{ "data": { "a": { "slug": "meta-model-api", "name": "Meta Model API", "vendor": "Meta", "vendorUrl": "https://dev.meta.ai", "kind": "model", "category": "inference", "summary": "Meta Model API is Meta's pay-as-you-go API for its hosted Muse models, including Muse Wonder and Muse Spark, through OpenAI-style Responses and Chat Completions endpoints and an Anthropic-style Messages endpoint, plus image, speech and segmentation routes.", "url": "https://www.anchorterminal.com/tools/meta-model-api", "markdownUrl": "https://www.anchorterminal.com/tools/meta-model-api.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/meta-model-api.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/meta-model-api.json", "dns": "meta-model-api.grade.anchorterminal.com", "license": "Closed service under the Meta Model API Terms of Service (last updated 9 October 2026), with Meta Platforms, Inc., or Meta Platforms Ireland Limited in the European Region, as the contracting party.", "transports": [ "http" ], "remoteUrl": "https://api.meta.ai/v1", "packages": [], "auth": "api-key", "authNotes": "A bearer API key created on the API keys tab of the Model API dashboard after a browser sign-up with email, mobile number, Facebook, Google or GitHub. Keys belong to a team, are shown once and are revoked by deletion. No key scopes were found, and every key on a team shares the team's rate limits.", "pricing": "usage", "pricingNotes": "Muse Wonder is $4.00 per million input tokens, $0.20 cached and $20.00 per million output tokens, Standard mode only (checked 2026-10-12). Muse Spark is $1.25, $0.15 and $4.25, or $0.10, $0.002 and $0.20 in Contributor mode, where Meta may train on the content. Billed in arrears to a card. No free allowance was found.", "priceSummary": "from $1.25 / 1M in", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in dev.meta.ai/llms.txt, the pricing page, the API reference or the billing help pages, checked 12 October 2026. Usage is charged to a card at a payment threshold or on the 1st of each month.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-12" }, "docsUrl": "https://dev.meta.ai/docs/overview", "llmsTxt": "https://dev.meta.ai/llms.txt", "capabilities": [ "inference.llm", "image.generate", "image.edit", "speech.stt", "speech.streaming" ], "tags": [ "official", "hosted", "model", "usage-priced", "closed-source", "llms-txt", "multimodal", "streaming", "openai-compatible", "anthropic-compatible", "card-required" ], "lastRelease": "2026-10-12", "graded": true, "anchor": { "graded": true, "score": 52.3, "grade": "D", "agentReady": false, "rank": 905, "ranked": true, "rankOf": 1260, "categoryRank": 26, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 75, "maintenance": 46, "payments": 20, "reliability": 40, "schema": 60, "security": 64, "transparency": 53 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-12" }, "negative": 0, "verdict": "Meta Model API serves Muse Wonder, in preview since 12 October 2026, and Muse Spark with 1M-token context, constrained JSON Schema output, automatic prompt caching and per-token prices published without a login. Standard-mode content is not used for training. There's no free allowance, status history, OpenAPI file, deprecation policy or way to force a tool call.", "bestFor": "Long-running agent and coding work over text, images, video, audio and PDFs with a 1M-token context, where training must stay off by default.", "strengths": [ "Muse Wonder and Muse Spark take text, image, video, audio and PDF input with a 1,048,576-token context window", "Per-token prices, per-model rate limits and rate-limit headers published without a login", "Content sent in Standard mode is not used to train Meta models, and training use is opt-in through `-contributor` model IDs", "Responses, Chat Completions and Messages endpoints, so the OpenAI and Anthropic SDKs work with a base-URL change", "llms.txt and a Markdown copy of every docs page, with an error guide that gives the Retry-After value for each retryable error" ], "weaknesses": [ "Muse Wonder is labelled a preview, and no deprecation policy or notice period was found", "No free API allowance found, and billing is set up with a card", "No status page with history. The docs' status link redirects to the home page, and `/v1/status` reports only the current state", "`tool_choice` accepts only `auto`, so a call can't be forced or ruled out", "No OpenAPI file, batch endpoint or Model API changelog found, and API keys have no scopes" ], "agentNotes": [ "Use `muse-wonder-1.0` for long multi-step work and `muse-spark-1.3` for cheaper, high-volume calls. Both take the same requests", "Keep personal or confidential data away from `-contributor` model IDs. Meta may train on that content", "Honour Retry-After on 429 and 503, which is 60 seconds for `service_overloaded`, and check `GET https://api.meta.ai/v1/status`, which needs no key", "Pass the key to the OpenAI SDK explicitly or set `OPENAI_API_KEY`. The SDK doesn't read `MODEL_API_KEY`", "Leave `tool_choice` at `auto`. The docs say `none` and `required` are not supported" ], "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": 52.3 } ], "editorialScores": { "ergonomics": 75, "maintenance": 46, "payments": 20, "reliability": 40, "schema": 60, "security": 64, "transparency": 41 }, "provenanceScore": 64, "checked": { "categories": { "ergonomics": "2026-10-12", "maintenance": "2026-10-12", "payments": "2026-10-12", "reliability": "2026-10-12", "schema": "2026-10-12", "security": "2026-10-12", "transparency": "2026-10-12" }, "last": "2026-10-12", "lastMoved": "2026-10-30", "oldest": "2026-10-12", "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 '{\"model\": \"muse-spark-1.3\", \"input\": \"What is the capital of France?\"}'" }, "letme": { "capability": "https://letme.dev/inference.llm", "tool": "https://letme.dev/meta-model-api" }, "sameCompany": [ "muse-spark-open", "muse-code", "muse-glimmer-30b" ], "area": "models", "unitPrices": [ { "item": "Muse Wonder input", "unit": "1m-tokens", "usd": 4, "note": "Standard mode, muse-wonder-1.0. No long-context premium." }, { "item": "Muse Wonder cached input", "unit": "1m-tokens", "usd": 0.2 }, { "item": "Muse Wonder output", "unit": "1m-tokens", "usd": 20 }, { "item": "Muse Spark input", "unit": "1m-tokens", "usd": 1.25, "note": "Standard mode, muse-spark-1.3, 1.2 and 1.1." }, { "item": "Muse Spark cached input", "unit": "1m-tokens", "usd": 0.15 }, { "item": "Muse Spark output", "unit": "1m-tokens", "usd": 4.25 }, { "item": "Muse Spark input, Contributor mode", "unit": "1m-tokens", "usd": 0.1, "note": "Meta may use the content to train its models." }, { "item": "Muse Spark output, Contributor mode", "unit": "1m-tokens", "usd": 0.2, "note": "Cached input is $0.002 per million tokens." }, { "item": "Web search grounding", "unit": "1k-requests", "usd": 2.5, "note": "Per 1,000 search queries, on top of token cost." }, { "item": "Muse Image generated image", "unit": "image", "usd": 0.01 } ], "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": "2026-10-12", "notes": [ "The terms (last updated 9 October 2026) are an agreement with Meta Platforms, Inc., or Meta Platforms Ireland Limited for users in the European Region. The model card names the same two.", "The privacy field is the Meta Privacy Policy, which the terms link. www.facebook.com's robots.txt asks readers like ours not to fetch it, as the 8 October policy reading records, so it wasn't read. The terms also link a subprocessor list at forwork.meta.com/legal/mfw-subprocessor-list/ and the Meta Global Processor Terms, neither of which was read.", "RDAP for meta.ai gives a registration date of 16 December 2017. The API answers at api.meta.ai.", "No status page. The error guide links dev.meta.ai/status, which redirects to the home page. `GET /v1/status` is an unauthenticated health endpoint with no history.", "No Model API changelog was found. The only changelog on dev.meta.ai is Muse Code's.", "dev.meta.ai/.well-known/security.txt returns 404. www.meta.ai's robots.txt disallows ClaudeBot, so its security.txt wasn't requested. www.facebook.com/.well-known/security.txt is valid until 11 November 2026 and points to bugbounty.meta.com.", "developer.meta.com/ai/ redirects to dev.meta.ai." ], "score": 64 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/meta-model-api.json", "live": { "slug": "meta-model-api", "probe": { "target": "https://api.meta.ai/v1", "method": "get", "lastAt": "2026-11-02T00:56:11.612519479Z", "lastOk": true, "lastStatus": 404, "lastMs": 68, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 71, "p95ms24h": 175, "samples24h": 249, "samples30d": 5065, "days": [ { "date": "2026-10-12", "probes": 33, "ok": 33 }, { "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": 10, "ok": 10 } ] }, "securityTxt": { "url": "https://meta.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-01T15:42:39.498601263Z" }, "llmsTxt": { "url": "https://dev.meta.