{ "data": { "a": { "slug": "muse-spark-open", "name": "Muse Spark Open", "vendor": "Meta", "vendorUrl": "https://dev.meta.ai/models/muse-spark-open", "kind": "model", "category": "inference", "summary": "Muse Spark Open is Meta's open-weight multimodal model for coding and agentic work, with 816B total and 42B active parameters and a 1M-token context, released on 15 October 2026 under the Muse Model Licence for self-hosting.", "url": "https://www.anchorterminal.com/tools/muse-spark-open", "markdownUrl": "https://www.anchorterminal.com/tools/muse-spark-open.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/muse-spark-open.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/muse-spark-open.json", "dns": "muse-spark-open.grade.anchorterminal.com", "repo": "https://huggingface.co/meta-models/Muse-Spark-Open-816B-A42B", "license": "Muse Model Licence (source-available weights, not an OSI licence), free of charge with an attribution notice, a separate agreement with Meta before Model as a Service by a licensee group above $20M gross revenue, and the Muse Spark Open Usage Policy", "transports": [ "http" ], "packages": [], "auth": "none", "authNotes": "Running the model needs no account or key. Getting Meta's weights does. Both Hugging Face repositories (BF16 and NVFP4) are gated with manual review and ask for full legal name, date of birth, country, affiliation and job title, and downloads then use a Hugging Face access token. The GGUF quantisations from ggml-org and Unsloth that Meta's docs point to are not gated. A local server has whatever authentication the owner adds, such as llama.cpp's `--api-key`.", "pricing": "free", "pricingNotes": "Free to download and run under the Muse Model Licence, with the owner's GPUs as the cost. A licensee whose group has more than $20M gross revenue in any 12 months must notify Meta and sign a separate agreement before offering it as Model as a Service. Hosted copies cost $1.25 input, $0.15 cached input and $4.25 output per million tokens on Fireworks, Baseten, Modal and OpenRouter (checked 2026-10-15). Meta Model API does not serve it.", "priceSummary": "from $1.25 / 1M in", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402. Muse Spark Open is a model the owner runs, with no payment route from Meta, and Meta Model API does not serve it (checked 2026-10-15).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-15" }, "docsUrl": "https://dev.meta.ai/docs/muse-spark-open", "llmsTxt": "https://dev.meta.ai/llms.txt", "capabilities": [ "inference.llm", "inference.open-weights", "inference.local" ], "tags": [ "model", "open-weights", "self-hosted", "local", "free", "gated", "multimodal", "openai-compatible", "llms-txt", "gpu", "new" ], "lastRelease": "2026-10-15", "graded": true, "anchor": { "graded": true, "score": 53.4, "grade": "D", "agentReady": false, "rank": 863, "ranked": true, "rankOf": 1260, "categoryRank": 24, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 69, "maintenance": 60, "payments": 50, "reliability": 42, "schema": 61, "security": 44, "transparency": 53 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-15" }, "negative": 0, "verdict": "Muse Spark Open runs on the owner's hardware in seven runtimes, with OpenAI-compatible servers in vLLM and SGLang, standard tool calls, a 1M-token context and Meta's own serving docs. Serving the 537 GB NVFP4 checkpoint takes four B300 GPUs, Meta's download is gated by manual review, and the licence adds attribution and a revenue threshold for model resellers.", "bestFor": "A team with a four-GPU Blackwell node, or two to four Mac Studios, that wants a 1M-token multimodal coding and agent model on its own hardware with no prompts leaving it.", "strengths": [ "816B total and 42B active parameters with a 1,048,576-token context, taking text, image, video and audio input", "Day-one support in vLLM, SGLang, TensorRT-LLM, Transformers, llama.cpp, MLX and Unsloth, with commands for each in Meta's docs", "With the `muse` parsers, reasoning comes back in its own field and tool calls as a standard `tool_calls` array", "The licence grants use, fine-tuning, distillation and resale free of charge, with no user cap and no regional exclusion", "llms.txt and Markdown docs cover checkpoints, prompting, stop tokens, recommended settings and post-training" ], "weaknesses": [ "The NVFP4 checkpoint (about 537 GB) serves on four B300 GPUs and the BF16 one (about 1.65 TB) on eight", "Meta's Hugging Face repositories need manual approval with legal name and date of birth, which the Get the model page doesn't mention", "Products must display \"Built with Muse Spark Open\", and a company group with over $20M revenue needs Meta's agreement to offer it as Model as a Service", "The Usage Policy rules out military, nuclear, espionage, critical infrastructure and heavy machinery uses, and users under 18", "Released on 15 October 2026, with no changelog, deprecation policy or CI found, and the full evaluation report not yet published" ], "agentNotes": [ "Start vLLM or SGLang with `--reasoning-parser muse --tool-call-parser muse` (vLLM also `--enable-auto-tool-choice`), or tool calls come back as raw text", "Set `reasoning_effort` to `low` or `medium` for short tasks. The default is `xhigh`, reasoning can't be turned off, and other values return an error", "Stop only on `\u003c|eot|\u003e` and end of text. Stopping on `\u003c|eom|\u003e` cuts off tool calls and final answers", "Stream long generations and leave `max_tokens` room for reasoning, or `content` can come back empty with `finish_reason` `length`", "Don't