://www.anchorterminal.com/compare/vercel-ai-gateway-vs-xai-api.json", "title": "Vercel AI Gateway vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/vercel-ai-gateway-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/antseed-vs-vercel-ai-gateway.json", "title": "Antseed vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/antseed-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/eden-ai-vs-vercel-ai-gateway.json", "title": "Eden AI vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/eden-ai-vs-vercel-ai-gateway" }, { "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/litellm-vs-vercel-ai-gateway.json", "title": "LiteLLM vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/litellm-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/ramp-router-vs-vercel-ai-gateway.json", "title": "Router.com (Ramp Router) vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/ramp-router-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/routerplus-vs-vercel-ai-gateway.json", "title": "RouterPlus vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/routerplus-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/tencent-tokenhub-vs-vercel-ai-gateway.json", "title": "Tencent Cloud TokenHub vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/tencent-tokenhub-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/prism-inference-vs-vercel-ai-gateway.json", "title": "Prism Inference vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/prism-inference-vs-vercel-ai-gateway" } ], "panel": null, "scores": [ { "by": 39, "edge": "vercel-ai-gateway", "key": "reliability", "muse-ember": 40, "name": "Reliability", "vercel-ai-gateway": 79, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 14, "edge": "vercel-ai-gateway", "key": "schema", "muse-ember": 60, "name": "Schema \u0026 documentation", "vercel-ai-gateway": 74, "weight": 13 }, { "by": 11, "edge": "vercel-ai-gateway", "key": "ergonomics", "muse-ember": 72, "name": "Agent ergonomics", "vercel-ai-gateway": 83, "weight": 13 }, { "by": 15, "edge": "vercel-ai-gateway", "key": "security", "muse-ember": 64, "name": "Security \u0026 auth", "vercel-ai-gateway": 79, "weight": 14 }, { "by": 0, "edge": "", "key": "payments", "muse-ember": 20, "name": "Payments \u0026 pricing", "vercel-ai-gateway": 20, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 33, "edge": "vercel-ai-gateway", "key": "maintenance", "muse-ember": 46, "name": "Maintenance \u0026 community", "vercel-ai-gateway": 79, "weight": 7 }, { "by": 18, "edge": "vercel-ai-gateway", "key": "transparency", "muse-ember": 53, "name": "Transparency \u0026 trust", "vercel-ai-gateway": 71, "weight": 7 } ], "summary": "Vercel AI Gateway scores 67.8 (B) on agent readiness against Muse Ember's 51.8 (D), and leads in 6 of 7 scored categories. Both do llm inference.", "tasks": null, "tutorials": [], "verdicts": { "muse-ember": "A cheap, capable model for the repeated parts of agent work, at $0.10 and $0.50 per million tokens with a 1M context and Meta's figures putting it level with Claude Haiku 5.5 on fewer tokens. Launched today on an API with no readable status page, SLA or deprecation policy, and closed, with no weights.", "vercel-ai-gateway": "Token prices pass through with no markup, prompts are not stored by the gateway, and budgets, provider failover and per-request logs are built in. The free monthly credit needs a card on file, rate limits are not published as numbers, no SLA covers the API, and the contractual promise not to train on content applies to Enterprise subscriptions only." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/muse-ember-vs-vercel-ai-gateway", "json": "https://www.anchorterminal.com/compare/muse-ember-vs-vercel-ai-gateway.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/muse-ember-vs-vercel-ai-gateway.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/muse-ember-vs-vercel-ai-gateway.min.md" }, "markdown": "Vercel AI Gateway scores 67.8 (B) on agent readiness against Muse Ember's 51.8 (D), and leads in 6 of 7 scored categories. Both do llm inference.