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-01T15:14:14.590383312Z" }, "domain": { "domain": "meta.ai", "registered": "2017-12-16", "source": "https://rdap.identitydigital.services/rdap/domain/meta.ai", "checkedAt": "2026-11-01T14:15:25.518716318Z" }, "pages": [ { "url": "https://dev.meta.ai/legal/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-11-01T06:38:45.037397948Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "0ef10c66f1b3" } ], "updatedAt": "2026-11-02T00:56:11.612519479Z" } }, "answer": "Tencent Cloud TokenHub scores 59.5 (C) on agent readiness against Meta Model API's 52.3 (D), and leads in every scored category.", "b": { "slug": "tencent-tokenhub", "name": "Tencent Cloud TokenHub", "vendor": "Tencent Cloud", "vendorUrl": "https://cloud.tencent.com", "kind": "router", "category": "inference", "summary": "Tencent Cloud TokenHub is a hosted model gateway serving Tencent's Hy models and third-party models such as DeepSeek, Kimi, GLM and MiniMax through OpenAI-compatible and Anthropic-compatible endpoints in Guangzhou and Singapore, with per-key scopes and quotas.", "url": "https://www.anchorterminal.com/tools/tencent-tokenhub", "markdownUrl": "https://www.anchorterminal.com/tools/tencent-tokenhub.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/tencent-tokenhub.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/tencent-tokenhub.json", "dns": "tencent-tokenhub.grade.anchorterminal.com", "repo": "https://github.com/TencentCloud/THCLI", "license": "Proprietary service under the TokenHub Terms of Service, the TokenHub SLA and the Tencent Cloud Service Agreement, with a special note for third-party deployed models. The `tencent-tokenhub-cli` package is Apache-2.0", "transports": [ "http" ], "remoteUrl": "https://tokenhub.tencentmaas.com/v1", "packages": [ { "registry": "npm", "name": "tencent-tokenhub-cli" } ], "auth": "api-key", "authNotes": "Bearer API key from the TokenHub console, or `x-api-key` on the Anthropic-style `/v1/messages`. Keys are long-lived, belong to one region (Guangzhou or Singapore), can be limited to chosen models and inference services, up to 200 IP ranges and token quotas, and can be disabled or deleted. They can also be created through the CreateApiKey control-plane call with signed Tencent Cloud credentials, or by `thcli auth login`. The account needs real-name verification first.", "pricing": "usage", "pricingNotes": "Pay per token in CNY, billed hourly. Hy4 preview costs 6 CNY in, 18 CNY out and 0.3 CNY cached per 1M tokens, Hy3 1, 4 and 0.25 CNY. DeepSeek models double at weekday peak hours. Batch is half price for Hy3 and Hy4 preview. Each account gets 1M free tokens per language model for a year, in a campaign to 31 December 2026. Token Plan subscriptions run from 28 to 599 CNY a month (https://cloud.tencent.com/document/product/1823/130055, checked 2026-11-01).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs table of contents, the billing pages or the API usage page. Payment is from a Tencent Cloud account balance, billed hourly (checked 2026-11-01).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 204, "pypiWeekly": null, "asOf": "2026-11-01" }, "docsUrl": "https://cloud.tencent.com/document/product/1823/130058", "rateLimitsUrl": "https://cloud.tencent.com/document/product/1823/136028", "llmsTxt": "https://cloud.tencent.com/document/product/1823/llms.txt", "capabilities": [ "inference.router", "inference.llm", "inference.open-weights", "embed.text", "embed.multimodal", "image.generate", "video.generate", "speech.tts", "speech.stt", "audio.music", "translate.text", "web.search", "obs.gateway" ], "tags": [ "hosted", "router", "usage-based", "free-credit", "openai-compatible", "anthropic-compatible", "llms-txt", "cli", "sla", "batch", "bug-bounty", "no-status-page", "regional-endpoints", "singapore", "chinese", "subscription" ], "lastRelease": "2026-10-24", "graded": true, "anchor": { "graded": true, "score": 59.5, "grade": "C", "agentReady": false, "rank": 646, "ranked": true, "rankOf": 1260, "categoryRank": 18, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 83, "maintenance": 73, "payments": 35, "reliability": 46, "schema": 73, "security": 71, "transparency": 54 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": -3, "negativeNotes": [ "2026-10-17. -3, a breaking change without notice. DeepSeek-V4.1-Flash (directly supplied) was moved to its 1017 version under the same model ids and prices on 17 October 2026, and the notice came two days later (https://cloud.tencent.com/announce/detail/2516). Callers pinned to the id got a different model's behaviour with no warning. One term at the floor: the API didn't change. The founder's decision, 1 November 2026." ], "verdict": "Keys can be limited to chosen models, source IPs and token quotas, errors name their source and code, and a 99.5% SLA covers paid use of models Tencent runs. Sign-up needs a Tencent Cloud account with real-name verification, prices are in CNY, no public status page was found, and 18 model retirement notices ran from April to October 2026.", "bestFor": "Teams in or near Tencent Cloud that want one key and bill for Tencent's Hy models and Chinese open-weight models (DeepSeek, Kimi, GLM, MiniMax, Qwen, MiMo) with per-key limits and CNY billing.", "strengths": [ "API keys can be limited to chosen models and inference services, up to 200 source IP ranges, and daily, monthly or total token quotas", "One base URL answers OpenAI Chat Completions, OpenAI Responses and Anthropic Messages calls, and `GET /v1/models` marks models due to retire as `pre-offline`", "Error bodies carry a six-digit code, English and Chinese messages, the source (client, gateway or upstream) and a request ID, and 429s can carry `Retry-After`", "A published SLA promises 99.5% monthly availability with voucher credits of 10 to 50 per cent of the month's fee, for paid use of models Tencent runs", "Per-call audit logs (request ID, key, client IP, status, tokens, latency) can be delivered to the customer's own Tencent Cloud CLS log service" ], "weaknesses": [ "Sign-up needs a Tencent Cloud account with real-name verification. The international site answered with a bot check, so access from outside China was not established", "No public status page was found. A four-hour outage of DeepSeek's directly supplied models on 15 October 2026 appears only as a compensation notice", "18 model retirement notices from 21 April to 22 October 2026. Those read gave 21 to 33 days, and eligible callers are switched to a successor at its price", "DeepSeek's directly supplied models send inputs to DeepSeek under its own terms, and the TokenHub SLA does not cover them", "Per-model RPM and TPM limits for chat models are shown in the console and the quota API, not in the public docs" ], "agentNotes": [ "Use `https://tokenhub.tencentmaas.com/v1` with keys made for Guangzhou and `https://tokenhub-intl.tencentmaas.com/v1` with keys made for Singapore. Keys do not work across the two", "Send the key as `Authorization: Bearer` on the OpenAI paths and as `x-api-key` on `/v1/messages`", "Parse `error.code` as a string or a number, since 429 codes can come back as integers, and wait for `Retry-After` before retrying", "Take model ids from `GET /v1/models` and watch for `pre-offline`. The quickstart's `deepseek-v3` example is not in the current model list", "Expect DeepSeek prices to double on weekdays from 9am to noon and 2pm to 6pm Beijing time, when the peak rate applies" ], "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": 59.5 } ], "editorialScores": { "ergonomics": 83, "maintenance": 73, "payments": 35, "reliability": 46, "schema": 73, "security": 71, "transparency": 59 }, "provenanceScore": 49, "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", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npm i -g tencent-tokenhub-cli", "http": "curl https://tokenhub.tencentmaas.com/v1/models \\\n -H \"Authorization: Bearer $TOKENHUB_API_KEY\"", "claudeCode": "{\n \"env\": {\n \"ANTHROPIC_BASE_URL\": \"https://tokenhub.tencentmaas.com\",\n \"ANTHROPIC_AUTH_TOKEN\": \"YOUR_API_KEY\",\n \"ANTHROPIC_MODEL\": \"hy3\"\n }\n}" }, "letme": { "capability": "https://letme.dev/inference.router", "tool": "https://letme.dev/tencent-tokenhub" }, "area": "models", "provenance": { "legalEntity": "Tencent Cloud Computing (Beijing) Co., Ltd. (腾讯云计算（北京）有限责任公司)", "domain": "tencentmaas.com", "domainRegistered": "2026-03-13", "endpointOnVendorDomain": false, "terms": "https://cloud.tencent.com/document/product/301/129852", "privacy": "https://privacy.qq.com/document/preview/91d5fd3c98ce4468ae462ac59233bba2", "statusPage": "", "changelog": "https://cloud.tencent.com/document/product/1823/130675", "securityTxt": "none", "checked": "2026-11-01", "notes": [ "The TokenHub Terms of Service (effective 14 September 2026), the SLA (effective 23 April 2026) and the special note on third-party deployed models (effective 14 September 2026) name 腾讯云计算（北京）有限责任公司. The docs footer also names 深圳市腾讯计算机系统有限公司 as ICP licence holder.", "The TokenHub privacy policy is linked from the docs to privacy.qq.com, which renders only with JavaScript, so it was not read. privacy.qq.com has no robots.txt (404).", "No public status page was found. status.cloud.tencent.com did not answer, and the Tencent Cloud health dashboard documentation answered with a bot check.", "security.txt answered 404 on cloud.tencent.com, www.tencent.com and tokenhub.tencentmaas.com. Tencent's bug bounty policy at en.security.tencent.com