call Meta Model API for this model. Use a self-hosted server or a hosted provider's model string, such as `meta-models/muse-spark-open`" ], "metrics": { "kind": "local", "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": 53.4 } ], "editorialScores": { "ergonomics": 69, "maintenance": 60, "payments": 50, "reliability": 42, "schema": 61, "security": 44, "transparency": 50 }, "provenanceScore": 55, "checked": { "categories": { "ergonomics": "2026-10-15", "maintenance": "2026-10-15", "payments": "2026-10-15", "reliability": "2026-10-15", "schema": "2026-10-15", "security": "2026-10-15", "transparency": "2026-10-15" }, "last": "2026-10-15", "lastMoved": "2026-10-30", "oldest": "2026-10-15", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "hf download meta-models/Muse-Spark-Open-816B-A42B-NVFP4 --local-dir ./muse-spark-open-nvfp4\n\nexport VLLM_USE_RUST_FRONTEND=1\nvllm serve meta-models/Muse-Spark-Open-816B-A42B-NVFP4 \\\n --tensor-parallel-size 4 \\\n --enable-expert-parallel \\\n --max-model-len 1048576 \\\n --reasoning-parser muse \\\n --tool-call-parser muse \\\n --enable-auto-tool-choice", "http": "curl http://localhost:8000/v1/chat/completions \\\n -H 'Content-Type: application/json' \\\n -d '{\n \"model\": \"meta-models/Muse-Spark-Open-816B-A42B-NVFP4\",\n \"messages\": [{\"role\": \"user\", \"content\": \"Refactor this module.\"}],\n \"reasoning_effort\": \"xhigh\"\n }'" }, "letme": { "capability": "https://letme.dev/inference.llm", "tool": "https://letme.dev/muse-spark-open" }, "sameCompany": [ "meta-model-api", "muse-code", "muse-glimmer-30b" ], "family": { "lab": "Meta", "family": "Muse", "url": "https://www.anchorterminal.com/open-weights/#meta", "others": [ { "name": "Muse Glimmer 30B", "url": "https://huggingface.co/meta-models/Muse-Glimmer-30B", "params": "30B (dense, multimodal)", "listing": "https://www.anchorterminal.com/tools/muse-glimmer-30b" }, { "name": "Muse Glimmer 30B assistant (DFlash drafter)", "url": "https://huggingface.co/meta-models/Muse-Glimmer-30B-assistant", "params": "2.56B (Hub safetensors count; the card states no figure)" } ], "olderCount": 50, "unrestrictedCopies": 1 }, "area": "models", "provenance": { "legalEntity": "Meta Platforms, Inc.", "domain": "meta.ai", "domainRegistered": "2017-12-16", "endpointOnVendorDomain": null, "terms": "https://huggingface.co/meta-models/Muse-Spark-Open-816B-A42B/blob/main/LICENSE.md", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-15", "notes": [ "The licence names Meta Platforms, Inc. as copyright holder, and defines Meta as Meta Platforms Ireland Limited for licensees in the European region and Meta Platforms, Inc. elsewhere. The model card names the same two as model provider.", "The licence is the document that governs use of the weights, so it is recorded as the terms. LICENSE.md matches the text shown on the gated access form word for word. The Usage Policy is its Exhibit A. The separate USE_POLICY.md that Meta's docs link answered 401 without access and wasn't read.", "No privacy policy governs the model, because the owner runs it and no input reaches Meta. The access form says its details are handled under the Meta Privacy Policy on www.facebook.com, whose robots.txt asks readers like ours not to fetch it, so it wasn't read.", "The domain is meta.ai, where Meta's developer docs (dev.meta.ai) and research post (research.meta.ai) sit, the same as the meta-model-api and muse-code listings. RDAP gives a registration date of 16 December 2017.", "No hosted endpoint from Meta, so no status page. No changelog for the model was found, and the Hugging Face commit history needs access to read.", "dev.meta.ai/.well-known/security.txt and research.meta.ai/.well-known/security.txt returned 404 on 15 October 2026.", "WebFetch read the research post. It refused the Hugging Face model card as outside its allowed set, so the card, LICENSE.md, the repository and collection metadata, the discussions, the evaluation methodology PDF, Meta's docs pages and the providers' model pages were read with curl." ], "score": 55 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/muse-spark-open.json", "live": { "slug": "muse-spark-open", "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": "2026-11-01T15:14:28.699045812Z" }, "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://huggingface.co/meta-models/Muse-Spark-Open-816B-A42B/blob/main/LICENSE.md", "kind": "terms", "status": 200, "checkedAt": "2026-11-01T06:46:21.900064433Z", "changedAt": "2026-11-01T06:46:21.900064433Z", "fingerprint": "c932eccddb04" } ], "models": { "meta/muse-spark-open": { "openrouterId": "meta/muse-spark-open", "tools": true, "structuredOutputs": true, "jsonMode": true, "reasoning": true, "input": [ "audio", "file", "image", "text", "video" ], "promptCaching": true, "contextTokens": 1048576, "maxOutput": 131072, "checkedAt": "2026-11-01T23:49:20.31928442Z" } }, "updatedAt": "2026-11-01T23:49:20.31928442Z" } }, "answer": "Tencent Cloud TokenHub scores 59.5 (C) on agent readiness against Muse Spark Open's 53.4 (D), and leads in 6 of 7 scored categories. Muse Spark Open leads on payments \u0026 pricing.", "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": "security", "leads": "tencent-tokenhub", "name": "Security \u0026 auth", "reasons": { "a": "Read as software the owner runs. No account or key to run it. Meta's weights need manual approval on Hugging Face and an access token, and server authentication is the owner's to add (12 of 30). An agent model that calls whatever tools the operator gives