{ "data": { "a": { "slug": "inkling-2-small", "name": "Inkling 2 Small", "vendor": "Thinking Machines Lab", "vendorUrl": "https://thinkingmachines.ai", "kind": "model", "category": "inference", "summary": "Inkling 2 Small is Thinking Machines Lab's mixture-of-experts model, 594B total and 17B active parameters, taking text and images and returning text. It runs on Tinker for inference and fine-tuning, with open weights promised.", "url": "https://www.anchorterminal.com/tools/inkling-2-small", "markdownUrl": "https://www.anchorterminal.com/tools/inkling-2-small.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/inkling-2-small.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/inkling-2-small.json", "dns": "inkling-2-small.grade.anchorterminal.com", "license": "Proprietary for now, used through Tinker under the Tinker Terms of Use and Thinking Machines' Model Acceptable Use Policy, per the model card. Thinking Machines says it will publish the weights under Apache 2.0 the week after launch, once outside safety testing is done", "transports": [], "remoteUrl": "https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1", "packages": [], "auth": "api-key", "authNotes": "A Tinker API key from the Tinker console, read from TINKER_API_KEY and passed as the OpenAI client's api_key on the OpenAI-compatible endpoint, or used by the Tinker Python SDK. Sign-up is a browser flow at auth.thinkingmachines.ai, and the quickstart asks for payment details in Billing before training, per the tinker listing.", "pricing": "usage", "pricingNotes": "Serverless inference (beta) is $0.30 per million input tokens, $0.03 cached and $1.00 output, at 256K context. On the training side prefill is the same $0.30, sampling $1.00, and training $1.50 per million at 64K or $3.00 at 256K. No free tier is listed (checked 2026-11-06).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 on Tinker's models and pricing page or its OpenAI-compatible API page, and Tinker bills against an account with payment details (checked 2026-11-06).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://thinkingmachines.ai/model-card/inkling-2-small/", "llmsTxt": "https://tinker-docs.thinkingmachines.ai/llms.txt", "capabilities": [ "inference.llm" ], "tags": [ "official", "hosted", "model", "moe", "multimodal", "vision", "reasoning", "openai-compatible", "usage-priced", "card-required", "beta", "llms-txt", "new" ], "lastRelease": "2026-11-05", "graded": true, "anchor": { "graded": true, "score": 52.1, "grade": "D", "agentReady": false, "rank": 899, "ranked": true, "rankOf": 1354, "categoryRank": 28, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 62, "maintenance": 75, "payments": 20, "reliability": 30, "schema": 70, "security": 57, "transparency": 64 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "A new multimodal mixture-of-experts model from Thinking Machines, callable today through Tinker's OpenAI-compatible endpoint at $0.30 and $1.00 per million tokens, with strong vendor-reported coding and agent scores. Tinker's serverless inference is beta, with no status page or SLA, and the weights aren't public yet.", "bestFor": "Developers who want a capable multimodal open-family model through an OpenAI-compatible API today, or to fine-tune it on Tinker, and who can live with a beta surface until the weights are published.", "strengths": [ "OpenAI-compatible chat and completions endpoint, so the OpenAI SDKs work with a Tinker key", "$0.30 input, $0.03 cached and $1.00 output per million tokens, published without a login", "Text and image input, a 256K context on Tinker and up to 1M per the model card", "reasoning_effort from none to xhigh or a number, with reasoning returned separately", "A model card with intended use, limitations, training data sources and safety testing that includes outside red-teaming", "Thinking Machines says Apache 2.0 weights follow a week after launch" ], "weaknesses": [ "Serverless inference and the OpenAI-compatible API are both labelled beta, with a waitlist for higher throughput", "No status page, SLA or published rate limits for serverless inference", "Tool-calling format and structured output aren't documented for this model", "No free tier, and sign-up is a browser flow with payment details", "Benchmark results are Thinking Machines' own, with no independent results yet" ], "agentNotes": [ "Call https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1 with an OpenAI client and TINKER_API_KEY, using /chat/completions", "The serverless model ID is thinkingmachines/Inkling-2-Small:peft:262144:sampling-nvfp4, per Tinker's pricing page. The OpenAI page's examples use your own checkpoint paths, so confirm it before relying on it", "Pass reasoning_effort as none to xhigh or 0.0 to 0.99 (default 0.9); reasoning arrives in reasoning_content unless separate_reasoning is false", "Keep images between 40 and 4096 px a side, per the model card", "Validate JSON yourself, since structured output and the tool-call format aren't documented", "Plan for a move to open weights. When they publish, the open-weights listing will carry sizes and runtimes" ], "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": 52.1 } ], "editorialScores": { "ergonomics": 62, "maintenance": 75, "payments": 20, "reliability": 30, "schema": 70, "security": 57, "transparency": 60 }, "provenanceScore": 68, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "http": "curl https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1/chat/completions \\\n -H \"Authorization: Bearer $TINKER_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"model\": \"thinkingmachines/Inkling-2-Small:peft:262144:sampling-nvfp4\",\n \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}],\n \"reasoning_effort\": \"low\"\n }'" }, "letme": { "capability": "https://letme.dev/inference.llm", "tool": "https://letme.dev/inkling-2-small" }, "sameCompany": [ "inkling", "inkling-small" ], "sameModel": [ "tinker" ], "area": "models", "provenance": { "legalEntity": "Thinking Machines Lab, Inc. (named as provider on the model card)", "domain": "thinkingmachines.ai", "domainRegistered": "", "domainNote": "Not looked up: RDAP isn't requested under the 1 November 2026 