lists Tencent Cloud in scope.", "RDAP at Verisign gives tencentmaas.com a registration date of 13 March 2026 with no registrant. The API answers at tokenhub.tencentmaas.com and tokenhub-intl.tencentmaas.com, named in Tencent Cloud's API usage page.", "cloud.tencent.com allows these docs in robots.txt. Its pages answered some requests with a JavaScript bot check, which was not passed. The pages were read when a later plain request returned them. www.tencentcloud.com answered robots.txt with a bot check, so the international site was not read." ], "score": 49 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/tencent-tokenhub.json", "live": { "slug": "tencent-tokenhub", "probe": { "target": "https://tokenhub.tencentmaas.com/v1", "method": "get", "lastAt": "2026-11-02T00:56:24.101434531Z", "lastOk": true, "lastStatus": 404, "lastMs": 795, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 826, "p95ms24h": 1067, "samples24h": 28, "samples30d": 28, "days": [ { "date": "2026-11-01", "probes": 18, "ok": 18 }, { "date": "2026-11-02", "probes": 10, "ok": 10 } ] }, "updatedAt": "2026-11-02T00:56:24.101434531Z" } }, "edges": [ { "by": 27, "category": "maintenance", "leads": "tencent-tokenhub", "name": "Maintenance \u0026 community", "reasons": { "a": "Model reading. Muse Wonder launched on 12 October 2026 (30). No deprecation policy or notice period found. All three Muse Spark versions are still served, so no retirement has tested one (0 of 12). Three dated launches in the last 90 days that we read, Muse Spark 1.2 on 5 August, Muse Code out of beta on 31 August and Muse Wonder on 12 October (8 of 8). No Model API changelog. A help centre with support tickets, answered 'typically within two business days' by Meta's own account, which we didn't test (8 of 15). No SDK of Meta's own for the API (0 of 15, 0 of 10).", "b": "Closed service, read on the model lines. The newest release note is dated 24 October 2026 and the price page was updated on 31 October (30). The four retirement notices read gave 21 to 33 days, and eligible callers are switched to a successor at its price. No minimum notice period is written, and DeepSeek-V4.1-Flash (directly supplied) was moved to the 1017 version under the same ids on 17 October 2026 in a notice dated two days later (7 of 12). 18 retirement notices from 21 April to 22 October 2026, 12 of them since 3 August (3 of 8). Dated release notes and announcements, ticket and phone support around the clock and a Q\u0026A community (13 of 15). Replies on the THCLI repository were not sampled (3 of 10). Tencent Cloud SDK 3.0 in several languages covers the control plane and `tencent-tokenhub-cli` 1.0.2 was published on 30 October 2026. No inference SDK of its own (12 of 15). The CLI has four releases since 15 September 2026, lists no runtime dependencies and needs Node.js 18 or later. CI not checked (5 of 10)." }, "scores": { "a": 46, "b": 73 } }, { "by": 15, "category": "payments", "leads": "tencent-tokenhub", "name": "Payments \u0026 pricing", "reasons": { "a": "No machine payment protocol (0). Per-token prices for Muse Wonder and Muse Spark, and per-image, per-hour and per-frame prices for the other models, published without a login (20). No free API allowance found. Billing needs a card, and Playground requests count towards usage (0). Browser sign-up with email, phone, Facebook, Google or GitHub (0).", "b": "No x402, MPP or L402 (0). Per-token prices for every model are public in CNY for Guangzhou and Singapore, with DeepSeek's peak and off-peak rates (20). Each account gets 1M free tokens per language model, valid for a year, in a campaign running to 31 December 2026. No card is mentioned, but the account needs real-name verification, so this line takes 15 of 20. A person signs up and completes real-name verification in a browser. Keys can then be created in code or by `thcli auth login`, but only from that account (0)." }, "scores": { "a": 20, "b": 35 } }, { "by": 13, "category": "schema", "leads": "tencent-tokenhub", "name": "Schema \u0026 documentation", "reasons": { "a": "No OpenAPI or similar machine-readable contract found. The reference is Markdown pages with schema sections, and /openapi.json paths on dev.meta.ai return 404 (0). llms.txt at dev.meta.ai/llms.txt, and every docs page has a Markdown copy (10). The models page says when to choose Muse Wonder and when Muse Spark, and the tool-calling and structured-output guides state their limits, such as `tool_choice` only accepting `auto` and which schema keywords `strict` allows (16 of 20). JSON Schema tools and output, `reasoning_effort` an enum from minimal to max, a strict subset that returns 400 when violated, though `tool_choice` has one value (12 of 15). Curl, Python and TypeScript examples on each page and an error guide covering 400 to 504 with the error envelope, codes and a fix for each (15). Versioned model IDs (muse-spark-1.1 to 1.3, muse-wonder-1.0) and dated launch posts on the developer blog, but no API changelog (7 of 15).", "b": "Router, scored on the API lines. No OpenAPI file for the inference routes. Field pages document the OpenAI Chat Completions, OpenAI Responses and Anthropic Messages formats as TokenHub implements them, and the control plane is a Tencent Cloud API 3.0 service (version 2026-03-22) with typed parameters, API Explorer and SDKs (12 of 25). An llms.txt at cloud.tencent.com/document/product/1823/llms.txt links a Markdown copy of each docs page (10). The docs say which models support thinking, tools, structured output and caching, how TokenHub departs from each standard protocol, and which DeepSeek model suits which job. The quickstart's examples still use `deepseek-v3`, which is not in the model list, and Qwen3.5 stays in the list with a past shutdown date (13 of 20). Protocol pages list each field with type, required flag and default, and control-plane parameters carry enums and required flags (10 of 15). Examples in curl, Python, Node.js, Java and Go, and an error page listing 30 codes with HTTP status, cause and fix (14 of 15). Paths carry `/v1`, release notes are dated monthly from 7 April to 24 October 2026, and the control-plane API has a dated history of 26 releases to 18 September 2026 (14 of 15)." }, "scores": { "a": 60, "b": 73 } }, { "by": 8, "category": "ergonomics", "leads": "tencent-tokenhub", "name": "Agent ergonomics", "reasons": { "a": "Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Tool calls on all three endpoints, parallel calls, tool search with deferred loading, built-in web search and a computer-use tool, but `tool_choice` accepts only `auto`, so a call can't be forced or forbidden (15 of 20). Output constrained to the JSON Schema on every surface (15). Automatic prompt caching with no setup, and cached input at 5 per cent of the input price on Muse Wonder (15). 1,048,576-token context on Muse Wonder and every Muse Spark version, with no long-context premium (15). No batch endpoint or discount found. Background responses run asynchronously at the normal price (0). No SDK of Meta's own. The docs use the OpenAI and Anthropic SDKs against compatible endpoints, the same reading as StepFun (0). OpenAI-style error envelope with `type` and `code`, per-status fixes and named retryable codes (15).", "b": "Router, read on the model lines. Function calling is marked on most chat models in the model list, with behaviour depending on the model routed (14 of 20). Structured output is marked per model and missing on the MiniMax and Qwen models, and an unsupported `response_format` returns code 400006 (12 of 15). Cache-hit prices are published per model, Kimi K3.1 Pro lists five-minute and one-hour cache writes, and a guide covers `prompt_cache_key` and the `X-Session-ID` header for instance affinity (14 of 15). Most listed chat models have contexts of one million tokens, a judgement call since a router has no default model (15). Batch at half price covers only Hy3 and Hy4 preview, reads and writes JSONL in the customer's own COS bucket and is documented for the Guangzhou endpoint (5 of 10). No TokenHub inference SDK. The OpenAI and Anthropic SDKs work with a changed base URL, and Tencent Cloud SDK 3.0 and the `thcli` CLI cover the control plane (8 of 10). Errors return a code, English and Chinese messages, the source, the upstream code and status and a request ID, and stream errors arrive as SSE error frames (15 of 15)." }, "scores": { "a": 75, "b": 83 } }, { "by": 7, "category": "security", "leads": "tencent-tokenhub", "name": "Security \u0026 auth", "reasons": { "a": "Model reading. Bearer keys per team, named, shown once and revoked by deletion, with rotation advice. No scopes, read-only keys or per-key limits found (20 of 30). The terms say Meta will not use Content submitted to the Standard Services to train Meta Models, and training applies only to the `-contributor` model IDs a caller picks. Content may still be used to develop and improve safety and security systems (17 of 20). Retention is 'as needed' for the service, the law, flagged violations and safety review, with no period stated. Zero data retention for qualified accounts through sales, with flagged content kept up to 2 years (10 of 15). The usage dashboard shows tokens and