it. The card recommends human-in-the-loop confirmation for irreversible actions and Meta reports agentic-risk evaluations, but nothing in the model or template enforces an approval (8 of 20). The chat template neutralises special-token sequences and media placeholders in caller text and wraps tool results in `\u003ctool_output\u003e`, and the card advises protecting internal assistant messages and layering defences against adversarial input. No indirect prompt-injection results are published (10 of 15). No call log of its own. Visibility depends on the serving stack (5 of 15). Weights are safetensors that load through Transformers' own classes from 5.19, and Meta published cyber, chemical, biological and misalignment evaluations. No security.txt on dev.meta.ai or research.meta.ai, and no security route on the card or in the docs, only museoss@meta.com and the Hugging Face discussions (9 of 20). 44.", "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": 44, "b": 71 } }, { "by": 15, "category": "payments", "leads": "muse-spark-open", "name": "Payments \u0026 pricing", "reasons": { "a": "Self-hosted rule. Nothing to buy from Meta, and the licence grants use free of charge. The Model as a Service clause asks for a separate agreement only from licensee groups above $20M gross revenue in 12 months (20). Free to run with no card (20). Meta's own weights need a manually reviewed form with legal name and date of birth, so an agent can't get them alone. The ungated GGUF quantisations from ggml-org and Unsloth that Meta's docs point to download without approval, so part of the line (10 of 20). No payment protocol (0). Hosted copies at $1.25 input and $4.25 output per million tokens need each provider's own account and are not graded. 50.", "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": 50, "b": 35 } }, { "by": 14, "category": "ergonomics", "leads": "tencent-tokenhub", "name": "Agent ergonomics", "reasons": { "a": "Model reading of the checklist (tool use, structured output, caching, context, throughput, defaults and SDKs, errors). OpenAI-format tools and parallel calls come back as `tool_calls`, and the template supports namespaced tools and deferred loading through a `tool_search` tool. A forced `tool_choice` is not documented (17 of 20). JSON mode and JSON Schema come from each runtime's guided decoding, which Meta's docs show for TensorRT-LLM only (8 of 15). Prefix caching is the runtime's. Meta's SGLang command turns on hierarchical caching, and Dynamo routes each request to the worker holding its cached context (8 of 10). 1,048,576-token context, with sliding-window attention on 46 of 62 layers holding KV memory down (15 of 15). Draft models for speculative decoding in SGLang and vLLM, and no batch mode of its own (7 of 10). Any OpenAI SDK works against a local server, but reasoning can't be turned off, defaults to the most expensive level, and needs streaming, a `max_tokens` budget for reasoning and the right stop tokens (6 of 15). The template raises named errors for an unsupported reasoning effort, tool arguments passed as a string and a tool message with no name. Server errors are the runtime's (8 of 15). 69.", "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": 69, "b": 83 } }, { "by": 13, "category": "maintenance", "leads": "tencent-tokenhub", "name": "Maintenance \u0026 community", "reasons": { "a": "Read for an open-weight model released today. Released on 15 October 2026 (30). One release, BF16 and NVFP4 on the same day, with no history of revisions, successors or notice periods, and Meta Model API has no deprecation policy either (6 of 20). Three Hugging Face discussions opened on release day had no reply from Meta when read. Feedback goes to the discussions or museoss@meta.com, and Meta's docs and developer blog carry dated posts (8 of 25). Day-one support in vLLM, SGLang, TensorRT-LLM, Transformers, llama.cpp, MLX and Unsloth with Meta's own recipes, though SGLang's is a dev image and TensorRT-LLM's a feature branch (12 of 15). Current dependencies (Transformers 5.19), but no CI visible to us (4 of 10). 60.", "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": 60, "b": 73 } }, { "by": 12, "category": "schema", "leads": "tencent-tokenhub", "name": "Schema \u0026 documentation", "reasons": { "a": "Read for a model the owner serves. No specification of its own. The contract is the Jinja chat template, which renders OpenAI-format tools with `additionalProperties: false` added and rejects bad values, plus the OpenAI-compatible servers in vLLM and SGLang with the `muse` parsers (10 of 25). dev.meta.ai/llms.txt lists eight Muse Spark Open pages, each with a Markdown copy (10). The card lists seven intended uses and six limitations, the docs say when to pick BF16 or NVFP4 and which reasoning strength suits which task, and the Usage Policy states what is out of scope (17 of 20). `reasoning_effort` is an enum of four values and anything else returns an error, and tools take JSON Schema. Structured output is documented only for TensorRT-LLM's `response_format`, not in the prompting guide or for vLLM and SGLang (11 of 15). curl and Python examples for every runtime and hosted provider, the rendered prompt for each case, and the template's own error messages, but no error reference for a served model (11 of 15). One release, with no changelog or version scheme beyond the licence's version line, Muse Spark Open (2 of 15). 