\n\n- Muse Ember: grade D, 51.8/100, rank #1017 of 1515. Markdown https://www.anchorterminal.com/tools/muse-ember.md · JSON https://www.anchorterminal.com/api/v1/tools/muse-ember.json\n- Vercel AI Gateway: grade B, 67.8/100, rank #303 of 1515. Markdown https://www.anchorterminal.com/tools/vercel-ai-gateway.md · JSON https://www.anchorterminal.com/api/v1/tools/vercel-ai-gateway.json\n- Best model APIs and inference for AI agents: https://www.anchorterminal.com/best/inference/index.md\n- All 871 models comparisons: https://www.anchorterminal.com/compare/inference/index.md\n\n## Which one, for what\n\n### Muse Ember (D)\n\nGood for: Agents that hand out many small, bounded tasks (sub-agents, tool loops, routing, extraction over thousands of files) and want a cheap multimodal model with a 1M context behind the same API as a bigger Muse model.\n\nAlso in its favour:\n- No incidents deducted, where Vercel AI Gateway loses 3 points for them\n\nWatch for: No weights and no parameter count published, so it can't be run locally\n\n### Vercel AI Gateway (B)\n\nGood for: Teams that want one key, one bill, budgets and failover in front of many model providers, especially on Vercel with OIDC.\n\nAhead on:\n- Reliability, 79 against 40\n- Schema \u0026 documentation, 74 against 60\n- Agent ergonomics, 83 against 72\n- Security \u0026 auth, 79 against 64\n- Maintenance \u0026 community, 79 against 46\n- Transparency \u0026 trust, 71 against 53\n\nWatch for: The free monthly credit needs a valid payment method on the team, and its amount is not stated in the reviewed docs\n\n\n## Why the edge\n\n### Reliability: Vercel AI Gateway +39\n\n- Muse Ember (40): Model reading, for the surface it's called on, Meta Model API. No status page with readable history, per the meta-model-api listing's 4 November check (0), so no readable incident history (5). Rate limits published per team and per model, 3,000 RPM and 4,000,000 TPM for muse-ember-1.0, read 9 November (15). 429 and 503 with Retry-After, backoff guidance and rate-limit headers, per the meta-model-api listing (15). No SLA found (0). Muse Ember carries no preview label, but the API opened as a public preview in July and no general-availability notice was found, so half, as for the platform (5). 0 + 5 + 15 + 15 + 0 + 5 = 40.\n- Vercel AI Gateway (79): Hosted reading. AI Gateway is a component on www.vercel-status.com (20). The history feed, re-read on 1 November 2026, has 25 entries from 23 July to 23 October, so it covers the whole 90 days from 3 August. None names AI Gateway in its title or text. The Drains, Logs and Observability incidents (6, 17 and 20 August, 16 to 17 September, 10 October in Washington, which names delayed logs, metrics and traces in general, and 23 October) name no AI Gateway surface, and none reports requests failing. Component tags sit in the status API, which robots.txt disallows, so they were not used. A readable page that posts incidents, none touching the product, is a clean record, as vercel-connect's incidents were read from the same feed (30). The rate-limit page, re-read on 1 November, says it describes behaviour rather than fixed numbers. The paid tier has no gateway limit, and the free tier's per-model limits are not published (5 of 15). A 429 has a documented JSON body, some carry `retry-after`, the docs give backoff code and separate a 429 from a 402 budget rejection, and failed provider attempts are retried on other providers (14 of 15). The Enterprise SLA excludes the APIs and CLI, and no SLA naming AI Gateway was found (0). Generally available since 21 August 2025. Token Pass is early access and the Python SDK is in beta (10).\n\n### Maintenance \u0026 community: Vercel AI Gateway +33\n\n- Muse Ember (46): Model reading. Released 9 November 2026 (30). No deprecation policy or notice period found, per the platform reading (0 of 12). Dated launches on the API, the latest Muse Wonder on 12 October and Muse Ember on 9 November (8 of 8). No Model API changelog; a help centre with tickets (8 of 15). No SDK of Meta's own (0 of 15, 0 of 10). 