rules.", "endpointOnVendorDomain": true, "terms": "https://thinkingmachines.ai/legal/terms/", "privacy": "https://thinkingmachines.ai/legal/privacy/", "statusPage": "", "changelog": "https://tinker-docs.thinkingmachines.ai/changelog/", "securityTxt": "valid", "checked": "2026-11-06", "notes": [ "The launch post and model card are on thinkingmachines.ai and name Thinking Machines Lab, Inc. as provider. The OpenAI-compatible endpoint is on thinkingmachines.dev, which Tinker's own docs give as the production base URL, so it's read as a domain the vendor controls; its registration wasn't looked up.", "Thinking Machines' terms bar scraping the Services, which the 4 November re-check read as a ban and paused. The founder decided on 6 November 2026 that reading at a person's pace is fine, so four pages were read one at a time: the launch post, the model card, the models and pricing page and the OpenAI-compatible API page. tinker-docs.thinkingmachines.ai has no robots.txt; thinkingmachines.ai's has no rules.", "security.txt lists security-reports@thinkingmachines.ai and expires 2029-07-13, per the 2 November reading.", "No status page was found." ], "score": 68 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/inkling-2-small.json", "live": { "slug": "inkling-2-small", "probe": { "target": "https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1", "method": "get", "lastAt": "2026-11-06T09:47:32.967989265Z", "lastOk": true, "lastStatus": 404, "lastMs": 389, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 398, "p95ms24h": 429, "samples24h": 47, "samples30d": 47, "days": [ { "date": "2026-11-06", "probes": 47, "ok": 47 } ] }, "updatedAt": "2026-11-06T09:47:32.967989265Z" } }, "answer": "Muse Spark Open scores 53.4 (D) on agent readiness against Inkling 2 Small's 52.1 (D), and leads in 3 of 7 scored categories. Inkling 2 Small leads on schema \u0026 documentation, security \u0026 auth, maintenance \u0026 community and transparency \u0026 trust.", "b": { "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. Meta's Get the model page also gives a download from its own site after signing in and accepting the licence, one file at a time. 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 and Modal (checked 2026-10-15). On 4 November Hugging Face lists Baseten and Together as live inference providers, Baseten at $4.25 output. 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": 852, "ranked": true, "rankOf": 1354, "categoryRank": 25, "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": "2026-11-04" }, "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", "No changelog, deprecation policy or CI found, and none of the Hugging Face discussion replies counted on 4 November came from Meta" ], "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": "2026-11-04", "maintenance": "2026-11-04", "payments": "2026-11-04", "reliability": "2026-11-04", "schema": "2026-11-04", "security": "2026-11-04", "transparency": "2026-11-04" }, "last": "2026-11-04", "lastMoved": "2026-10-30", "oldest": "2026-11-04", "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": "2026-11-04", "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.", "Re-read on 4 November 2026 from the Hugging Face model pages, which show both Meta repositories gated with manual review and last changed on 15 October 2026. Meta's Get the model page now also lists a signed-in download from dev.meta.ai." ], "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": "2026-11-05T15:55:33.018883278Z" }, "llmsTxt": { "url": "https://dev.meta.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-05T15:26:43.362877914Z" }, "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": "2026-11-05T12:57:30.663035371Z", "changedAt": "2026-11-05T12:35:34.643909044Z", "fingerprint": "bebe68770266" } ], "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": 943718, "checkedAt": "2026-11-05T23:49:24.366022811Z" } }, "updatedAt": "2026-11-05T23:49:24.366022811Z" } }, "edges": [ { "by": 30, "category": "payments", "leads": "muse-spark-open", "name": "Payments \u0026 pricing", "reasons": { "a": "Published rubric. No payment protocol (0). Per-million-token prices for serverless inference and training published without a login on 6 November (20). No free tier listed, and the quickstart asks for payment details before training, per the tinker listing (0). Sign-up is a browser flow (0). 0 + 20 + 0 + 0 = 20.", "b": "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 Hugging Face form with legal name and date of birth, or, since the 4 November re-read of Get the model, a signed-in download from Meta's own page, 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 (the Unsloth repository is ungated on 4 November), 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. 20 + 20 + 10 + 0 = 50." }, "scores": { "a": 20, "b": 50 } }, { "by": 15, "category": "maintenance", "leads": "inkling-2-small", "name": "Maintenance \u0026 community", "reasons": { "a": "Model reading. Released 5 November 2026 (30). Churn and notice in place of release counts: Inkling, Inkling-Small (30 July) and Inkling 2 Small in about four months, and a deprecations page with dated retirements and a promise to 'aim to give advance notice' by email, with no stated period, per the tinker listing (10 of 20). A public changelog and a support address and Discord, per the tinker listing (10 of 15). Current official SDKs, Tinker's Python SDK and the OpenAI-compatible endpoint (15). SDK and cookbook CI, per the tinker listing (10). 30 + 10 + 10 + 15 + 10 = 75.", "b": "Read for an open-weight model released three weeks ago. 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). None of the 29 replies counted by script on 4 November across the BF16 repository's discussions came from Meta. 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). 30 + 6 + 8 + 12 + 4 = 60." }, "scores": { "a": 75, "b": 60 } }, { "by": 13, "category": "security", "leads": "inkling-2-small", "name": "Security \u0026 auth", "reasons": { "a": "Platform readings are the tinker listing's. Revocable API keys from the console, with no per-key scopes found (20). Org, team and project permissions with no read-only role (5). The model returns its own completions, no third-party content (10). get_audit_log() for admins (15). security.txt with a reporting address and no stated acknowledgement time (7). For the model reading, Tinker's terms commit not to use Customer Content for training, recorded under transparency. 