61.", "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": 61, "b": 73 } } ], "facts": [ { "a": "Model API", "b": "Model router", "name": "Kind" }, { "a": "Meta", "b": "Tencent Cloud", "name": "Vendor" }, { "a": "no (local only)", "b": "https://tokenhub.tencentmaas.com/v1", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "None", "b": "API key", "name": "Auth" }, { "a": "Free", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Muse Model Licence (source-available weights, not an OSI licence), free of charge with an attribution notice, a separate agreement with Meta before Model as a Service by a licensee group above $20M gross revenue, and the Muse Spark Open Usage Policy", "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": "2026-10-15", "b": "2026-10-24", "name": "Last release" }, { "a": "2026-10-15", "b": "couldn't be read", "name": "Terms last updated" }, { "a": "no document linked", "b": "couldn't be read", "name": "Privacy policy last updated" }, { "a": "not found in the text", "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": "not found in the text", "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": "not found in the text", "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 Muse Spark Open's 53.4 (D), and leads in 6 of 7 scored categories. Muse Spark Open leads on payments \u0026 pricing.", "question": "Which is better for AI agents, Muse Spark Open or Tencent Cloud TokenHub?" }, { "answer": "Muse Spark Open needs no key. Tencent Cloud TokenHub needs an API key.", "question": "Do Muse Spark Open and Tencent Cloud TokenHub need an API key?" }, { "answer": "No hosted endpoint is listed for Muse Spark Open. Tencent Cloud TokenHub has a hosted endpoint at https://tokenhub.tencentmaas.com/v1.", "question": "Can an agent call Muse Spark Open and Tencent Cloud TokenHub without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Payments \u0026 pricing, 50 against 35" ], "also": [ "No key needed to call it", "No incidents deducted, where Tencent Cloud TokenHub loses 3 points for them" ], "goodFor": "A team with a four-GPU Blackwell node, or two to four Mac Studios, that wants a 1M-token multimodal coding and agent model on its own hardware with no prompts leaving it.", "slug": "muse-spark-open", "watchFor": "The NVFP4 checkpoint (about 537 GB) serves on four B300 GPUs and the BF16 one (about 1.65 TB) on eight" }, { "aheadOn": [ "Schema \u0026 documentation, 73 against 61", "Agent ergonomics, 83 against 69", "Security \u0026 auth, 71 against 44", "Maintenance \u0026 community, 73 against 60" ], "also": [ "A hosted endpoint, with nothing to install" ], "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": { "muse-spark-open": [ { "causes": [ "method" ], "date": "2026-10-30", "delta": -0.1, "from": 53.5, "fromGrade": "D", "to": 53.4, "toGrade": "D" }, { "causes": [ "evidence" ], "date": "2026-10-28", "delta": 0, "from": 53.5, "fromGrade": "D", "to": 53.5, "toGrade": "D" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 53.4, "fromGrade": "D", "to": 53.5, "toGrade": "D" } ], "tencent-tokenhub": null }, "job": { "capability": "inference.llm", "name": "LLM inference" }, "others": [ { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-muse-spark-open.json", "title": "Claude API vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-muse-spark-open" }, { "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-muse-spark-open.json", "title": "Antseed vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/antseed-vs-muse-spark-open" }, { "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-muse-spark-open.json", "title": "BlockRun.AI vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-muse-spark-open" }, { "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-muse-spark-open.json", "title": "Cerebras Inference vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-muse-spark-open" }, { "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-muse-spark-open.json", "title": "Cloudflare AI Gateway vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-muse-spark-open" }, { "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-muse-spark-open.json", "title": "Cloudflare Workers AI vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-muse-spark-open" }, { "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-muse-spark-open.json", "title": "Cohere Chat API (Command models) vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-muse-spark-open" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-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-muse-spark-open.json", "title": "DeepInfra vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/deepinfra-vs-muse-spark-open" }, { "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-muse-spark-open.json", "title": "DeepSeek API vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-muse-spark-open" }, { "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-muse-spark-open.json", "title": "Glimpse vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-muse-spark-open" }, { "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-muse-spark-open.json", "title": "Fireworks AI Inference vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-muse-spark-open" }, { "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-muse-spark-open.json", "title": "Gemini Developer API vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/gemini-api-vs-muse-spark-open" }, { "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-muse-spark-open.json", "title": "GroqCloud vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/groq-vs-muse-spark-open" }, { "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-muse-spark-open.json", "title": "Jais 