30 + 0 + 8 + 8 + 0 = 46.\n- Vercel AI Gateway (79): Closed service, read on the model lines. The newest changelog entry naming AI Gateway is dated 30 October 2026 (30). Twelve models in the model list carry a `deprecated_at` date on 1 November, from 5 November 2026 (4 days ahead) to 26 February 2027. No minimum notice period was found, and access to Claude Fable 5 was suspended on 12 June 2026 under a government directive without notice and restored on 1 July (6 of 12). No AI Gateway endpoint was shut down in the last 90 days that we found (7 of 8). 95 changelog entries name AI Gateway from 3 August to 30 October 2026, and support runs from the dashboard (13 of 15). Replies to issues on vercel/ai were not read, because GitHub's pages refuse our reader (3 of 10). `@ai-sdk/gateway` is at 4.0.132 in vercel/ai, versioned on 30 October 2026, and had 29,597,661 npm downloads in the week to 12 October per the 17 October check. The Python SDK is in beta (14 of 15). Three runtime dependencies and a test file beside most modules. CI was not checked (6 of 10).\n\n### Transparency \u0026 trust: Vercel AI Gateway +18\n\n- Muse Ember (53): Editorial half. Closed model under the Model API terms, with clear terms and law; no weights and no parameter count, unlike Muse Spark Open and Muse Glimmer (15). Standard content isn't used for training, retention periods not stated outside zero retention (18 of 30). No deprecation policy or dated notices (0). A subprocessor list linked but not read, no data locations (8 of 20). 15 + 18 + 0 + 8 = 41.\n- Vercel AI Gateway (71): Closed service under the Terms of Service last updated 19 October 2026, the AI Product Terms with an AI Gateway section, and Token Pass terms on its docs page. Routed models carry the terms of 64 providers listed in the Notices and Licence Information, and the SDK is Apache-2.0 (18 of 30). The FAQ, the ZDR page and the logs page agree that prompt and response content is not kept. The terms place content sent to providers under the providers' own terms, give the no-training warranty only to Enterprise and bar sensitive personal information in Input. The DPA covers Pro and Enterprise, not Hobby, and the privacy notice gives retention criteria, not periods (17 of 30). No deprecation policy found. Model retirements carry dates in the model list, and the AI Product Terms let Vercel change fees, change or end anything in beta without notice, and end Token Pass with a pro-rata refund (8 of 20). Provider terms are listed per provider and regional inference names four regions, while the gateway itself may process a request in any Vercel region. The subprocessor list on security.vercel.com was not read (12 of 20).\n\n### Security \u0026 auth: Vercel AI Gateway +15\n\n- Muse Ember (64): Platform readings are the meta-model-api listing's of 4 November. Team keys, named, revocable, no scopes (20 of 30). Standard mode only, so content isn't used to train Meta models under the terms, with safety use reserved (17 of 20). Retention 'as needed' with zero retention through sales (10 of 15). Usage dashboard by model, no per-call log (5 of 15). No security.txt on dev.meta.ai, a bug bounty and a security commitments page, no named certification (12 of 20). 20 + 17 + 10 + 5 + 12 = 64.