20 + 5 + 10 + 15 + 7 = 57.", "b": "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. dev.meta.ai/.well-known/security.txt answers 404 (re-read on 4 November), research.meta.ai per the 15 October check, and no security route is on the card or in the docs, only museoss@meta.com and the Hugging Face discussions (9 of 20). 12 + 8 + 10 + 5 + 9 = 44." }, "scores": { "a": 57, "b": 44 } }, { "by": 12, "category": "reliability", "leads": "muse-spark-open", "name": "Reliability", "reasons": { "a": "Model reading, for the surface it's called on, Tinker's serverless inference and OpenAI-compatible API. No status page found, per the tinker listing's checks of 1 October and 4 November (0), so no readable incident history (5). The only published limit is the in-flight sample cap of 2,000, per the tinker listing's 1 October check; the OpenAI-compatible page gives no numbers and says higher or more stable throughput needs the waitlist (10). The SDK retries sampling with stable request IDs, per the tinker listing's reading of the SDK repository; the OpenAI-compatible page has no retry guidance (15). No SLA found (0). Serverless inference is 'currently in beta' on the models and pricing page and the OpenAI-compatible API is labelled Beta, read 6 November (0). 0 + 5 + 10 + 15 + 0 + 0 = 30.", "b": "Read with the local-software lines, since the owner serves the weights. Meta's weights come from two Hugging Face repositories gated with manual review. The docs state Python 3.10 or later, Transformers 5.19 or later, Docker images for SGLang and vLLM and the GPUs for each checkpoint (4 × B300 for NVFP4, 8 × B300 for BF16), but SGLang's image is a dev tag and TensorRT-LLM's support sits on a feature branch (13 of 20). No CI or test suite of Meta's for the model was found. github.com/meta-models answered 403 to our fetcher, so its repositories are unchecked (0 of 25). On 4 November the BF16 repository's discussions page lists 13 open threads from 15 October to 1 November, 10 discussions and 3 pull requests (one a draft). A script counted 29 replies across the seven threads with replies, six discussions and the draft pull request, none from the repository owner or a Meta member, and their text wasn't read, so crash reports weren't separated from other posts (15 of 25, held from 15 October and flagged). No changelog, version tags or revision notes, and the commit history needs gated access (2 of 15). Released as a final checkpoint with no preview label from Meta, and both repositories unchanged since 15 October, though runtime support ships as launch-specific images and a branch, and Groq lists it as a preview (12 of 15). 13 + 0 + 15 + 2 + 12 = 42." }, "scores": { "a": 30, "b": 42 } }, { "by": 11, "category": "transparency", "leads": "inkling-2-small", "name": "Transparency \u0026 trust", "reasons": { "a": "Editorial half. Closed for now under the Tinker Terms of Use and the Model Acceptable Use Policy, per the model card, with Apache 2.0 weights promised the week after launch (15). Terms commit not to use Customer Content for training, keep it only as needed, with a DPA and deletion on request; the privacy notice wasn't re-read, per the tinker listing (15). Dated deprecation notices with no stated period (15). The DPA annex names Google Cloud, Cloudflare, WorkOS and OpenAI with service and location (15). 15 + 15 + 15 + 15 = 60.", "b": "Weights are downloadable under the Muse Model Licence, which is clear and broad in its grant but not an OSI licence. It adds a display requirement, a separate agreement before Model as a Service by a licensee group above $20M gross revenue, and a Usage Policy with field-of-use limits (military, nuclear, espionage, critical infrastructure, heavy machinery) and an age limit of 18. It has no regional exclusion and no governing-law clause. Training code and data aren't released (18 of 30). Inputs stay on the owner's hardware, and Meta's docs say self-hosting keeps 'every prompt and response' inside the owner's infrastructure. The access form's details, and a download from Meta's own page after signing in, go to Meta under its general privacy policy, which we didn't read, and the training data is described in outline only (20 of 30). No deprecation policy, dated notices or versioning found (0 of 20). The Get the model page says everything runs offline once the weights land, and safetensors weights carry no code. No other telemetry statement, and Meta's download form records name, date of birth, country and IP location (12 of 20). 18 + 20 + 0 + 12 = 50." }, "scores": { "a": 64, "b": 53 } }, { "by": 9, "category": "schema", "leads": "inkling-2-small", "name": "Schema \u0026 documentation", "reasons": { "a": "Model reading. No OpenAPI file of its own; the OpenAI-compatible chat and completions endpoints and the typed Python SDK are the contract, as the tinker listing reads it (15). llms.txt on the docs host, per the tinker listing's 1 October check (10). The model card states intended use (agentic and tool-use systems, coding assistants, chatbots, RAG), inputs, outputs and limitations, and the launch post its benchmarks (16 of 20). Model IDs, context lengths and the reasoning_effort values (none to xhigh, or 0.0 to 0.99) are documented; the tool-call format and structured output aren't, for this model (8 of 15). A Python example and an HTTP 400 for models without reasoning_effort, with no error page (6 of 15). A dated Tinker changelog and a model deprecations page, per the tinker listing (15). 15 + 10 + 16 + 8 + 6 + 15 = 70.", "b": "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 the Muse Spark Open overview and seven pages under it, plus three cookbook 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). 