requests per day by model, with no per-key or per-call log found (5 of 15). No security.txt on dev.meta.ai. Meta's bug bounty at bugbounty.meta.com is named in the Muse Code SDK's security policy, and a security commitments page describes TLS 1.2 or later, PCI-DSS card handling and an ISMS, with no named certification for the API (12 of 20).", "b": "Router, read on the model lines. Bearer keys can be limited to chosen models and inference services, up to 200 source IP ranges and daily, monthly or total token quotas, can be disabled or deleted, and can be created in code through CreateApiKey with signed Tencent Cloud credentials. Keys are long-lived with no expiry setting or built-in rotation (26 of 30). Clause 2.17 of the terms says inputs are not used to train Tencent Cloud's own models, and the FAQ says data is not used for training. Inputs to third-party deployed models (DeepSeek's directly supplied ones) go to DeepSeek under its terms (14 of 20). Clause 2.14 keeps data only as long as the service needs, with no periods stated. When a customer asks for generated content without AI labels, Tencent Cloud keeps logs of who received it for at least six months. No zero-retention option was found (7 of 15). Per-call audit logs (request ID, key, client IP, status, tokens, latency) and optional full call logs go to the customer's CLS, billed separately, with usage by key and a monitoring dashboard (14 of 15). No security.txt on cloud.tencent.com, www.tencent.com or tokenhub.tencentmaas.com (404). Tencent's bug bounty through TSRC lists Tencent Cloud in scope. No certification for TokenHub was checked (10 of 20)." }, "scores": { "a": 64, "b": 71 } }, { "by": 6, "category": "reliability", "leads": "tencent-tokenhub", "name": "Reliability", "reasons": { "a": "No status page with component history. The error guide's link to dev.meta.ai/status redirects to the home page, and `GET /v1/status` reports only the current state, `operational` when we called it on 12 October (0). No readable incident history (5). Rate limits published per team and per model, 3,000 RPM and 4,000,000 TPM for muse-wonder-1.0, 150 RPM for the contributor variants, 600 background submissions a minute (15). 429 and 503 carry Retry-After (60 seconds for `service_overloaded` and `backend_unavailable`), with backoff-with-jitter guidance, rate-limit headers on every token response and a documented mid-stream `server_shutting_down` event to retry (15). No SLA found, and the terms let Meta throttle or suspend access without notice (0). Muse Wonder is labelled a preview. Muse Spark 1.3 carries no preview label, but the API opened on 8 July 2026 as a public preview and we found no general-availability notice, so half (5 of 10, a departure from the all-or-nothing line).", "b": "Hosted reading. No public status page was found. status.cloud.tencent.com did not answer and the Tencent Cloud health dashboard documentation answered with a bot check (0). With no page there is no incident record to read (5 of 30). The announcements carry one incident, DeepSeek's directly supplied models unavailable from 9:06 to 13:04 Beijing time on 15 October 2026 after a fault at DeepSeek, compensated with vouchers. Rate limits are per model, shown in the console and returned by DescribeModelQuota. The public docs give numbers only for batch jobs (20 created a minute, 10 active), image models (5 concurrent) and DeepSeek V4 Flash and Pro (2,500 and 500 concurrent), with the rules for self-serve increases (8 of 15). Six 429 codes separate RPM, TPM, TPD, concurrency and upstream capacity, 429s may carry `Retry-After` and the docs advise exponential backoff. No idempotency guidance, though inference calls are not writes (13 of 15). The TokenHub SLA promises 99.5% monthly availability with vouchers of 10, 25 or 50 per cent of the month's fee. It excludes free use and third-party deployed models such as DeepSeek's directly supplied ones (10). Generally available since 7 April 2026, with some models marked preview (10)." }, "scores": { "a": 40, "b": 46 } } ], "facts": [ { "a": "Model API", "b": "Model router", "name": "Kind" }, { "a": "Meta", "b": "Tencent Cloud", "name": "Vendor" }, { "a": "https://api.meta.ai/v1", "b": "https://tokenhub.tencentmaas.com/v1", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "API key", "b": "API key", "name": "Auth" }, { "a": "Pay per use", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Closed service under the Meta Model API Terms of Service (last updated 9 October 2026), with Meta Platforms, Inc., or Meta Platforms Ireland Limited in the European Region, as the contracting party.", "b": "Proprietary service under the TokenHub Terms of Service, the TokenHub SLA and the Tencent Cloud Service Agreement, with a special note for third-party deployed models. The `tencent-tokenhub-cli` package is Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-12", "b": "2026-10-24", "name": "Last release" }, { "a": "2026-10-02", "b": "couldn't be read", "name": "Terms last updated" }, { "a": "couldn't be read", "b": "couldn't be read", "name": "Privacy policy last updated" }, { "a": "yes", "b": "couldn't be read", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "couldn't be read", "name": "Terms restrict automated access" }, { "a": "yes", "b": "couldn't be read", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "couldn't be read", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "couldn't be read", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "204 npm/wk", "name": "Popularity" } ], "faq": [ { "answer": "Tencent Cloud TokenHub scores 59.5 (C) on agent readiness against Meta Model API's 52.3 (D), and leads in every scored category.", "question": "Which is better for AI agents, Meta Model API or Tencent Cloud TokenHub?" }, { "answer": "Both need an API key.", "question": "Do Meta Model API and Tencent Cloud TokenHub need an API key?" }, { "answer": "Yes. Meta Model API has a hosted endpoint at https://api.meta.ai/v1 and Tencent Cloud TokenHub at https://tokenhub.tencentmaas.com/v1.", "question": "Can an agent call Meta Model API and Tencent Cloud TokenHub without installing anything?" } ], "goodFor": [ { "aheadOn": null, "also": [ "No incidents deducted, where Tencent Cloud TokenHub loses 3 points for them" ], "goodFor": "Long-running agent and coding work over text, images, video, audio and PDFs with a 1M-token context, where training must stay off by default.", "slug": "meta-model-api", "watchFor": "Muse Wonder is labelled a preview, and no deprecation policy or notice period was found" }, { "aheadOn": [ "Reliability, 46 against 40", "Schema \u0026 documentation, 73 against 60", "Agent ergonomics, 83 against 75", "Security \u0026 auth, 71 against 64", "Payments \u0026 pricing, 35 against 20", "Maintenance \u0026 community, 73 against 46" ], "also": null, "goodFor": "Teams in or near Tencent Cloud that want one key and bill for Tencent's Hy models and Chinese open-weight models (DeepSeek, Kimi, GLM, MiniMax, Qwen, MiMo) with per-key limits and CNY billing.", "slug": "tencent-tokenhub", "watchFor": "Sign-up needs a Tencent Cloud account with real-name verification. The international site answered with a bot check, so access from outside China was not established" } ], "history": { "meta-model-api": [ { "causes": [ "method" ], "date": "2026-10-30", "delta": -0.2, "from": 52.5, "fromGrade": "D", "to": 52.3, "toGrade": "D" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.3, "from": 52.2, "fromGrade": "D", "to": 52.5, "toGrade": "D" } ], "tencent-tokenhub": null }, "job": { "capability": "inference.llm", "name": "LLM inference" }, "others": [ { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-meta-model-api.json", "title": "Claude API vs Meta Model API", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-tencent-tokenhub.json", "title": "Claude API vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/antseed-vs-meta-model-api.json", "title": "Antseed vs Meta Model API", "url": "https://www.anchorterminal.com/compare/antseed-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-meta-model-api.json", "title": "BlockRun.AI vs Meta Model API", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-tencent-tokenhub.json", "title": "BlockRun.AI vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/cerebras-inference-vs-meta-model-api.json", "title": "Cerebras Inference vs Meta Model API", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/cerebras-inference-vs-tencent-tokenhub.json", "title": "Cerebras Inference vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-meta-model-api.json", "title": "Cloudflare AI Gateway vs Meta Model API", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-tencent-tokenhub.json", "title": "Cloudflare AI Gateway vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-meta-model-api.json", "title": "Cloudflare Workers AI vs Meta Model API", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-tencent-tokenhub.json", "title": "Cloudflare Workers AI vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-meta-model-api.json", "title": "Cohere Chat API (Command models) vs Meta Model API", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-tencent-tokenhub.json", "title": "Cohere