\n- Vercel AI Gateway (79): Router, read on the model lines. AI Gateway API keys belong to a team, can be limited to one project and given an expiry and a budget, are deactivated when their creator leaves the team, and can be revoked without authentication by reporting a leaked key. Keys carry no per-model or read-only scope apart from the Token Pass key type. On Vercel, project OIDC tokens replace long-lived keys (24 of 30). Vercel says it does not train on prompts, and the AI Product Terms make that a warranty only for Enterprise subscriptions. Provider training is filtered only when `disallowPromptTraining` or ZDR is set, the filter does not apply to BYOK, and the terms say Stealth Model providers may train on inputs (12 of 20). The gateway does not keep prompt or response content. Provider ZDR is free per request on Pro and Enterprise and not available on Hobby, and BYOK keys are skipped under ZDR unless marked (12 of 15). Per-request logs record status, provider attempts, tokens, cost and authentication method, with routing details kept 30 days and Trace Drains and spend reports on paid plans (13 of 15). Valid security.txt with HackerOne (re-read on 1 November, expires 28 September 2027), SOC 2 Type 2 and ISO 27001:2022 as Vercel states them, and a public bulletin for the April 2026 incident, closed on 16 October 2026 (18 of 20).\n\n### Schema \u0026 documentation: Vercel AI Gateway +14\n\n- Muse Ember (60): Model reading. No OpenAPI file; the Markdown reference is the contract, per the meta-model-api listing (0). llms.txt and Markdown copies of every page (10). The Muse Ember page and choose-a-model page say what to hand it and what not to (hard single-shot coding, knowledge-heavy questions, visual coding), with model ID, inputs, context, max output and effort range (18 of 20). JSON Schema tools and output, reasoning effort an enum, per the platform reading (12 of 15). Curl, Python and TypeScript examples and the platform's error guide (15). A versioned model ID and a dated launch post, with no API changelog (5 of 15). 0 + 10 + 18 + 12 + 15 + 5 = 60.\n- Vercel AI Gateway (74): Router, scored on the API lines. Vercel's OpenAPI 3.0.3 document has AI Gateway management paths (budgets, routing rules, virtual model configs, routers) and `POST /api-keys`. It does not cover the inference routes on ai-gateway.vercel.sh or `/v1/models`, `/v1/credits`, `/v1/generation` and `/v1/report`, which follow the OpenAI and Anthropic formats and the REST reference page (12 of 25). Every docs page is served as Markdown, and vercel.com/llms.txt lists AI Gateway and the keyless model list (10). The docs say when to use AI Gateway, which API format suits which client, and what each control leaves out, such as BYOK spend outside budgets (16 of 20). `providerOptions.gateway` fields are documented in tables with types, and the model list names each model's supported parameters. The request bodies have no published schema of their own (9 of 15). cURL, TypeScript and Python examples on most pages, and error tables in the FAQ, the REST reference and the Token Pass pages. The Chat Completions error list omits 402 (13 of 15). Paths carry `/v1`, the changelog is dated, with 95 entries naming AI Gateway from 3 August to 30 October 2026, and `@ai-sdk/gateway` keeps a CHANGELOG. The changelog sitemap dates one AI Gateway entry to 25 March 2025, before the alpha (14 of 15).\n\n### Agent ergonomics: Vercel AI Gateway +11\n\n- Muse Ember (72): Model reading. Tool calls, parallel calls, computer use and search grounding, with tool_choice limited to auto per the platform reading (15 of 20). Strict structured output (15). Automatic prompt caching, cached input at 4% of the input price (15). A 1,048,576-token context, but requests over 200K input tokens bill at three times the rate for the whole request (12 of 15). No batch endpoint (0). No SDK of Meta's own; OpenAI and Anthropic SDKs against compatible endpoints (0). OpenAI-style errors with fixes and retryable codes (15). 15 + 15 + 15 + 12 + 0 + 0 + 15 = 72.\n- Vercel AI Gateway (83): Router, read on the model lines. Tool calling is documented on all six surfaces and 303 of 498 models carry the tool-use tag on 1 November, with behaviour depending on the model routed (16 of 20). Structured output is documented per surface and tagged on 278 models (13 of 15). `caching: 'auto'` adds Anthropic cache markers, `cache_ttl` asks for one-hour entries, `x-session-affinity` keeps a conversation on one provider, and cache-read prices are listed per model (14 of 15). 