10 + 10 + 17 + 11 + 11 + 2 = 61." }, "scores": { "a": 70, "b": 61 } } ], "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Thinking Machines Lab", "b": "Meta", "name": "Vendor" }, { "a": "https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "HTTP", "name": "Transports" }, { "a": "API key", "b": "None", "name": "Auth" }, { "a": "Pay per use", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary for now, used through Tinker under the Tinker Terms of Use and Thinking Machines' Model Acceptable Use Policy, per the model card. Thinking Machines says it will publish the weights under Apache 2.0 the week after launch, once outside safety testing is done", "b": "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", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-11-05", "b": "2026-10-15", "name": "Last release" }, { "a": "not read yet", "b": "2026-10-15", "name": "Terms last updated" }, { "a": "not read yet", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "not read yet", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not read yet", "b": "not found in the text", "name": "Arbitration or class-action waiver" } ], "faq": [ { "answer": "Muse Spark Open scores 53.4 (D) on agent readiness against Inkling 2 Small's 52.1 (D), and leads in 3 of 7 scored categories. Inkling 2 Small leads on schema \u0026 documentation, security \u0026 auth, maintenance \u0026 community and transparency \u0026 trust.", "question": "Which is better for AI agents, Inkling 2 Small or Muse Spark Open?" }, { "answer": "Inkling 2 Small needs an API key. Muse Spark Open needs no key.", "question": "Do Inkling 2 Small and Muse Spark Open need an API key?" }, { "answer": "Inkling 2 Small has a hosted endpoint at https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1. No hosted endpoint is listed for Muse Spark Open.", "question": "Can an agent call Inkling 2 Small and Muse Spark Open without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 70 against 61", "Security \u0026 auth, 57 against 44", "Maintenance \u0026 community, 75 against 60", "Transparency \u0026 trust, 64 against 53" ], "also": [ "A hosted endpoint, with nothing to install" ], "goodFor": "Developers who want a capable multimodal open-family model through an OpenAI-compatible API today, or to fine-tune it on Tinker, and who can live with a beta surface until the weights are published.", "slug": "inkling-2-small", "watchFor": "Serverless inference and the OpenAI-compatible API are both labelled beta, with a waitlist for higher throughput" }, { "aheadOn": [ "Reliability, 42 against 30", "Agent ergonomics, 69 against 62", "Payments \u0026 pricing, 50 against 20" ], "also": [ "No key needed to call it" ], "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" } ], "history": { "inkling-2-small": null, "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" } ] }, "job": { "capability": "inference.llm", "name": "LLM inference" }, "others": [ { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-inkling-2-small.json", "title": "Claude API vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-inkling-2-small" }, { "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/antseed-vs-inkling-2-small.json", "title": "Antseed vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/antseed-vs-inkling-2-small" }, { "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-inkling-2-small.json", "title": "BlockRun.AI vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-inkling-2-small" }, { "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/cerebras-inference-vs-inkling-2-small.json", "title": "Cerebras Inference vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-inkling-2-small" }, { "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/cloudflare-ai-gateway-vs-inkling-2-small.json", "title": "Cloudflare AI Gateway vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-inkling-2-small" }, { "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-workers-ai-vs-inkling-2-small.json", "title": "Cloudflare Workers AI vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-inkling-2-small" }, { "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/cohere-chat-vs-inkling-2-small.json", "title": "Cohere Chat API (Command models) vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-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/deepinfra-vs-inkling-2-small.json", "title": "DeepInfra vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/deepinfra-vs-inkling-2-small" }, { "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/deepseek-api-vs-inkling-2-small.json", "title": "DeepSeek API vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-inkling-2-small" }, { "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/elorian-glimpse-vs-inkling-2-small.json", "title": "Glimpse vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-inkling-2-small" }, { "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/fireworks-inference-vs-inkling-2-small.json", "title": "Fireworks AI Inference vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-inkling-2-small" }, { "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/gemini-api-vs-inkling-2-small.json", "title": "Gemini Developer API vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/gemini-api-vs-inkling-2-small" }, { "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/groq-vs-inkling-2-small.json", "title": "GroqCloud vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/groq-vs-inkling-2-small" }, { "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/inkling-2-small-vs-jais-3.json", "title": "Inkling 2 Small vs Jais 3", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-meta-model-api.json", "title": "Inkling 2 Small vs Meta Model API", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-api.json", "title": "Inkling 2 Small vs MiniMax API", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-api" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-mistral-api.json", "title": "Inkling 2 Small vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-5-super-vl.json", "title": "Inkling 2 Small vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-novita-ai.json", "title": "Inkling 2 Small vs Novita AI", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-novita-ai" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-openai-api.json", "title": "Inkling 2 Small vs OpenAI API", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-openai-api" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-openrouter.json", "title": "Inkling 2 Small vs OpenRouter", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-openrouter" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-prism-inference.json", "title": "Inkling 2 Small vs Prism Inference", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ramp-router.json", "title": "Inkling 2 Small vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-reflection-beam.json", "title": "Inkling 2 Small vs Beam 1.0", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-reflection-beam" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-routerplus.json", "title": "Inkling 2 Small vs RouterPlus", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-routerplus" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-sambanova.json", "title": "Inkling 2 Small vs SambaCloud", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-sambanova" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-siliconflow.json", "title": "Inkling 2 Small vs SiliconFlow", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-siliconflow" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-simplismart.json", "title": "Inkling 2 Small vs Simplismart", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-simplismart" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-stepfun-api.json", "title": "Inkling 2 Small vs StepFun API", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-stepfun-api" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-swe-2-flash.json", "title": "Inkling 2 Small vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-tencent-tokenhub.json", "title": "Inkling 2 Small vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-together-inference.json", "title": "Inkling 2 Small vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-together-inference" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-vercel-ai-gateway.json", "title": "Inkling 2 Small vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-muse-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/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/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/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/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-swe-2-flash.json", "title": "Muse Spark Open vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-swe-2-flash" }, { "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/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" } ], "panel": null, "scores": [ { "by": 12, "edge": "muse-spark-open", "inkling-2-small": 30, "key": "reliability", "muse-spark-open": 42, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 9, "edge": "inkling-2-small", "inkling-2-small": 70, "key": "schema", "muse-spark-open": 61, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 7, "edge": "muse-spark-open", "inkling-2-small": 62, "key": "ergonomics", "muse-spark-open": 69, "name": "Agent ergonomics", "weight": 13 }, { "by": 13, "edge": "inkling-2-small", "inkling-2-small": 57, "key": "security", "muse-spark-open": 44, "name": "Security \u0026 auth", "weight": 14 }, { "by": 30, "edge": "muse-spark-open", "inkling-2-small": 20, "key": "payments", "muse-spark-open": 50, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 15, "edge": "inkling-2-small", "inkling-2-small": 75, "key": "maintenance", "muse-spark-open": 60, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 11, "edge": "inkling-2-small", "inkling-2-small": 64, "key": "transparency", "muse-spark-open": 53, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Muse Spark Open scores 53.4 (D) on agent readiness against Inkling 2 Small's 52.1 (D), and leads in 3 of 7 scored categories. Inkling 2 Small leads on schema \u0026 documentation, security \u0026 auth, maintenance \u0026 community and transparency \u0026 trust. Both do llm inference.", "tasks": null, "tutorials": [], "verdicts": { "inkling-2-small": "A new multimodal mixture-of-experts model from Thinking Machines, callable today through Tinker's OpenAI-compatible endpoint at $0.30 and $1.00 per million tokens, with strong vendor-reported coding and agent scores. Tinker's serverless inference is beta, with no status page or SLA, and the weights aren't public yet.", "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." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-spark-open", "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-spark-open.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-spark-open.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-spark-open.min.md" }, "markdown": "Muse Spark Open scores 53.4 (D) on agent readiness against Inkling 2 Small's 52.1 (D), and leads in 3 of 7 scored categories. Inkling 2 Small leads on schema \u0026 documentation, security \u0026 auth, maintenance \u0026 community and transparency \u0026 trust. Both do llm inference.\n\n- Inkling 2 Small: grade D, 52.1/100, rank #899 of 1354. Markdown https://www.anchorterminal.com/tools/inkling-2-small.md · JSON https://www.anchorterminal.com/api/v1/tools/inkling-2-small.json\n- Muse Spark Open: grade D, 53.4/100, rank #852 of 1354. Markdown https://www.anchorterminal.com/tools/muse-spark-open.md · JSON https://www.anchorterminal.com/api/v1/tools/muse-spark-open.json\n- Best model APIs and inference for AI agents: https://www.anchorterminal.com/best/inference/index.md\n- All 596 models comparisons: https://www.anchorterminal.com/compare/inference/index.md\n\n## Which one, for what\n\n### Inkling 2 Small (D)\n\nGood for: Developers who want a capable multimodal open-family model through an OpenAI-compatible API today, or to fine-tune it on Tinker, and who can live with a beta surface until the weights are published.\n\nAhead on:\n- Schema \u0026 documentation, 70 against 61\n- Security \u0026 auth, 57 against 44\n- Maintenance \u0026 community, 75 against 60\n- Transparency \u0026 trust, 64 against 53\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: Serverless inference and the OpenAI-compatible API are both labelled beta, with a waitlist for higher throughput\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- Reliability, 42 against 30\n- Agent ergonomics, 69 against 62\n- Payments \u0026 pricing, 50 against 20\n\nAlso in its favour:\n- No key needed to call it\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\n## Why the edge\n\n### Payments \u0026 pricing: Muse Spark Open +30\n\n- Inkling 2 Small (20): Published rubric. No payment protocol (0). Per-million-token prices for serverless inference and training published without a login on 6 November (20). No free tier listed, and the quickstart asks for payment details before training, per the tinker listing (0). Sign-up is a browser flow (0). 