3 vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/jais-3-vs-muse-spark-open" }, { "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-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-tencent-tokenhub.json", "title": "Meta Model API vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/minimax-api-vs-muse-spark-open.json", "title": "MiniMax API vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/minimax-api-vs-muse-spark-open" }, { "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-muse-spark-open.json", "title": "Mistral AI API vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-muse-spark-open" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-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-nemotron-3-5-super-vl.json", "title": "Muse Spark Open vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-novita-ai.json", "title": "Muse Spark Open vs Novita AI", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-novita-ai" }, { "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-openai-api.json", "title": "Muse Spark Open vs OpenAI API", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-openai-api" }, { "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-openrouter.json", "title": "Muse Spark Open vs OpenRouter", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-openrouter" }, { "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-prism-inference.json", "title": "Muse Spark Open vs Prism Inference", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-ramp-router.json", "title": "Muse Spark Open vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-reflection-beam.json", "title": "Muse Spark Open vs Beam 1.0", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-reflection-beam" }, { "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-routerplus.json", "title": "Muse Spark Open vs RouterPlus", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-routerplus" }, { "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-sambanova.json", "title": "Muse Spark Open vs SambaCloud", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-sambanova" }, { "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-siliconflow.json", "title": "Muse Spark Open vs SiliconFlow", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-siliconflow" }, { "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-simplismart.json", "title": "Muse Spark Open vs Simplismart", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-simplismart" }, { "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-stepfun-api.json", "title": "Muse Spark Open vs StepFun API", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-stepfun-api" }, { "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-together-inference.json", "title": "Muse Spark Open vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-together-inference" }, { "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/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": 4, "edge": "tencent-tokenhub", "key": "reliability", "muse-spark-open": 42, "name": "Reliability", "tencent-tokenhub": 46, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 12, "edge": "tencent-tokenhub", "key": "schema", "muse-spark-open": 61, "name": "Schema \u0026 documentation", "tencent-tokenhub": 73, "weight": 13 }, { "by": 14, "edge": "tencent-tokenhub", "key": "ergonomics", "muse-spark-open": 69, "name": "Agent ergonomics", "tencent-tokenhub": 83, "weight": 13 }, { "by": 27, "edge": "tencent-tokenhub", "key": "security", "muse-spark-open": 44, "name": "Security \u0026 auth", "tencent-tokenhub": 71, "weight": 14 }, { "by": 15, "edge": "muse-spark-open", "key": "payments", "muse-spark-open": 50, "name": "Payments \u0026 pricing", "tencent-tokenhub": 35, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 13, "edge": "tencent-tokenhub", "key": "maintenance", "muse-spark-open": 60, "name": "Maintenance \u0026 community", "tencent-tokenhub": 73, "weight": 7 }, { "by": 1, "edge": "tencent-tokenhub", "key": "transparency", "muse-spark-open": 53, "name": "Transparency \u0026 trust", "tencent-tokenhub": 54, "weight": 7 } ], "summary": "Tencent Cloud TokenHub scores 59.5 (C) on agent readiness against Muse Spark Open's 53.4 (D), and leads in 6 of 7 scored categories. Muse Spark Open leads on payments \u0026 pricing. Both do llm inference.", "tasks": null, "tutorials": [], "verdicts": { "muse-spark-open": "Muse Spark Open runs on the owner's hardware in seven runtimes, with OpenAI-compatible servers in vLLM and SGLang, standard tool calls, a 1M-token context and Meta's own serving docs. Serving the 537 GB NVFP4 checkpoint takes four B300 GPUs, Meta's download is gated by manual review, and the licence adds attribution and a revenue threshold for model resellers.", "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/muse-spark-open-vs-tencent-tokenhub", "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-tencent-tokenhub.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/muse-spark-open-vs-tencent-tokenhub.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/muse-spark-open-vs-tencent-tokenhub.min.md" }, "markdown": "Tencent Cloud TokenHub scores 59.5 (C) on agent readiness against Muse Spark Open's 53.4 (D), and leads in 6 of 7 scored categories. Muse Spark Open leads on payments \u0026 pricing. Both do llm inference.\n\n- Muse Spark Open: grade D, 53.4/100, rank #863 of 1260. Markdown https://www.anchorterminal.com/tools/muse-spark-open.md · JSON https://www.anchorterminal.com/api/v1/tools/muse-spark-open.