Chat API (Command models) vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/deepinfra-vs-meta-model-api.json", "title": "DeepInfra vs Meta Model API", "url": "https://www.anchorterminal.com/compare/deepinfra-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/deepinfra-vs-tencent-tokenhub.json", "title": "DeepInfra vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/deepinfra-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/deepseek-api-vs-meta-model-api.json", "title": "DeepSeek API vs Meta Model API", "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/deepseek-api-vs-tencent-tokenhub.json", "title": "DeepSeek API vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-meta-model-api.json", "title": "Glimpse vs Meta Model API", "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-tencent-tokenhub.json", "title": "Glimpse vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-meta-model-api.json", "title": "Fireworks AI Inference vs Meta Model API", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-tencent-tokenhub.json", "title": "Fireworks AI Inference vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/gemini-api-vs-meta-model-api.json", "title": "Gemini Developer API vs Meta Model API", "url": "https://www.anchorterminal.com/compare/gemini-api-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/gemini-api-vs-tencent-tokenhub.json", "title": "Gemini Developer API vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/gemini-api-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/groq-vs-meta-model-api.json", "title": "GroqCloud vs Meta Model API", "url": "https://www.anchorterminal.com/compare/groq-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/groq-vs-tencent-tokenhub.json", "title": "GroqCloud vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/groq-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-meta-model-api.json", "title": "Jais 3 vs Meta Model API", "url": "https://www.anchorterminal.com/compare/jais-3-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-tencent-tokenhub.json", "title": "Jais 3 vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/jais-3-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-minimax-api.json", "title": "Meta Model API vs MiniMax API", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-minimax-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/meta-model-api-vs-muse-spark-open.json", "title": "Meta Model API vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-muse-spark-open" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-nemotron-3-5-super-vl.json", "title": "Meta Model API vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-novita-ai.json", "title": "Meta Model API vs Novita AI", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-novita-ai" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-openai-api.json", "title": "Meta Model API vs OpenAI API", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-openai-api" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-openrouter.json", "title": "Meta Model API vs OpenRouter", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-openrouter" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-prism-inference.json", "title": "Meta Model API vs Prism Inference", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-ramp-router.json", "title": "Meta Model API vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-reflection-beam.json", "title": "Meta Model API vs Beam 1.0", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-reflection-beam" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-routerplus.json", "title": "Meta Model API vs RouterPlus", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-routerplus" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-sambanova.json", "title": "Meta Model API vs SambaCloud", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-sambanova" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-siliconflow.json", "title": "Meta Model API vs SiliconFlow", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-siliconflow" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-simplismart.json", "title": "Meta Model API vs Simplismart", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-simplismart" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-stepfun-api.json", "title": "Meta Model API vs StepFun API", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-stepfun-api" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-together-inference.json", "title": "Meta Model API vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-together-inference" }, { "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-tencent-tokenhub.json", "title": "MiniMax API vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/minimax-api-vs-tencent-tokenhub" }, { "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/muse-spark-open-vs-tencent-tokenhub.json", "title": "Muse Spark Open vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/novita-ai-vs-tencent-tokenhub.json", "title": "Novita AI vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/novita-ai-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/openai-api-vs-tencent-tokenhub.json", "title": "OpenAI API vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/openai-api-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/openrouter-vs-tencent-tokenhub.json", "title": "OpenRouter vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/openrouter-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/reflection-beam-vs-tencent-tokenhub.json", "title": "Beam 1.0 vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/reflection-beam-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/sambanova-vs-tencent-tokenhub.json", "title": "SambaCloud vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/sambanova-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/siliconflow-vs-tencent-tokenhub.json", "title": "SiliconFlow vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/siliconflow-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/simplismart-vs-tencent-tokenhub.json", "title": "Simplismart vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/simplismart-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/stepfun-api-vs-tencent-tokenhub.json", "title": "StepFun API vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/stepfun-api-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/tencent-tokenhub-vs-together-inference.json", "title": "Tencent Cloud TokenHub vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/tencent-tokenhub-vs-together-inference" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-tencent-tokenhub.json", "title": "Nemotron 3.5 Super VL vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/prism-inference-vs-tencent-tokenhub.json", "title": "Prism Inference vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/prism-inference-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/antseed-vs-tencent-tokenhub.json", "title": "Antseed vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/antseed-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/ramp-router-vs-tencent-tokenhub.json", "title": "Router.com (Ramp Router) vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/ramp-router-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/routerplus-vs-tencent-tokenhub.json", "title": "RouterPlus vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/routerplus-vs-tencent-tokenhub" }, { "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" } ], "panel": null, "scores": [ { "by": 6, "edge": "tencent-tokenhub", "key": "reliability", "meta-model-api": 40, "name": "Reliability", "tencent-tokenhub": 46, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 13, "edge": "tencent-tokenhub", "key": "schema", "meta-model-api": 60, "name": "Schema \u0026 documentation", "tencent-tokenhub": 73, "weight": 13 }, { "by": 8, "edge": "tencent-tokenhub", "key": "ergonomics", "meta-model-api": 75, "name": "Agent ergonomics", "tencent-tokenhub": 83, "weight": 13 }, { "by": 7, "edge": "tencent-tokenhub", "key": "security", "meta-model-api": 64, "name": "Security \u0026 auth", "tencent-tokenhub": 71, "weight": 14 }, { "by": 15, "edge": "tencent-tokenhub", "key": "payments", "meta-model-api": 20, "name": "Payments \u0026 pricing", "tencent-tokenhub": 35, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 27, "edge": "tencent-tokenhub", "key": "maintenance", "meta-model-api": 46, "name": "Maintenance \u0026 community", "tencent-tokenhub": 73, "weight": 7 }, { "by": 1, "edge": "tencent-tokenhub", "key": "transparency", "meta-model-api": 53, "name": "Transparency \u0026 trust", "tencent-tokenhub": 54, "weight": 7 } ], "summary": "Tencent Cloud TokenHub scores 59.5 (C) on agent readiness against Meta Model API's 52.3 (D), and leads in every scored category. Both do llm inference.", "tasks": null, "tutorials": [], "verdicts": { "meta-model-api": "Meta Model API serves Muse Wonder, in preview since 12 October 2026, and Muse Spark with 1M-token context, constrained JSON Schema output, automatic prompt caching and per-token prices published without a login. Standard-mode content is not used for training. There's no free allowance, status history, OpenAPI file, deprecation policy or way to force a tool call.", "tencent-tokenhub": "Keys can be limited to chosen models, source IPs and token quotas, errors name their source and code, and a 99.5% SLA covers paid use of models Tencent runs. Sign-up needs a Tencent Cloud account with real-name verification, prices are in CNY, no public status page was found, and 18 model retirement notices ran from April to October 2026." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/meta-model-api-vs-tencent-tokenhub", "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-tencent-tokenhub.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/meta-model-api-vs-tencent-tokenhub.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/meta-model-api-vs-tencent-tokenhub.min.md" }, "markdown": "Tencent Cloud TokenHub scores 59.5 (C) on agent readiness against Meta Model API's 52.3 (D), and leads in every scored category. Both do llm inference.\n\n- Meta Model API: grade D, 52.3/100, rank #905 of 1260. Markdown https://www.anchorterminal.com/tools/meta-model-api.md · JSON https://www.anchorterminal.com/api/v1/tools/meta-model-api.json\n- Tencent Cloud TokenHub: grade C, 59.5/100, rank #646 of 1260. Markdown https://www.anchorterminal.com/tools/tencent-tokenhub.md · JSON https://www.anchorterminal.com/api/v1/tools/tencent-tokenhub.json\n- Best model APIs and inference for AI agents: https://www.anchorterminal.com/best/inference/index.md\n- All 529 models comparisons: https://www.anchorterminal.com/compare/inference/index.md\n\n## Which one, for what\n\n### Meta Model API (D)\n\nGood for: Long-running agent and coding work over text, images, video, audio and PDFs with a 1M-token context, where training must stay off by default.\n\nAlso in its favour:\n- No incidents deducted, where Tencent Cloud TokenHub loses 3 points for them\n\nWatch for: Muse Wonder is labelled a preview, and no deprecation policy or notice period was found\n\n### Tencent Cloud TokenHub (C)\n\nGood for: Teams in or near Tencent Cloud that want one key and bill for Tencent's Hy models and Chinese open-weight models (DeepSeek, Kimi, GLM, MiniMax, Qwen, MiMo) with per-key limits and CNY billing.\n\nAhead on:\n- Reliability, 46 against 40\n- Schema \u0026 documentation, 73 against 60\n- Agent ergonomics, 83 against 75\n- Security \u0026 auth, 71 against 64\n- Payments \u0026 pricing, 35 against 20\n- Maintenance \u0026 community, 73 against 46\n\nWatch for: Sign-up needs a Tencent Cloud account with real-name verification. The international site answered with a bot check, so access from outside China was not established\n\n\n## Why the edge\n\n### Maintenance \u0026 community: Tencent Cloud TokenHub +27\n\n- Meta Model API (46): Model reading. Muse Wonder launched on 12 October 2026 (30). No deprecation policy or notice period found. All three Muse Spark versions are still served, so no retirement has tested one (0 of 12). Three dated launches in the last 90 days that we read, Muse Spark 1.2 on 5 August, Muse Code out of beta on 31 August and Muse Wonder on 12 October (8 of 8). No Model API changelog. A help centre with support tickets, answered 'typically within two business days' by Meta's own account, which we didn't test (8 of 15). No SDK of Meta's own for the API (0 of 15, 0 of 10).\n- Tencent Cloud TokenHub (73): Closed service, read on the model lines. The newest release note is dated 24 October 2026 and the price page was updated on 31 October (30). The four retirement notices read gave 21 to 33 days, and eligible callers are switched to a successor at its price. No minimum notice period is written, and DeepSeek-V4.1-Flash (directly supplied) was moved to the 1017 version under the same ids on 17 October 2026 in a notice dated two days later (7 of 12). 18 retirement notices from 21 April to 22 October 2026, 12 of them since 3 August (3 of 8). Dated release notes and announcements, ticket and phone support around the clock and a Q\u0026A community (13 of 15). Replies on the THCLI repository were not sampled (3 of 10). Tencent Cloud SDK 3.0 in several languages covers the control plane and `tencent-tokenhub-cli` 1.0.2 was published on 30 October 2026. No inference SDK of its own (12 of 15). The CLI has four releases since 15 September 2026, lists no runtime dependencies and needs Node.js 18 or later. CI not checked (5 of 10).\n\n### Payments \u0026 pricing: Tencent Cloud TokenHub +15\n\n- Meta Model API (20): No machine payment protocol (0). Per-token prices for Muse Wonder and Muse Spark, and per-image, per-hour and per-frame prices for the other models, published without a login (20). No free API allowance found. Billing needs a card, and Playground requests count towards usage (0). Browser sign-up with email, phone, Facebook, Google or GitHub (0).\n- Tencent Cloud TokenHub (35): No x402, MPP or L402 (0). Per-token prices for every model are public in CNY for Guangzhou and Singapore, with DeepSeek's peak and off-peak rates (20). Each account gets 1M free tokens per language model, valid for a year, in a campaign running to 31 December 2026. No card is mentioned, but the account needs real-name verification, so this line takes 15 of 20. A person signs up and completes real-name verification in a browser. Keys can then be created in code or by `thcli auth login`, but only from that account (0).\n\n### Schema \u0026 documentation: Tencent Cloud TokenHub +13\n\n- Meta Model API (60): No OpenAPI or similar machine-readable contract found. The reference is Markdown pages with schema sections, and /openapi.json paths on dev.meta.ai return 404 (0). llms.txt at dev.meta.ai/llms.txt, and every docs page has a Markdown copy (10). The models page says when to choose Muse Wonder and when Muse Spark, and the tool-calling and structured-output guides state their limits, such as `tool_choice` only accepting `auto` and which schema keywords `strict` allows (16 of 20). JSON Schema tools and output, `reasoning_effort` an enum from minimal to max, a strict subset that returns 400 when violated, though `tool_choice` has one value (12 of 15). Curl, Python and TypeScript examples on each page and an error guide covering 400 to 504 with the error envelope, codes and a fix for each (15). Versioned model IDs (muse-spark-1.1 to 1.3, muse-wonder-1.0) and dated launch posts on the developer blog, but no API changelog (7 of 15).\n- Tencent Cloud TokenHub (73): Router, scored on the API lines. No OpenAPI file for the inference routes. Field pages document the OpenAI Chat Completions, OpenAI Responses and Anthropic Messages formats as TokenHub implements them, and the control plane is a Tencent Cloud API 3.0 service (version 2026-03-22) with typed parameters, API Explorer and SDKs (12 of 25). An llms.txt at cloud.tencent.com/document/product/1823/llms.txt links a Markdown copy of each docs page (10). The docs say which models support thinking, tools, structured output and caching, how TokenHub departs from each standard protocol, and which DeepSeek model suits which job. The quickstart's examples still use `deepseek-v3`, which is not in the model list, and Qwen3.5 stays in the list with a past shutdown date (13 of 20). Protocol pages list each field with type, required flag and default, and control-plane parameters carry enums and required flags (10 of 15). Examples in curl, Python, Node.js, Java and Go, and an error page listing 30 codes with HTTP status, cause and fix (14 of 15). Paths carry `/v1`, release notes are dated monthly from 7 April to 24 October 2026, and the control-plane API has a dated history of 26 releases to 18 September 2026 (14 of 15).\n\n### Agent ergonomics: Tencent Cloud TokenHub +8\n\n- Meta Model API (75): Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Tool calls on all three endpoints, parallel calls, tool search with deferred loading, built-in web search and a computer-use tool, but `tool_choice` accepts only `auto`, so a call can't be forced or forbidden (15 of 20). Output constrained to the JSON Schema on every surface (15). Automatic prompt caching with no setup, and cached input at 5 per cent of the input price on Muse Wonder (15). 1,048,576-token context on Muse Wonder and every Muse Spark version, with no long-context premium (15). No batch endpoint or discount found. Background responses run asynchronously at the normal price (0). No SDK of Meta's own. The docs use the OpenAI and Anthropic SDKs against compatible endpoints, the same reading as StepFun (0). OpenAI-style error envelope with `type` and `code`, per-status fixes and named retryable codes (15).\n- Tencent Cloud TokenHub (83): Router, read on the model lines. Function calling is marked on most chat models in the model list, with behaviour depending on the model routed (14 of 20). Structured output is marked per model and missing on the MiniMax and Qwen models, and an unsupported `response_format` returns code 400006 (12 of 15). Cache-hit prices are published per model, Kimi K3.1 Pro lists five-minute and one-hour cache writes, and a guide covers `prompt_cache_key` and the `X-Session-ID` header for instance affinity (14 of 15). Most listed chat models have contexts of one million tokens, a judgement call since a router has no default model (15). Batch at half price covers only Hy3 and Hy4 preview, reads and writes JSONL in the customer's own COS bucket and is documented for the Guangzhou endpoint (5 of 10). No TokenHub inference SDK. The OpenAI and Anthropic SDKs work with a changed base URL, and Tencent Cloud SDK 3.0 and the `thcli` CLI cover the control plane (8 of 10). Errors return a code, English and Chinese messages, the source, the upstream code and status and a request ID, and stream errors arrive as SSE error frames (15 of 15).