0 + 20 + 0 + 0 = 20.\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 Hugging Face form with legal name and date of birth, or, since the 4 November re-read of Get the model, a signed-in download from Meta's own page, 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 (the Unsloth repository is ungated on 4 November), 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. 20 + 20 + 10 + 0 = 50.\n\n### Maintenance \u0026 community: Inkling 2 Small +15\n\n- Inkling 2 Small (75): Model reading. Released 5 November 2026 (30). Churn and notice in place of release counts: Inkling, Inkling-Small (30 July) and Inkling 2 Small in about four months, and a deprecations page with dated retirements and a promise to 'aim to give advance notice' by email, with no stated period, per the tinker listing (10 of 20). A public changelog and a support address and Discord, per the tinker listing (10 of 15). Current official SDKs, Tinker's Python SDK and the OpenAI-compatible endpoint (15). SDK and cookbook CI, per the tinker listing (10). 30 + 10 + 10 + 15 + 10 = 75.\n- Muse Spark Open (60): Read for an open-weight model released three weeks ago. 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). None of the 29 replies counted by script on 4 November across the BF16 repository's discussions came from Meta. 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). 30 + 6 + 8 + 12 + 4 = 60.\n\n### Security \u0026 auth: Inkling 2 Small +13\n\n- Inkling 2 Small (57): Platform readings are the tinker listing's. Revocable API keys from the console, with no per-key scopes found (20). Org, team and project permissions with no read-only role (5). The model returns its own completions, no third-party content (10). get_audit_log() for admins (15). security.txt with a reporting address and no stated acknowledgement time (7). For the model reading, Tinker's terms commit not to use Customer Content for training, recorded under transparency. 20 + 5 + 10 + 15 + 7 = 57.\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. dev.meta.ai/.well-known/security.txt answers 404 (re-read on 4 November), research.meta.ai per the 15 October check, and no security route is on the card or in the docs, only museoss@meta.com and the Hugging Face discussions (9 of 20). 12 + 8 + 10 + 5 + 9 = 44.\n\n### Reliability: Muse Spark Open +12\n\n- Inkling 2 Small (30): Model reading, for the surface it's called on, Tinker's serverless inference and OpenAI-compatible API. No status page found, per the tinker listing's checks of 1 October and 4 November (0), so no readable incident history (5). The only published limit is the in-flight sample cap of 2,000, per the tinker listing's 1 October check; the OpenAI-compatible page gives no numbers and says higher or more stable throughput needs the waitlist (10). The SDK retries sampling with stable request IDs, per the tinker listing's reading of the SDK repository; the OpenAI-compatible page has no retry guidance (15). No SLA found (0). Serverless inference is 'currently in beta' on the models and pricing page and the OpenAI-compatible API is labelled Beta, read 6 November (0). 0 + 5 + 10 + 15 + 0 + 0 = 30.\n- Muse Spark Open (42): Read with the local-software lines, since the owner serves the weights. Meta's weights come from two Hugging Face repositories gated with manual review. The docs state Python 3.10 or later, Transformers 5.19 or later, Docker images for SGLang and vLLM and the GPUs for each checkpoint (4 × B300 for NVFP4, 8 × B300 for BF16), but SGLang's image is a dev tag and TensorRT-LLM's support sits on a feature branch (13 of 20). No CI or test suite of Meta's for the model was found. github.com/meta-models answered 403 to our fetcher, so its repositories are unchecked (0 of 25). On 4 November the BF16 repository's discussions page lists 13 open threads from 15 October to 1 November, 10 discussions and 3 pull requests (one a draft). A script counted 29 replies across the seven threads with replies, six discussions and the draft pull request, none from the repository owner or a Meta member, and their text wasn't read, so crash reports weren't separated from other posts (15 of 25, held from 15 October and flagged). No changelog, version tags or revision notes, and the commit history needs gated access (2 of 15). Released as a final checkpoint with no preview label from Meta, and both repositories unchanged since 15 October, though runtime support ships as launch-specific images and a branch, and Groq lists it as a preview (12 of 15). 13 + 0 + 15 + 2 + 12 = 42.\n\n### Transparency \u0026 trust: Inkling 2 Small +11\n\n- Inkling 2 Small (64): Editorial half. Closed for now under the Tinker Terms of Use and the Model Acceptable Use Policy, per the model card, with Apache 2.0 weights promised the week after launch (15). Terms commit not to use Customer Content for training, keep it only as needed, with a DPA and deletion on request; the privacy notice wasn't re-read, per the tinker listing (15). Dated deprecation notices with no stated period (15). The DPA annex names Google Cloud, Cloudflare, WorkOS and OpenAI with service and location (15). 15 + 15 + 15 + 15 = 60.\n- Muse Spark Open (53): Weights are downloadable under the Muse Model Licence, which is clear and broad in its grant but not an OSI licence. It adds a display requirement, a separate agreement before Model as a Service by a licensee group above $20M gross revenue, and a Usage Policy with field-of-use limits (military, nuclear, espionage, critical infrastructure, heavy machinery) and an age limit of 18. It has no regional exclusion and no governing-law clause. Training code and data aren't released (18 of 30). Inputs stay on the owner's hardware, and Meta's docs say self-hosting keeps 'every prompt and response' inside the owner's infrastructure. The access form's details, and a download from Meta's own page after signing in, go to Meta under its general privacy policy, which we didn't read, and the training data is described in outline only (20 of 30). No deprecation policy, dated notices or versioning found (0 of 20). The Get the model page says everything runs offline once the weights land, and safetensors weights carry no code. No other telemetry statement, and Meta's download form records name, date of birth, country and IP location (12 of 20). 