162 models list a context of one million tokens or more, a judgement call since a router has no default model (15). The SDK source has a `gateway-batch.ts` file, but no batch endpoint or batch discount was found in the docs (2 of 10). The AI SDK for TypeScript, the AI SDK for Python in beta, and the OpenAI and Anthropic SDKs with a changed base URL (10). Errors return `message` and `type`, an exceeded budget answers 402 apart from a 429, the SDK has ten typed `Gateway*Error` classes, and the FAQ maps each status to a fix (13 of 15).\n\n## Score by category\n\n| Category | Weight | Muse Ember | Vercel AI Gateway | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 40 | 79 | Vercel AI Gateway +39 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 60 | 74 | Vercel AI Gateway +14 |\n| Agent ergonomics | 13% (16.2 this run) | 72 | 83 | Vercel AI Gateway +11 |\n| Security \u0026 auth | 14% (17.5 this run) | 64 | 79 | Vercel AI Gateway +15 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 20 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 46 | 79 | Vercel AI Gateway +33 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 53 | 71 | Vercel AI Gateway +18 |\n| Negative events | ≤15 | 0 | -3 | |\n| **Total** | | **51.8 · D** | **67.8 · B** | |\n\n## Facts side by side\n\n| Fact | Muse Ember | Vercel AI Gateway |\n| --- | --- | --- |\n| Kind | Model API | Model router |\n| Vendor | Meta | Vercel Inc. |\n| Hosted endpoint | `https://api.meta.ai/v1` | `https://ai-gateway.vercel.sh/v1` |\n| Transports | | HTTP |\n| Auth | API key | OAuth or key |\n| Pricing | Pay per use | Pay per use |\n| x402 | no | no |\n| Licence | Closed model, used through Meta Model API and Muse Code under the Meta Model API Terms of Service (last updated 9 October 2026). No open weights; Meta's open-weight models are Muse Spark Open and Muse Glimmer | Proprietary service under Vercel's Terms of Service and AI Product Terms, with Token Pass terms on its docs page. Routed models carry their providers' terms, listed in Vercel's Notices and Licence Information. The `@ai-sdk/gateway` provider is Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-11-09 | 2026-10-30 |\n| Terms last updated | 2026-10-02 | 2026-06-01 |\n| Privacy policy last updated | couldn't be read | 2026-06-01 |\n| Customer content may train models | yes | yes, with an opt-out |\n| Terms restrict automated access | not found in the text | not found in the text |\n| Terms restrict benchmarking | yes | not found in the text |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | yes | yes |\n| Popularity | none | 29.6M npm/wk |\n| Agent reviews | none | 3/5 (4) |\n\n## How the scores have moved\n\n### Muse Ember\n\nNo score change since it was listed.\n\n### Vercel AI Gateway\n\n- +1.0 on 1 November 2026: correction\n- +0.1 on 27 October 2026: checklist\n\n## Verdicts\n\n**Muse Ember.** A cheap, capable model for the repeated parts of agent work, at $0.10 and $0.50 per million tokens with a 1M context and Meta's figures putting it level with Claude Haiku 5.5 on fewer tokens. Launched today on an API with no readable status page, SLA or deprecation policy, and closed, with no weights.\n\n**Vercel AI Gateway.** Token prices pass through with no markup, prompts are not stored by the gateway, and budgets, provider failover and per-request logs are built in. The free monthly credit needs a card on file, rate limits are not published as numbers, no SLA covers the API, and the contractual promise not to train on content applies to Enterprise subscriptions only.