\n\n### Security \u0026 auth: Tencent Cloud TokenHub +7\n\n- Meta Model API (64): Model reading. Bearer keys per team, named, shown once and revoked by deletion, with rotation advice. No scopes, read-only keys or per-key limits found (20 of 30). The terms say Meta will not use Content submitted to the Standard Services to train Meta Models, and training applies only to the `-contributor` model IDs a caller picks. Content may still be used to develop and improve safety and security systems (17 of 20). Retention is 'as needed' for the service, the law, flagged violations and safety review, with no period stated. Zero data retention for qualified accounts through sales, with flagged content kept up to 2 years (10 of 15). The usage dashboard shows tokens and requests per day by model, with no per-key or per-call log found (5 of 15). No security.txt on dev.meta.ai. Meta's bug bounty at bugbounty.meta.com is named in the Muse Code SDK's security policy, and a security commitments page describes TLS 1.2 or later, PCI-DSS card handling and an ISMS, with no named certification for the API (12 of 20).\n- Tencent Cloud TokenHub (71): Router, read on the model lines. Bearer keys can be limited to chosen models and inference services, up to 200 source IP ranges and daily, monthly or total token quotas, can be disabled or deleted, and can be created in code through CreateApiKey with signed Tencent Cloud credentials. Keys are long-lived with no expiry setting or built-in rotation (26 of 30). Clause 2.17 of the terms says inputs are not used to train Tencent Cloud's own models, and the FAQ says data is not used for training. Inputs to third-party deployed models (DeepSeek's directly supplied ones) go to DeepSeek under its terms (14 of 20). Clause 2.14 keeps data only as long as the service needs, with no periods stated. When a customer asks for generated content without AI labels, Tencent Cloud keeps logs of who received it for at least six months. No zero-retention option was found (7 of 15). Per-call audit logs (request ID, key, client IP, status, tokens, latency) and optional full call logs go to the customer's CLS, billed separately, with usage by key and a monitoring dashboard (14 of 15). No security.txt on cloud.tencent.com, www.tencent.com or tokenhub.tencentmaas.com (404). Tencent's bug bounty through TSRC lists Tencent Cloud in scope. No certification for TokenHub was checked (10 of 20).\n\n### Reliability: Tencent Cloud TokenHub +6\n\n- Meta Model API (40): No status page with component history. The error guide's link to dev.meta.ai/status redirects to the home page, and `GET /v1/status` reports only the current state, `operational` when we called it on 12 October (0). No readable incident history (5). Rate limits published per team and per model, 3,000 RPM and 4,000,000 TPM for muse-wonder-1.0, 150 RPM for the contributor variants, 600 background submissions a minute (15). 429 and 503 carry Retry-After (60 seconds for `service_overloaded` and `backend_unavailable`), with backoff-with-jitter guidance, rate-limit headers on every token response and a documented mid-stream `server_shutting_down` event to retry (15). No SLA found, and the terms let Meta throttle or suspend access without notice (0). Muse Wonder is labelled a preview. Muse Spark 1.3 carries no preview label, but the API opened on 8 July 2026 as a public preview and we found no general-availability notice, so half (5 of 10, a departure from the all-or-nothing line).\n- Tencent Cloud TokenHub (46): Hosted reading. No public status page was found. status.cloud.tencent.com did not answer and the Tencent Cloud health dashboard documentation answered with a bot check (0). With no page there is no incident record to read (5 of 30). The announcements carry one incident, DeepSeek's directly supplied models unavailable from 9:06 to 13:04 Beijing time on 15 October 2026 after a fault at DeepSeek, compensated with vouchers. Rate limits are per model, shown in the console and returned by DescribeModelQuota. The public docs give numbers only for batch jobs (20 created a minute, 10 active), image models (5 concurrent) and DeepSeek V4 Flash and Pro (2,500 and 500 concurrent), with the rules for self-serve increases (8 of 15). Six 429 codes separate RPM, TPM, TPD, concurrency and upstream capacity, 429s may carry `Retry-After` and the docs advise exponential backoff. No idempotency guidance, though inference calls are not writes (13 of 15). The TokenHub SLA promises 99.5% monthly availability with vouchers of 10, 25 or 50 per cent of the month's fee. It excludes free use and third-party deployed models such as DeepSeek's directly supplied ones (10). Generally available since 7 April 2026, with some models marked preview (10).\n\n## Score by category\n\n| Category | Weight | Meta Model API | Tencent Cloud TokenHub | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 40 | 46 | Tencent Cloud TokenHub +6 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 60 | 73 | Tencent Cloud TokenHub +13 |\n| Agent ergonomics | 13% (16.2 this run) | 75 | 83 | Tencent Cloud TokenHub +8 |\n| Security \u0026 auth | 14% (17.5 this run) | 64 | 71 | Tencent Cloud TokenHub +7 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 35 | Tencent Cloud TokenHub +15 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 46 | 73 | Tencent Cloud TokenHub +27 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 53 | 54 | Tencent Cloud TokenHub +1 |\n| Negative events | ≤15 | 0 | -3 | |\n| **Total** | | **52.3 · D** | **59.5 · C** | |\n\n## Facts side by side\n\n| Fact | Meta Model API | Tencent Cloud TokenHub |\n| --- | --- | --- |\n| Kind | Model API | Model router |\n| Vendor | Meta | Tencent Cloud |\n| Hosted endpoint | `https://api.meta.ai/v1` | `https://tokenhub.tencentmaas.com/v1` |\n| Transports | HTTP | HTTP |\n| Auth | API key | API key |\n| Pricing | Pay per use | Pay per use |\n| x402 | no | no |\n| Licence | Closed service under the Meta Model API Terms of Service (last updated 9 October 2026), with Meta Platforms, Inc., or Meta Platforms Ireland Limited in the European Region, as the contracting party. | Proprietary service under the TokenHub Terms of Service, the TokenHub SLA and the Tencent Cloud Service Agreement, with a special note for third-party deployed models. The `tencent-tokenhub-cli` package is Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-12 | 2026-10-24 |\n| Terms last updated | 2026-10-02 | couldn't be read |\n| Privacy policy last updated | couldn't be read | couldn't be read |\n| Customer content may train models | yes | couldn't be read |\n| Terms restrict automated access | not found in the text | couldn't be read |\n| Terms restrict benchmarking | yes | couldn't be read |\n| Terms or service can change without notice | not found in the text | couldn't be read |\n| Arbitration or class-action waiver | yes | couldn't be read |\n| Popularity | none | 204 npm/wk |\n\n## How the scores have moved\n\n### Meta Model API\n\n- -0.2 on 30 October 2026: checklist\n- +0.3 on 27 October 2026: checklist\n\n### Tencent Cloud TokenHub\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Meta Model API.** Meta Model API serves Muse Wonder, in preview since 12 October 2026, and Muse Spark with 1M-token context, constrained JSON Schema output, automatic prompt caching and per-token prices published without a login. Standard-mode content is not used for training. There's no free allowance, status history, OpenAPI file, deprecation policy or way to force a tool call.\n\n**Tencent Cloud TokenHub.** Keys can be limited to chosen models, source IPs and token quotas, errors name their source and code, and a 99.5% SLA covers paid use of models Tencent runs. Sign-up needs a Tencent Cloud account with real-name verification, prices are in CNY, no public status page was found, and 18 model retirement notices ran from April to October 2026.\n\n## Before you call either\n\n### Meta Model API\n\n1. Use `muse-wonder-1.0` for long multi-step work and `muse-spark-1.3` for cheaper, high-volume calls. Both take the same requests\n2. Keep personal or confidential data away from `-contributor` model IDs. Meta may train on that content\n3. Honour Retry-After on 429 and 503, which is 60 seconds for `service_overloaded`, and check `GET https://api.meta.ai/v1/status`, which needs no key\n4. Pass the key to the OpenAI SDK explicitly or set `OPENAI_API_KEY`. The SDK doesn't read `MODEL_API_KEY`\n5. Leave `tool_choice` at `auto`. The docs say `none` and `required` are not supported\n\n### Tencent Cloud TokenHub\n\n1. Use `https://tokenhub.tencentmaas.com/v1` with keys made for Guangzhou and `https://tokenhub-intl.tencentmaas.com/v1` with keys made for Singapore. Keys do not work across the two\n2. Send the key as `Authorization: Bearer` on the OpenAI paths and as `x-api-key` on `/v1/messages`\n3. Parse `error.code` as a string or a number, since 429 codes can come back as integers, and wait for `Retry-After` before retrying\n4. Take model ids from `GET /v1/models` and watch for `pre-offline`. The quickstart's `deepseek-v3` example is not in the current model list\n5. Expect DeepSeek prices to double on weekdays from 9am to noon and 2pm to 6pm Beijing time, when the peak rate applies\n\n## Questions\n\n### Which is better for AI agents, Meta Model API or Tencent Cloud TokenHub?