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### Muse Spark Open (D)\n\nGood for: A team with a four-GPU Blackwell node, or two to four Mac Studios, that wants a 1M-token multimodal coding and agent model on its own hardware with no prompts leaving it.\n\nAhead on:\n- Payments \u0026 pricing, 50 against 35\n\nAlso in its favour:\n- No key needed to call it\n- No incidents deducted, where Tencent Cloud TokenHub loses 3 points for them\n\nWatch for: The NVFP4 checkpoint (about 537 GB) serves on four B300 GPUs and the BF16 one (about 1.65 TB) on eight\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- Schema \u0026 documentation, 73 against 61\n- Agent ergonomics, 83 against 69\n- Security \u0026 auth, 71 against 44\n- Maintenance \u0026 community, 73 against 60\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\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### Security \u0026 auth: Tencent Cloud TokenHub +27\n\n- Muse Spark Open (44): Read as software the owner runs. No account or key to run it. Meta's weights need manual approval on Hugging Face and an access token, and server authentication is the owner's to add (12 of 30). An agent model that calls whatever tools the operator gives it. The card recommends human-in-the-loop confirmation for irreversible actions and Meta reports agentic-risk evaluations, but nothing in the model or template enforces an approval (8 of 20). The chat template neutralises special-token sequences and media placeholders in caller text and wraps tool results in `\u003ctool_output\u003e`, and the card advises protecting internal assistant messages and layering defences against adversarial input. No indirect prompt-injection results are published (10 of 15). No call log of its own. Visibility depends on the serving stack (5 of 15). Weights are safetensors that load through Transformers' own classes from 5.19, and Meta published cyber, chemical, biological and misalignment evaluations. No security.txt on dev.meta.ai or research.meta.ai, and no security route on the card or in the docs, only museoss@meta.com and the Hugging Face discussions (9 of 20). 44.\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### Payments \u0026 pricing: Muse Spark Open +15\n\n- Muse Spark Open (50): Self-hosted rule. Nothing to buy from Meta, and the licence grants use free of charge. The Model as a Service clause asks for a separate agreement only from licensee groups above $20M gross revenue in 12 months (20). Free to run with no card (20). Meta's own weights need a manually reviewed form with legal name and date of birth, so an agent can't get them alone. The ungated GGUF quantisations from ggml-org and Unsloth that Meta's docs point to download without approval, so part of the line (10 of 20). No payment protocol (0). Hosted copies at $1.25 input and $4.25 output per million tokens need each provider's own account and are not graded. 50.\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### Agent ergonomics: Tencent Cloud TokenHub +14\n\n- Muse Spark Open (69): Model reading of the checklist (tool use, structured output, caching, context, throughput, defaults and SDKs, errors). OpenAI-format tools and parallel calls come back as `tool_calls`, and the template supports namespaced tools and deferred loading through a `tool_search` tool. A forced `tool_choice` is not documented (17 of 20). JSON mode and JSON Schema come from each runtime's guided decoding, which Meta's docs show for TensorRT-LLM only (8 of 15). Prefix caching is the runtime's. Meta's SGLang command turns on hierarchical caching, and Dynamo routes each request to the worker holding its cached context (8 of 10). 1,048,576-token context, with sliding-window attention on 46 of 62 layers holding KV memory down (15 of 15). Draft models for speculative decoding in SGLang and vLLM, and no batch mode of its own (7 of 10). Any OpenAI SDK works against a local server, but reasoning can't be turned off, defaults to the most expensive level, and needs streaming, a `max_tokens` budget for reasoning and the right stop tokens (6 of 15). The template raises named errors for an unsupported reasoning effort, tool arguments passed as a string and a tool message with no name. Server errors are the runtime's (8 of 15). 69.\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### Maintenance \u0026 community: Tencent Cloud TokenHub +13\n\n- Muse Spark Open (60): Read for an open-weight model released today. Released on 15 October 2026 (30). One release, BF16 and NVFP4 on the same day, with no history of revisions, successors or notice periods, and Meta Model API has no deprecation policy either (6 of 20). Three Hugging Face discussions opened on release day had no reply from Meta when read. Feedback goes to the discussions or museoss@meta.com, and Meta's docs and developer blog carry dated posts (8 of 25). Day-one support in vLLM, SGLang, TensorRT-LLM, Transformers, llama.cpp, MLX and Unsloth with Meta's own recipes, though SGLang's is a dev image and TensorRT-LLM's a feature branch (12 of 15). Current dependencies (Transformers 5.19), but no CI visible to us (4 of 10). 60.