\n\n## Before you call either\n\n### Muse Ember\n\n1. Call https://api.meta.ai/v1/responses (or /chat/completions or /messages) with model muse-ember-1.0 and a bearer MODEL_API_KEY\n2. Set the effort explicitly, reasoning.effort on Responses or reasoning_effort on Chat Completions. It defaults to max, and none isn't accepted; minimal or low suits classification and routing\n3. Keep input under 200K tokens a request, cached tokens and previous_response_id history included, or the whole request bills at the long-context rate\n4. Use it for sub-agents and bounded repeated tasks, and a larger Muse model for the plan, as Meta advises\n5. Use strict structured output for extraction and routing steps\n6. In Claude Code, map the haiku alias and sub-agent model to muse-ember-1.0, per Meta's guide\n\n### Vercel AI Gateway\n\n1. Read `GET https://ai-gateway.vercel.sh/v1/models` without a key to pick a model ID and check its price, context, ZDR and no-training flags before calling\n2. Set `zeroDataRetention` or `disallowPromptTraining` to true in `providerOptions.gateway` on sensitive requests. Default routing ignores provider retention and training policies\n3. Treat a 429 as retryable and honour `retry-after` when present. A 402 with `quota_for_entity_exceeded` is a spent budget, so do not retry it\n4. On a Token Pass key, a 403 with `no_providers_available` means spent credit or a model outside the pass. Retry with a standard AI Gateway key, which bills credits\n5. Set `inferenceRegion` when data residency matters. The default `global` may run inference outside the user's jurisdiction\n\n## Questions\n\n### Which is better for AI agents, Muse Ember or Vercel AI Gateway?\n\nVercel AI Gateway scores 67.8 (B) on agent readiness against Muse Ember's 51.8 (D), and leads in 6 of 7 scored categories.\n\n### Do Muse Ember and Vercel AI Gateway need an API key?\n\nMuse Ember needs an API key. Vercel AI Gateway takes an API key or an OAuth sign-in.\n\n### Can an agent call Muse Ember and Vercel AI Gateway without installing anything?\n\nYes. Muse Ember has a hosted endpoint at https://api.meta.ai/v1 and Vercel AI Gateway at https://ai-gateway.vercel.sh/v1.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/muse-ember-vs-vercel-ai-gateway.json, and with the fewest tokens: https://www.anchorterminal.com/compare/muse-ember-vs-vercel-ai-gateway.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"muse-ember\", \"b\": \"vercel-ai-gateway\"}`. From a terminal: `anchor compare muse-ember vercel-ai-gateway`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/muse-ember.json and https://www.anchorterminal.com/api/v1/tools/vercel-ai-gateway.json\n\n## Other comparisons with Muse Ember or Vercel AI Gateway\n\n- [Amazon Bedrock vs Muse Ember](https://www.anchorterminal.com/compare/amazon-bedrock-vs-muse-ember.md)\n- [Amazon Bedrock vs Vercel AI Gateway](https://www.anchorterminal.com/compare/amazon-bedrock-vs-vercel-ai-gateway.md)\n- [Claude API vs Muse Ember](https://www.anchorterminal.com/compare/anthropic-api-vs-muse-ember.md)\n- [Claude API vs Vercel AI Gateway](https://www.anchorterminal.com/compare/anthropic-api-vs-vercel-ai-gateway.md)\n- [Antseed vs Muse Ember](https://www.anchorterminal.com/compare/antseed-vs-muse-ember.md)\n- [Azure OpenAI in Foundry Models vs Muse Ember](https://www.anchorterminal.com/compare/azure-openai-vs-muse-ember.md)\n- [Azure OpenAI in Foundry Models vs Vercel AI Gateway](https://www.anchorterminal.com/compare/azure-openai-vs-vercel-ai-gateway.md)\n- [BlockRun.AI vs Muse Ember](https://www.anchorterminal.com/compare/blockrun-ai-vs-muse-ember.md)\n- [BlockRun.AI vs Vercel AI Gateway](https://www.anchorterminal.com/compare/blockrun-ai-vs-vercel-ai-gateway.md)\n- [Cerebras Inference vs Muse Ember](https://www.anchorterminal.com/compare/cerebras-inference-vs-muse-ember.md)\n- [Cerebras Inference vs Vercel AI Gateway](https://www.anchorterminal.com/compare/cerebras-inference-vs-vercel-ai-gateway.md)\n- [Cloudflare AI Gateway vs Muse Ember](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-muse-ember.md)\n- [Cloudflare AI Gateway vs Vercel AI Gateway](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-vercel-ai-gateway.md)\n- [Cloudflare Workers AI vs Muse Ember](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-muse-ember.md)\n- [Cloudflare Workers AI vs Vercel AI Gateway](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-vercel-ai-gateway.md)\n- [Cohere