\n\nTencent Cloud TokenHub scores 59.5 (C) on agent readiness against Meta Model API's 52.3 (D), and leads in every scored category.\n\n### Do Meta Model API and Tencent Cloud TokenHub need an API key?\n\nBoth need an API key.\n\n### Can an agent call Meta Model API and Tencent Cloud TokenHub without installing anything?\n\nYes. Meta Model API has a hosted endpoint at https://api.meta.ai/v1 and Tencent Cloud TokenHub at https://tokenhub.tencentmaas.com/v1.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/meta-model-api-vs-tencent-tokenhub.json, and with the fewest tokens: https://www.anchorterminal.com/compare/meta-model-api-vs-tencent-tokenhub.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"meta-model-api\", \"b\": \"tencent-tokenhub\"}`. From a terminal: `anchor compare meta-model-api tencent-tokenhub`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/meta-model-api.json and https://www.anchorterminal.com/api/v1/tools/tencent-tokenhub.json\n\n## Other comparisons with Meta Model API or Tencent Cloud TokenHub\n\n- [Claude API vs Meta Model API](https://www.anchorterminal.com/compare/anthropic-api-vs-meta-model-api.md)\n- [Claude API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/anthropic-api-vs-tencent-tokenhub.md)\n- [Antseed vs Meta Model API](https://www.anchorterminal.com/compare/antseed-vs-meta-model-api.md)\n- [BlockRun.AI vs Meta Model API](https://www.anchorterminal.com/compare/blockrun-ai-vs-meta-model-api.md)\n- [BlockRun.AI vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/blockrun-ai-vs-tencent-tokenhub.md)\n- [Cerebras Inference vs Meta Model API](https://www.anchorterminal.com/compare/cerebras-inference-vs-meta-model-api.md)\n- [Cerebras Inference vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/cerebras-inference-vs-tencent-tokenhub.md)\n- [Cloudflare AI Gateway vs Meta Model API](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-meta-model-api.md)\n- [Cloudflare AI Gateway vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-tencent-tokenhub.md)\n- [Cloudflare Workers AI vs Meta Model API](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-meta-model-api.md)\n- [Cloudflare Workers AI vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-tencent-tokenhub.md)\n- [Cohere Chat API (Command models) vs Meta Model API](https://www.anchorterminal.com/compare/cohere-chat-vs-meta-model-api.md)\n- [Cohere Chat API (Command models) vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/cohere-chat-vs-tencent-tokenhub.md)\n- [DeepInfra vs Meta Model API](https://www.anchorterminal.com/compare/deepinfra-vs-meta-model-api.md)\n- [DeepInfra vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/deepinfra-vs-tencent-tokenhub.md)\n- [DeepSeek API vs Meta Model API](https://www.anchorterminal.com/compare/deepseek-api-vs-meta-model-api.md)\n- [DeepSeek API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/deepseek-api-vs-tencent-tokenhub.md)\n- [Glimpse vs Meta Model API](https://www.anchorterminal.com/compare/elorian-glimpse-vs-meta-model-api.md)\n- [Glimpse vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/elorian-glimpse-vs-tencent-tokenhub.md)\n- [Fireworks AI Inference vs Meta Model API](https://www.anchorterminal.com/compare/fireworks-inference-vs-meta-model-api.md)\n- [Fireworks AI Inference vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/fireworks-inference-vs-tencent-tokenhub.md)\n- [Gemini Developer API vs Meta Model API](https://www.anchorterminal.com/compare/gemini-api-vs-meta-model-api.md)\n- [Gemini Developer API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/gemini-api-vs-tencent-tokenhub.md)\n- [GroqCloud vs Meta Model API](https://www.anchorterminal.com/compare/groq-vs-meta-model-api.md)\n- [GroqCloud vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/groq-vs-tencent-tokenhub.md)\n- [Jais 3 vs Meta Model API](https://www.anchorterminal.com/compare/jais-3-vs-meta-model-api.md)\n- [Jais 3 vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/jais-3-vs-tencent-tokenhub.md)\n- [Meta Model API vs MiniMax API](https://www.anchorterminal.com/compare/meta-model-api-vs-minimax-api.md)\n- [Meta Model API vs Mistral AI API](https://www.anchorterminal.com/compare/meta-model-api-vs-mistral-api.md)\n- [Meta Model API vs Muse Spark Open](https://www.anchorterminal.com/compare/meta-model-api-vs-muse-spark-open.md)\n- [Meta Model API vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/meta-model-api-vs-nemotron-3-5-super-vl.md)\n- [Meta Model API vs Novita AI](https://www.anchorterminal.com/compare/meta-model-api-vs-novita-ai.md)\n- [Meta Model API vs OpenAI API](https://www.anchorterminal.com/compare/meta-model-api-vs-openai-api.md)\n- [Meta Model API vs OpenRouter](https://www.anchorterminal.com/compare/meta-model-api-vs-openrouter.md)\n- [Meta Model API vs Prism Inference](https://www.anchorterminal.com/compare/meta-model-api-vs-prism-inference.md)\n- [Meta Model API vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/meta-model-api-vs-ramp-router.md)\n- [Meta Model API vs Beam 1.0](https://www.anchorterminal.com/compare/meta-model-api-vs-reflection-beam.md)\n- [Meta Model API vs RouterPlus](https://www.anchorterminal.com/compare/meta-model-api-vs-routerplus.md)\n- [Meta Model API vs SambaCloud](https://www.anchorterminal.com/compare/meta-model-api-vs-sambanova.md)\n- [Meta Model API vs SiliconFlow](https://www.anchorterminal.com/compare/meta-model-api-vs-siliconflow.md)\n- [Meta Model API vs Simplismart](https://www.anchorterminal.com/compare/meta-model-api-vs-simplismart.md)\n- [Meta Model API vs StepFun API](https://www.anchorterminal.com/compare/meta-model-api-vs-stepfun-api.md)\n- [Meta Model API vs Together AI Inference](https://www.anchorterminal.com/compare/meta-model-api-vs-together-inference.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 Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/minimax-api-vs-tencent-tokenhub.md)\n- [Mistral AI API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/mistral-api-vs-tencent-tokenhub.md)\n- [Muse Spark Open vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/muse-spark-open-vs-tencent-tokenhub.md)\n- [Novita AI vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/novita-ai-vs-tencent-tokenhub.md)\n- [OpenAI API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/openai-api-vs-tencent-tokenhub.md)\n- [OpenRouter vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/openrouter-vs-tencent-tokenhub.md)\n- [Beam 1.0 vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/reflection-beam-vs-tencent-tokenhub.md)\n- [SambaCloud vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/sambanova-vs-tencent-tokenhub.md)\n- [SiliconFlow vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/siliconflow-vs-tencent-tokenhub.md)\n- [Simplismart vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/simplismart-vs-tencent-tokenhub.md)\n- [StepFun API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/stepfun-api-vs-tencent-tokenhub.md)\n- [Tencent Cloud TokenHub vs Together AI Inference](https://www.anchorterminal.com/compare/tencent-tokenhub-vs-together-inference.md)\n- [Nemotron 3.5 Super VL vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-tencent-tokenhub.md)\n- [Prism Inference vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/prism-inference-vs-tencent-tokenhub.md)\n- [Antseed vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/antseed-vs-tencent-tokenhub.md)\n- [Router.com (Ramp Router) vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/ramp-router-vs-tencent-tokenhub.md)\n- [RouterPlus vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/routerplus-vs-tencent-tokenhub.md)\n- [Tencent Cloud TokenHub vs Vercel AI Gateway](https://www.anchorterminal.com/compare/tencent-tokenhub-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": "2026-11-02", "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": "Meta Model API vs Tencent Cloud TokenHub", "url": "" } ], "description": "Tencent Cloud TokenHub scores 59.5 (C) to Meta Model's 52.3 (D) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Meta Model API D 52.3", "Tencent Cloud TokenHub C 59.5", "scores" ], "h1": "Meta Model API vs Tencent Cloud TokenHub", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/meta-model-api-vs-tencent-tokenhub", "published": "2026-10-01", "section": "tools", "title": "Meta Model vs Tencent Cloud TokenHub for AI agents (2026)", "toc": null, "updated": "2026-11-01", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-tencent-tokenhub" }, "tokens": { "markdown": 6850, "slim": 3730 }, "version": 1 }