\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### Schema \u0026 documentation: Tencent Cloud TokenHub +12\n\n- Muse Spark Open (61): Read for a model the owner serves. No specification of its own. The contract is the Jinja chat template, which renders OpenAI-format tools with `additionalProperties: false` added and rejects bad values, plus the OpenAI-compatible servers in vLLM and SGLang with the `muse` parsers (10 of 25). dev.meta.ai/llms.txt lists eight Muse Spark Open pages, each with a Markdown copy (10). The card lists seven intended uses and six limitations, the docs say when to pick BF16 or NVFP4 and which reasoning strength suits which task, and the Usage Policy states what is out of scope (17 of 20). `reasoning_effort` is an enum of four values and anything else returns an error, and tools take JSON Schema. Structured output is documented only for TensorRT-LLM's `response_format`, not in the prompting guide or for vLLM and SGLang (11 of 15). curl and Python examples for every runtime and hosted provider, the rendered prompt for each case, and the template's own error messages, but no error reference for a served model (11 of 15). One release, with no changelog or version scheme beyond the licence's version line, Muse Spark Open (2 of 15). 61.\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## Score by category\n\n| Category | Weight | Muse Spark Open | Tencent Cloud TokenHub | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 42 | 46 | Tencent Cloud TokenHub +4 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 61 | 73 | Tencent Cloud TokenHub +12 |\n| Agent ergonomics | 13% (16.2 this run) | 69 | 83 | Tencent Cloud TokenHub +14 |\n| Security \u0026 auth | 14% (17.5 this run) | 44 | 71 | Tencent Cloud TokenHub +27 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 50 | 35 | Muse Spark Open +15 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 60 | 73 | Tencent Cloud TokenHub +13 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 53 | 54 | Tencent Cloud TokenHub +1 |\n| Negative events | ≤15 | 0 | -3 | |\n| **Total** | | **53.4 · D** | **59.5 · C** | |\n\n## Facts side by side\n\n| Fact | Muse Spark Open | Tencent Cloud TokenHub |\n| --- | --- | --- |\n| Kind | Model API | Model router |\n| Vendor | Meta | Tencent Cloud |\n| Hosted endpoint | no (local only) | `https://tokenhub.tencentmaas.com/v1` |\n| Transports | HTTP | HTTP |\n| Auth | None | API key |\n| Pricing | Free | Pay per use |\n| x402 | no | no |\n| Licence | Muse Model Licence (source-available weights, not an OSI licence), free of charge with an attribution notice, a separate agreement with Meta before Model as a Service by a licensee group above $20M gross revenue, and the Muse Spark Open Usage Policy | 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 | 2026-10-15 | 2026-10-24 |\n| Terms last updated | 2026-10-15 | couldn't be read |\n| Privacy policy last updated | no document linked | couldn't be read |\n| Customer content may train models | not found in the text | couldn't be read |\n| Terms restrict automated access | not found in the text | couldn't be read |\n| Terms restrict benchmarking | not found in the text | 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 | not found in the text | couldn't be read |\n| Popularity | none | 204 npm/wk |\n\n## How the scores have moved\n\n### Muse Spark Open\n\n- -0.1 on 30 October 2026: checklist\n- no change on 28 October 2026: new evidence\n- +0.1 on 27 October 2026: checklist\n\n### Tencent Cloud TokenHub\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Muse Spark Open.** Muse Spark Open runs on the owner's hardware in seven runtimes, with OpenAI-compatible servers in vLLM and SGLang, standard tool calls, a 1M-token context and Meta's own serving docs. Serving the 537 GB NVFP4 checkpoint takes four B300 GPUs, Meta's download is gated by manual review, and the licence adds attribution and a revenue threshold for model resellers.\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### Muse Spark Open\n\n1. Start vLLM or SGLang with `--reasoning-parser muse --tool-call-parser muse` (vLLM also `--enable-auto-tool-choice`), or tool calls come back as raw text\n2. Set `reasoning_effort` to `low` or `medium` for short tasks. The default is `xhigh`, reasoning can't be turned off, and other values return an error\n3. Stop only on `\u003c|eot|\u003e` and end of text. Stopping on `\u003c|eom|\u003e` cuts off tool calls and final answers\n4. Stream long generations and leave `max_tokens` room for reasoning, or `content` can come back empty with `finish_reason` `length`\n5. Don't call Meta Model API for this model. Use a self-hosted server or a hosted provider's model string, such as `meta-models/muse-spark-open`\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, Muse Spark Open or Tencent Cloud TokenHub?\n\nTencent Cloud TokenHub scores 59.5 (C) on agent readiness against Muse Spark Open's 53.4 (D), and leads in 6 of 7 scored categories. Muse Spark Open leads on payments \u0026 pricing.\n\n### Do Muse Spark Open and Tencent Cloud TokenHub need an API key?\n\nMuse Spark Open needs no key. Tencent Cloud TokenHub needs an API key.\n\n### Can an agent call Muse Spark Open and Tencent Cloud TokenHub without installing anything?\n\nNo hosted endpoint is listed for Muse Spark Open. Tencent Cloud TokenHub has a hosted endpoint at https://tokenhub.tencentmaas.com/v1.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/muse-spark-open-vs-tencent-tokenhub.json, and with the fewest tokens: https://www.anchorterminal.com/compare/muse-spark-open-vs-tencent-tokenhub.