Chat API (Command models) vs Muse Ember](https://www.anchorterminal.com/compare/cohere-chat-vs-muse-ember.md)\n- [Cohere Chat API (Command models) vs Vercel AI Gateway](https://www.anchorterminal.com/compare/cohere-chat-vs-vercel-ai-gateway.md)\n- [DeepInfra vs Muse Ember](https://www.anchorterminal.com/compare/deepinfra-vs-muse-ember.md)\n- [DeepInfra vs Vercel AI Gateway](https://www.anchorterminal.com/compare/deepinfra-vs-vercel-ai-gateway.md)\n- [DeepSeek API vs Muse Ember](https://www.anchorterminal.com/compare/deepseek-api-vs-muse-ember.md)\n- [DeepSeek API vs Vercel AI Gateway](https://www.anchorterminal.com/compare/deepseek-api-vs-vercel-ai-gateway.md)\n- [Eden AI vs Muse Ember](https://www.anchorterminal.com/compare/eden-ai-vs-muse-ember.md)\n- [Glimpse vs Muse Ember](https://www.anchorterminal.com/compare/elorian-glimpse-vs-muse-ember.md)\n- [Glimpse vs Vercel AI Gateway](https://www.anchorterminal.com/compare/elorian-glimpse-vs-vercel-ai-gateway.md)\n- [Fireworks AI Inference vs Muse Ember](https://www.anchorterminal.com/compare/fireworks-inference-vs-muse-ember.md)\n- [Fireworks AI Inference vs Vercel AI Gateway](https://www.anchorterminal.com/compare/fireworks-inference-vs-vercel-ai-gateway.md)\n- [Gemini Developer API vs Muse Ember](https://www.anchorterminal.com/compare/gemini-api-vs-muse-ember.md)\n- [Gemini Developer API vs Vercel AI Gateway](https://www.anchorterminal.com/compare/gemini-api-vs-vercel-ai-gateway.md)\n- [GroqCloud vs Muse Ember](https://www.anchorterminal.com/compare/groq-vs-muse-ember.md)\n- [GroqCloud vs Vercel AI Gateway](https://www.anchorterminal.com/compare/groq-vs-vercel-ai-gateway.md)\n- [Hugging Face Inference Providers vs Muse Ember](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-muse-ember.md)\n- [Inkling 2 Small vs Muse Ember](https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-ember.md)\n- [Inkling 2 Small vs Vercel AI Gateway](https://www.anchorterminal.com/compare/inkling-2-small-vs-vercel-ai-gateway.md)\n- [Jais 3 vs Muse Ember](https://www.anchorterminal.com/compare/jais-3-vs-muse-ember.md)\n- [Jais 3 vs Vercel AI Gateway](https://www.anchorterminal.com/compare/jais-3-vs-vercel-ai-gateway.md)\n- [Meta Model API vs Muse Ember](https://www.anchorterminal.com/compare/meta-model-api-vs-muse-ember.md)\n- [Meta Model API vs Vercel AI Gateway](https://www.anchorterminal.com/compare/meta-model-api-vs-vercel-ai-gateway.md)\n- [MiniMax API vs Muse Ember](https://www.anchorterminal.com/compare/minimax-api-vs-muse-ember.md)\n- [MiniMax API vs Vercel AI Gateway](https://www.anchorterminal.com/compare/minimax-api-vs-vercel-ai-gateway.md)\n- [Mistral AI API vs Muse Ember](https://www.anchorterminal.com/compare/mistral-api-vs-muse-ember.md)\n- [Mistral AI API vs Vercel AI Gateway](https://www.anchorterminal.com/compare/mistral-api-vs-vercel-ai-gateway.md)\n- [Muse Ember vs Muse Spark Open](https://www.anchorterminal.com/compare/muse-ember-vs-muse-spark-open.md)\n- [Muse Ember vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/muse-ember-vs-nemotron-3-5-super-vl.md)\n- [Muse Ember vs Novita AI](https://www.anchorterminal.com/compare/muse-ember-vs-novita-ai.md)\n- [Muse Ember vs OpenAI API](https://www.anchorterminal.com/compare/muse-ember-vs-openai-api.md)\n- [Muse Ember vs OpenRouter](https://www.anchorterminal.com/compare/muse-ember-vs-openrouter.md)\n- [Muse Ember vs Prism Inference](https://www.anchorterminal.com/compare/muse-ember-vs-prism-inference.md)\n- [Muse Ember vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/muse-ember-vs-ramp-router.md)\n- [Muse Ember vs Beam 1.0](https://www.anchorterminal.com/compare/muse-ember-vs-reflection-beam.md)\n- [Muse Ember vs RouterPlus](https://www.anchorterminal.com/compare/muse-ember-vs-routerplus.md)\n- [Muse Ember vs SambaCloud](https://www.anchorterminal.com/compare/muse-ember-vs-sambanova.md)\n- [Muse Ember vs SiliconFlow](https://www.anchorterminal.com/compare/muse-ember-vs-siliconflow.md)\n- [Muse