18 + 20 + 0 + 12 = 50.\n\n### Schema \u0026 documentation: Inkling 2 Small +9\n\n- Inkling 2 Small (70): Model reading. No OpenAPI file of its own; the OpenAI-compatible chat and completions endpoints and the typed Python SDK are the contract, as the tinker listing reads it (15). llms.txt on the docs host, per the tinker listing's 1 October check (10). The model card states intended use (agentic and tool-use systems, coding assistants, chatbots, RAG), inputs, outputs and limitations, and the launch post its benchmarks (16 of 20). Model IDs, context lengths and the reasoning_effort values (none to xhigh, or 0.0 to 0.99) are documented; the tool-call format and structured output aren't, for this model (8 of 15). A Python example and an HTTP 400 for models without reasoning_effort, with no error page (6 of 15). A dated Tinker changelog and a model deprecations page, per the tinker listing (15). 15 + 10 + 16 + 8 + 6 + 15 = 70.\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 the Muse Spark Open overview and seven pages under it, plus three cookbook 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). 10 + 10 + 17 + 11 + 11 + 2 = 61.\n\n## Score by category\n\n| Category | Weight | Inkling 2 Small | Muse Spark Open | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 30 | 42 | Muse Spark Open +12 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 70 | 61 | Inkling 2 Small +9 |\n| Agent ergonomics | 13% (16.2 this run) | 62 | 69 | Muse Spark Open +7 |\n| Security \u0026 auth | 14% (17.5 this run) | 57 | 44 | Inkling 2 Small +13 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 50 | Muse Spark Open +30 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 75 | 60 | Inkling 2 Small +15 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 64 | 53 | Inkling 2 Small +11 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **52.1 · D** | **53.4 · D** | |\n\n## Facts side by side\n\n| Fact | Inkling 2 Small | Muse Spark Open |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Thinking Machines Lab | Meta |\n| Hosted endpoint | `https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1` | no (local only) |\n| Transports | | HTTP |\n| Auth | API key | None |\n| Pricing | Pay per use | Free |\n| x402 | no | no |\n| Licence | Proprietary for now, used through Tinker under the Tinker Terms of Use and Thinking Machines' Model Acceptable Use Policy, per the model card. Thinking Machines says it will publish the weights under Apache 2.0 the week after launch, once outside safety testing is done | 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 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-11-05 | 2026-10-15 |\n| Terms last updated | not read yet | 2026-10-15 |\n| Privacy policy last updated | not read yet | no document linked |\n| Customer content may train models | not read yet | not found in the text |\n| Terms restrict automated access | not read yet | not found in the text |\n| Terms restrict benchmarking | not read yet | not found in the text |\n| Terms or service can change without notice | not read yet | not found in the text |\n| Arbitration or class-action waiver | not read yet | not found in the text |\n\n## How the scores have moved\n\n### Inkling 2 Small\n\nNo score change since it was listed.\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## Verdicts\n\n**Inkling 2 Small.** A new multimodal mixture-of-experts model from Thinking Machines, callable today through Tinker's OpenAI-compatible endpoint at $0.30 and $1.00 per million tokens, with strong vendor-reported coding and agent scores. Tinker's serverless inference is beta, with no status page or SLA, and the weights aren't public yet.\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## Before you call either\n\n### Inkling 2 Small\n\n1. Call https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1 with an OpenAI client and TINKER_API_KEY, using /chat/completions\n2. The serverless model ID is thinkingmachines/Inkling-2-Small:peft:262144:sampling-nvfp4, per Tinker's pricing page. The OpenAI page's examples use your own checkpoint paths, so confirm it before relying on it\n3. Pass reasoning_effort as none to xhigh or 0.0 to 0.99 (default 0.9); reasoning arrives in reasoning_content unless separate_reasoning is false\n4. Keep images between 40 and 4096 px a side, per the model card\n5. Validate JSON yourself, since structured output and the tool-call format aren't documented\n6. Plan for a move to open weights. When they publish, the open-weights listing will carry sizes and runtimes\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## Questions\n\n### Which is better for AI agents, Inkling 2 Small or Muse Spark Open?\n\nMuse Spark Open scores 53.4 (D) on agent readiness against Inkling 2 Small's 52.1 (D), and leads in 3 of 7 scored categories. Inkling 2 Small leads on schema \u0026 documentation, security \u0026 auth, maintenance \u0026 community and transparency \u0026 trust.\n\n### Do Inkling 2 Small and Muse Spark Open need an API key?\n\nInkling 2 Small needs an API key. Muse Spark Open needs no key.\n\n### Can an agent call Inkling 2 Small and Muse Spark Open without installing anything?\n\nInkling 2 Small has a hosted endpoint at https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1. No hosted endpoint is listed for Muse Spark Open.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-spark-open.json, and with the fewest tokens: https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-spark-open.