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"muse-spark-open\", \"b\": \"tencent-tokenhub\"}`. From a terminal: `anchor compare muse-spark-open tencent-tokenhub`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/muse-spark-open.json and https://www.anchorterminal.com/api/v1/tools/tencent-tokenhub.json\n\n## Other comparisons with Muse Spark Open or Tencent Cloud TokenHub\n\n- [Claude API vs Muse Spark Open](https://www.anchorterminal.com/compare/anthropic-api-vs-muse-spark-open.md)\n- [Claude API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/anthropic-api-vs-tencent-tokenhub.md)\n- [Antseed vs Muse Spark Open](https://www.anchorterminal.com/compare/antseed-vs-muse-spark-open.md)\n- [BlockRun.AI vs Muse Spark Open](https://www.anchorterminal.com/compare/blockrun-ai-vs-muse-spark-open.md)\n- [BlockRun.AI vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/blockrun-ai-vs-tencent-tokenhub.md)\n- [Cerebras Inference vs Muse Spark Open](https://www.anchorterminal.com/compare/cerebras-inference-vs-muse-spark-open.md)\n- [Cerebras Inference vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/cerebras-inference-vs-tencent-tokenhub.md)\n- [Cloudflare AI Gateway vs Muse Spark Open](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-muse-spark-open.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 Muse Spark Open](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-muse-spark-open.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 Muse Spark Open](https://www.anchorterminal.com/compare/cohere-chat-vs-muse-spark-open.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 Muse Spark Open](https://www.anchorterminal.com/compare/deepinfra-vs-muse-spark-open.md)\n- [DeepInfra vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/deepinfra-vs-tencent-tokenhub.md)\n- [DeepSeek API vs Muse Spark Open](https://www.anchorterminal.com/compare/deepseek-api-vs-muse-spark-open.md)\n- [DeepSeek API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/deepseek-api-vs-tencent-tokenhub.md)\n- [Glimpse vs Muse Spark Open](https://www.anchorterminal.com/compare/elorian-glimpse-vs-muse-spark-open.md)\n- [Glimpse vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/elorian-glimpse-vs-tencent-tokenhub.md)\n- [Fireworks AI Inference vs Muse Spark Open](https://www.anchorterminal.com/compare/fireworks-inference-vs-muse-spark-open.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 Muse Spark Open](https://www.anchorterminal.com/compare/gemini-api-vs-muse-spark-open.md)\n- [Gemini Developer API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/gemini-api-vs-tencent-tokenhub.md)\n- [GroqCloud vs Muse Spark Open](https://www.anchorterminal.com/compare/groq-vs-muse-spark-open.md)\n- [GroqCloud vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/groq-vs-tencent-tokenhub.md)\n- [Jais 3 vs Muse Spark Open](https://www.anchorterminal.com/compare/jais-3-vs-muse-spark-open.md)\n- [Jais 3 vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/jais-3-vs-tencent-tokenhub.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 Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/meta-model-api-vs-tencent-tokenhub.md)\n- [MiniMax API vs Muse Spark Open](https://www.anchorterminal.com/compare/minimax-api-vs-muse-spark-open.md)\n- [MiniMax API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/minimax-api-vs-tencent-tokenhub.md)\n- [Mistral AI API vs Muse Spark Open](https://www.anchorterminal.com/compare/mistral-api-vs-muse-spark-open.md)\n- [Mistral AI API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/mistral-api-vs-tencent-tokenhub.md)\n- [Muse Spark Open vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/muse-spark-open-vs-nemotron-3-5-super-vl.md)\n- [Muse Spark Open vs Novita AI](https://www.anchorterminal.com/compare/muse-spark-open-vs-novita-ai.md)\n- [Muse Spark Open vs OpenAI API](https://www.anchorterminal.com/compare/muse-spark-open-vs-openai-api.md)\n- [Muse Spark Open vs OpenRouter](https://www.anchorterminal.com/compare/muse-spark-open-vs-openrouter.md)\n- [Muse Spark Open vs Prism Inference](https://www.anchorterminal.com/compare/muse-spark-open-vs-prism-inference.md)\n- [Muse Spark Open vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/muse-spark-open-vs-ramp-router.md)\n- [Muse Spark Open vs Beam 1.0](https://www.anchorterminal.com/compare/muse-spark-open-vs-reflection-beam.md)\n- [Muse Spark Open vs RouterPlus](https://www.anchorterminal.com/compare/muse-spark-open-vs-routerplus.md)\n- [Muse Spark Open vs SambaCloud](https://www.anchorterminal.com/compare/muse-spark-open-vs-sambanova.md)\n- [Muse Spark Open vs SiliconFlow](https://www.anchorterminal.com/compare/muse-spark-open-vs-siliconflow.md)\n- [Muse Spark Open vs Simplismart](https://www.anchorterminal.com/compare/muse-spark-open-vs-simplismart.md)\n- [Muse Spark Open vs StepFun API](https://www.anchorterminal.com/compare/muse-spark-open-vs-stepfun-api.md)\n- [Muse Spark Open vs Together AI Inference](https://www.anchorterminal.com/compare/muse-spark-open-vs-together-inference.md)\n- [Muse Spark Open vs Vercel AI Gateway](https://www.anchorterminal.com/compare/muse-spark-open-vs-vercel-ai-gateway.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": "Muse Spark Open vs Tencent Cloud TokenHub", "url": "" } ], "description": "Tencent Cloud TokenHub scores 59.5 (C) to Muse Spark Open's 53.4 (D) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Muse Spark Open D 53.4", "Tencent Cloud TokenHub C 59.5", "scores" ], "h1": "Muse Spark Open vs Tencent Cloud TokenHub", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/muse-spark-open-vs-tencent-tokenhub", "published": "2026-10-01", "section": "tools", "title": "Muse Spark Open vs Tencent Cloud TokenHub for AI agents (2026)", "toc": null, "updated": "2026-11-01", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-tencent-tokenhub" }, "tokens": { "markdown": 6700, "slim": 3530 }, "version": 1 }