Ember vs Simplismart](https://www.anchorterminal.com/compare/muse-ember-vs-simplismart.md)\n- [Muse Ember vs StepFun API](https://www.anchorterminal.com/compare/muse-ember-vs-stepfun-api.md)\n- [Muse Ember vs SWE-2 Flash](https://www.anchorterminal.com/compare/muse-ember-vs-swe-2-flash.md)\n- [Muse Ember vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/muse-ember-vs-tencent-tokenhub.md)\n- [Muse Ember vs Together AI Inference](https://www.anchorterminal.com/compare/muse-ember-vs-together-inference.md)\n- [Muse Ember vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/muse-ember-vs-vertex-ai.md)\n- [Muse Ember vs xAI API (Grok)](https://www.anchorterminal.com/compare/muse-ember-vs-xai-api.md)\n- [Muse Spark Open vs Vercel AI Gateway](https://www.anchorterminal.com/compare/muse-spark-open-vs-vercel-ai-gateway.md)\n- [Nemotron 3.5 Super VL vs Vercel AI Gateway](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-vercel-ai-gateway.md)\n- [Novita AI vs Vercel AI Gateway](https://www.anchorterminal.com/compare/novita-ai-vs-vercel-ai-gateway.md)\n- [OpenAI API vs Vercel AI Gateway](https://www.anchorterminal.com/compare/openai-api-vs-vercel-ai-gateway.md)\n- [OpenRouter vs Vercel AI Gateway](https://www.anchorterminal.com/compare/openrouter-vs-vercel-ai-gateway.md)\n- [Beam 1.0 vs Vercel AI Gateway](https://www.anchorterminal.com/compare/reflection-beam-vs-vercel-ai-gateway.md)\n- [SambaCloud vs Vercel AI Gateway](https://www.anchorterminal.com/compare/sambanova-vs-vercel-ai-gateway.md)\n- [SiliconFlow vs Vercel AI Gateway](https://www.anchorterminal.com/compare/siliconflow-vs-vercel-ai-gateway.md)\n- [Simplismart vs Vercel AI Gateway](https://www.anchorterminal.com/compare/simplismart-vs-vercel-ai-gateway.md)\n- [StepFun API vs Vercel AI Gateway](https://www.anchorterminal.com/compare/stepfun-api-vs-vercel-ai-gateway.md)\n- [SWE-2 Flash vs Vercel AI Gateway](https://www.anchorterminal.com/compare/swe-2-flash-vs-vercel-ai-gateway.md)\n- [Together AI Inference vs Vercel AI Gateway](https://www.anchorterminal.com/compare/together-inference-vs-vercel-ai-gateway.md)\n- [Vercel AI Gateway vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/vercel-ai-gateway-vs-vertex-ai.md)\n- [Vercel AI Gateway vs xAI API (Grok)](https://www.anchorterminal.com/compare/vercel-ai-gateway-vs-xai-api.md)\n- [Antseed vs Vercel AI Gateway](https://www.anchorterminal.com/compare/antseed-vs-vercel-ai-gateway.md)\n- [Eden AI vs Vercel AI Gateway](https://www.anchorterminal.com/compare/eden-ai-vs-vercel-ai-gateway.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- [LiteLLM vs Vercel AI Gateway](https://www.anchorterminal.com/compare/litellm-vs-vercel-ai-gateway.md)\n- [Router.com (Ramp Router) vs Vercel AI Gateway](https://www.anchorterminal.com/compare/ramp-router-vs-vercel-ai-gateway.md)\n- [RouterPlus vs Vercel AI Gateway](https://www.anchorterminal.com/compare/routerplus-vs-vercel-ai-gateway.md)\n- [Tencent Cloud TokenHub vs Vercel AI Gateway](https://www.anchorterminal.com/compare/tencent-tokenhub-vs-vercel-ai-gateway.md)\n- [Prism Inference vs Vercel AI Gateway](https://www.anchorterminal.com/compare/prism-inference-vs-vercel-ai-gateway.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": "2026-11-09", "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": "Muse Ember vs Vercel AI Gateway", "url": "" } ], "description": "Vercel AI Gateway scores 67.8 (B) to Muse Ember's 51.8 (D) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Muse Ember D 51.8", "Vercel AI Gateway B 67.8", "scores" ], "h1": "Muse Ember vs Vercel AI Gateway", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/muse-ember-vs-vercel-ai-gateway", "published": "2026-10-01", "section": "tools", "title": "Muse Ember vs Vercel AI Gateway for AI agents (2026) | Anchor Terminal", "toc": null, "updated": "2026-11-09", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-vercel-ai-gateway" }, "tokens": { "markdown": 7100, "slim": 1030 }, "version": 1 }