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"inkling-2-small\", \"b\": \"muse-spark-open\"}`. From a terminal: `anchor compare inkling-2-small muse-spark-open`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/inkling-2-small.json and https://www.anchorterminal.com/api/v1/tools/muse-spark-open.json\n\n## Other comparisons with Inkling 2 Small or Muse Spark Open\n\n- [Claude API vs Inkling 2 Small](https://www.anchorterminal.com/compare/anthropic-api-vs-inkling-2-small.md)\n- [Claude API vs Muse Spark Open](https://www.anchorterminal.com/compare/anthropic-api-vs-muse-spark-open.md)\n- [Antseed vs Inkling 2 Small](https://www.anchorterminal.com/compare/antseed-vs-inkling-2-small.md)\n- [Antseed vs Muse Spark Open](https://www.anchorterminal.com/compare/antseed-vs-muse-spark-open.md)\n- [BlockRun.AI vs Inkling 2 Small](https://www.anchorterminal.com/compare/blockrun-ai-vs-inkling-2-small.md)\n- [BlockRun.AI vs Muse Spark Open](https://www.anchorterminal.com/compare/blockrun-ai-vs-muse-spark-open.md)\n- [Cerebras Inference vs Inkling 2 Small](https://www.anchorterminal.com/compare/cerebras-inference-vs-inkling-2-small.md)\n- [Cerebras Inference vs Muse Spark Open](https://www.anchorterminal.com/compare/cerebras-inference-vs-muse-spark-open.md)\n- [Cloudflare AI Gateway vs Inkling 2 Small](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-inkling-2-small.md)\n- [Cloudflare AI Gateway vs Muse Spark Open](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-muse-spark-open.md)\n- [Cloudflare Workers AI vs Inkling 2 Small](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-inkling-2-small.md)\n- [Cloudflare Workers AI vs Muse Spark Open](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-muse-spark-open.md)\n- [Cohere Chat API (Command models) vs Inkling 2 Small](https://www.anchorterminal.com/compare/cohere-chat-vs-inkling-2-small.md)\n- [Cohere Chat API (Command models) vs Muse Spark Open](https://www.anchorterminal.com/compare/cohere-chat-vs-muse-spark-open.md)\n- [DeepInfra vs Inkling 2 Small](https://www.anchorterminal.com/compare/deepinfra-vs-inkling-2-small.md)\n- [DeepInfra vs Muse Spark Open](https://www.anchorterminal.com/compare/deepinfra-vs-muse-spark-open.md)\n- [DeepSeek API vs Inkling 2 Small](https://www.anchorterminal.com/compare/deepseek-api-vs-inkling-2-small.md)\n- [DeepSeek API vs Muse Spark Open](https://www.anchorterminal.com/compare/deepseek-api-vs-muse-spark-open.md)\n- [Glimpse vs Inkling 2 Small](https://www.anchorterminal.com/compare/elorian-glimpse-vs-inkling-2-small.md)\n- [Glimpse vs Muse Spark Open](https://www.anchorterminal.com/compare/elorian-glimpse-vs-muse-spark-open.md)\n- [Fireworks AI Inference vs Inkling 2 Small](https://www.anchorterminal.com/compare/fireworks-inference-vs-inkling-2-small.md)\n- [Fireworks AI Inference vs Muse Spark Open](https://www.anchorterminal.com/compare/fireworks-inference-vs-muse-spark-open.md)\n- [Gemini Developer API vs Inkling 2 Small](https://www.anchorterminal.com/compare/gemini-api-vs-inkling-2-small.md)\n- [Gemini Developer API vs Muse Spark Open](https://www.anchorterminal.com/compare/gemini-api-vs-muse-spark-open.md)\n- [GroqCloud vs Inkling 2 Small](https://www.anchorterminal.com/compare/groq-vs-inkling-2-small.md)\n- [GroqCloud vs Muse Spark Open](https://www.anchorterminal.com/compare/groq-vs-muse-spark-open.md)\n- [Inkling 2 Small vs Jais 3](https://www.anchorterminal.com/compare/inkling-2-small-vs-jais-3.md)\n- [Inkling 2 Small vs Meta Model API](https://www.anchorterminal.com/compare/inkling-2-small-vs-meta-model-api.md)\n- [Inkling 2 Small vs MiniMax API](https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-api.md)\n- [Inkling 2 Small vs Mistral AI API](https://www.anchorterminal.com/compare/inkling-2-small-vs-mistral-api.md)\n- [Inkling 2 Small vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-5-super-vl.md)\n- [Inkling 2 Small vs Novita AI](https://www.anchorterminal.com/compare/inkling-2-small-vs-novita-ai.md)\n- [Inkling 2 Small vs OpenAI API](https://www.anchorterminal.com/compare/inkling-2-small-vs-openai-api.md)\n- [Inkling 2 Small vs OpenRouter](https://www.anchorterminal.com/compare/inkling-2-small-vs-openrouter.md)\n- [Inkling 2 Small vs Prism Inference](https://www.anchorterminal.com/compare/inkling-2-small-vs-prism-inference.md)\n- [Inkling 2 Small vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/inkling-2-small-vs-ramp-router.md)\n- [Inkling 2 Small vs Beam 1.0](https://www.anchorterminal.com/compare/inkling-2-small-vs-reflection-beam.md)\n- [Inkling 2 Small vs RouterPlus](https://www.anchorterminal.com/compare/inkling-2-small-vs-routerplus.md)\n- [Inkling 2 Small vs SambaCloud](https://www.anchorterminal.com/compare/inkling-2-small-vs-sambanova.md)\n- [Inkling 2 Small vs SiliconFlow](https://www.anchorterminal.com/compare/inkling-2-small-vs-siliconflow.md)\n- [Inkling 2 Small vs Simplismart](https://www.anchorterminal.com/compare/inkling-2-small-vs-simplismart.md)\n- [Inkling 2 Small vs StepFun API](https://www.anchorterminal.com/compare/inkling-2-small-vs-stepfun-api.md)\n- [Inkling 2 Small vs SWE-2 Flash](https://www.anchorterminal.com/compare/inkling-2-small-vs-swe-2-flash.md)\n- [Inkling 2 Small vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/inkling-2-small-vs-tencent-tokenhub.md)\n- [Inkling 2 Small vs Together AI Inference](https://www.anchorterminal.com/compare/inkling-2-small-vs-together-inference.md)\n- [Inkling 2 Small vs Vercel AI Gateway](https://www.anchorterminal.com/compare/inkling-2-small-vs-vercel-ai-gateway.md)\n- [Jais 3 vs Muse Spark Open](https://www.anchorterminal.com/compare/jais-3-vs-muse-spark-open.md)\n- [Meta Model API vs Muse Spark Open](https://www.anchorterminal.com/compare/meta-model-api-vs-muse-spark-open.md)\n- [MiniMax API vs Muse Spark Open](https://www.anchorterminal.com/compare/minimax-api-vs-muse-spark-open.md)\n- [Mistral AI API vs Muse Spark Open](https://www.anchorterminal.com/compare/mistral-api-vs-muse-spark-open.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 SWE-2 Flash](https://www.anchorterminal.com/compare/muse-spark-open-vs-swe-2-flash.md)\n- [Muse Spark Open vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/muse-spark-open-vs-tencent-tokenhub.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", "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": "2026-11-06", "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": "Inkling 2 Small vs Muse Spark Open", "url": "" } ], "description": "Muse Spark Open scores 53.4 (D) to Inkling 2 Small's 52.1 (D) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Inkling 2 Small D 52.1", "Muse Spark Open D 53.4", "scores" ], "h1": "Inkling 2 Small vs Muse Spark Open", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/inkling-2-small-vs-muse-spark-open", "published": "2026-10-01", "section": "tools", "title": "Inkling 2 Small vs Muse Spark Open for AI agents (2026)", "toc": null, "updated": "2026-11-06", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-spark-open" }, "tokens": { "markdown": 6800, "slim": 3530 }, "version": 1 }