{ "data": { "a": { "slug": "muse-ember", "name": "Muse Ember", "vendor": "Meta", "vendorUrl": "https://dev.meta.ai", "kind": "model", "category": "inference", "summary": "Muse Ember is Meta's smallest and most efficient hosted model, built for sub-agent tasks, tool calls, routing and work over large collections of files and images, taking text, images, video, audio and PDF with a 1M-token context.", "url": "https://www.anchorterminal.com/tools/muse-ember", "markdownUrl": "https://www.anchorterminal.com/tools/muse-ember.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/muse-ember.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/muse-ember.json", "dns": "muse-ember.grade.anchorterminal.com", "license": "Closed model, used through Meta Model API and Muse Code under the Meta Model API Terms of Service (last updated 9 October 2026). No open weights; Meta's open-weight models are Muse Spark Open and Muse Glimmer", "transports": [], "remoteUrl": "https://api.meta.ai/v1", "packages": [], "auth": "api-key", "authNotes": "A bearer key from the API keys tab of the Model API dashboard, read from MODEL_API_KEY in Meta's examples, after a browser sign-up with email, mobile number, Facebook, Google or GitHub. Keys belong to a team and share its limits, with no scopes found, per the meta-model-api listing.", "pricing": "usage", "pricingNotes": "$0.10 per million input tokens, $0.004 cached and $0.50 output for requests up to 200K input tokens, and $0.30, $0.012 and $1.50 for the whole request above that. Standard mode only, no Contributor discount. Web search grounding $2.50 per 1,000 queries. Included in every Muse Code plan. No free API allowance found (checked 2026-11-09).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 on Meta's pricing page, which bills tokens to a team account with a card (checked 2026-11-09).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-09" }, "docsUrl": "https://dev.meta.ai/docs/muse-ember", "llmsTxt": "https://dev.meta.ai/llms.txt", "capabilities": [ "inference.llm" ], "tags": [ "official", "hosted", "model", "multimodal", "vision", "reasoning", "long-context", "tool-calling", "openai-compatible", "anthropic-compatible", "usage-priced", "card-required", "closed-source", "llms-txt", "new" ], "lastRelease": "2026-11-09", "graded": true, "anchor": { "graded": true, "score": 51.8, "grade": "D", "agentReady": false, "rank": 1017, "ranked": true, "rankOf": 1515, "categoryRank": 36, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 72, "maintenance": 46, "payments": 20, "reliability": 40, "schema": 60, "security": 64, "transparency": 53 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-09" }, "negative": 0, "verdict": "A cheap, capable model for the repeated parts of agent work, at $0.10 and $0.50 per million tokens with a 1M context and Meta's figures putting it level with Claude Haiku 5.5 on fewer tokens. Launched today on an API with no readable status page, SLA or deprecation policy, and closed, with no weights.", "bestFor": "Agents that hand out many small, bounded tasks (sub-agents, tool loops, routing, extraction over thousands of files) and want a cheap multimodal model with a 1M context behind the same API as a bigger Muse model.", "strengths": [ "$0.10 input, $0.004 cached and $0.50 output per million tokens up to 200K input, published without a login", "Text, image, video, audio and PDF in, a 1,048,576-token context and up to 524,288 output tokens", "The same request body as Muse Spark and Muse Wonder on Responses, Chat Completions and Messages endpoints", "Tool calling, structured output, computer use and search grounding", "Reasoning effort from minimal to max, with clear guidance on what to hand it and what not to", "3,000 requests and 4,000,000 tokens a minute per team, published" ], "weaknesses": [ "No weights and no parameter count published, so it can't be run locally", "Requests over 200K input tokens are billed at three times the rate for the whole request", "Default reasoning effort is max, which spends output tokens on simple routing calls unless set lower", "No readable status page, SLA, deprecation policy or API changelog, per the meta-model-api listing", "Benchmark and cost figures are Meta's own, several on internal benchmarks" ], "agentNotes": [ "Call https://api.meta.ai/v1/responses (or /chat/completions or /messages) with model muse-ember-1.0 and a bearer MODEL_API_KEY", "Set the effort explicitly, reasoning.effort on Responses or reasoning_effort on Chat Completions. It defaults to max, and none isn't accepted; minimal or low suits classification and routing", "Keep input under 200K tokens a request, cached tokens and previous_response_id history included, or the whole request bills at the long-context rate", "Use it for sub-agents and bounded repeated tasks, and a larger Muse model for the plan, as Meta advises", "Use strict structured output for extraction and routing steps", "In Claude Code, map the haiku alias and sub-agent model to muse-ember-1.0, per Meta's guide" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 51.8 } ], "editorialScores": { "ergonomics": 72, "maintenance": 46, "payments": 20, "reliability": 40, "schema": 60, "security": 64, "transparency": 41 }, "provenanceScore": 64, "checked": { "categories": { "ergonomics": "2026-11-09", "maintenance": "2026-11-09", "payments": "2026-11-09", "reliability": "2026-11-09", "schema": "2026-11-09", "security": "2026-11-09", "transparency": "2026-11-09" }, "last": "2026-11-09", "oldest": "2026-11-09", "stale": false, "staleAfterDays": 90 } }, "connect": { "http": "curl -X POST \"https://api.meta.ai/v1/responses\" \\\n -H \"Authorization: Bearer $MODEL_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"model\": \"muse-ember-1.0\",\n \"input\": \"Classify this support ticket as billing, bug, or feature request.\",\n \"reasoning\": {\"effort\": \"low\"}\n}'" }, "letme": { "capability": "https://letme.dev/inference.llm", "tool": "https://letme.dev/muse-ember" }, "sameCompany": [ "muse-spark-open", "muse-code", "muse-glimmer-30b" ], "sameModel": [ "meta-model-api" ], "area": "models", "unitPrices": [ { "item": "Muse Ember input", "unit": "1m-tokens", "usd": 0.1, "note": "Up to 200K input tokens a request; $0.30 above, for the whole request" }, { "item": "Muse Ember cached input", "unit": "1m-tokens", "usd": 0.004, "note": "$0.012 above 200K input tokens" }, { "item": "Muse Ember output", "unit": "1m-tokens", "usd": 0.5, "note": "$1.50 above 200K input tokens" } ], "provenance": { "legalEntity": "Meta Platforms, Inc.", "domain": "meta.ai", "domainRegistered": "2017-12-16", "endpointOnVendorDomain": true, "terms": "https://dev.meta.ai/legal/terms-of-service", "privacy": "https://www.facebook.com/privacy/policy/", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-11-09", "notes": [ "Company and platform facts are the meta-model-api listing's (checked 4 November 2026): Meta Platforms, Inc., or Meta Platforms Ireland Limited in the European Region, under the 9 October 2026 terms; no readable status page; no Model API changelog; no security.txt on dev.meta.ai.", "dev.meta.ai's and research.meta.ai's robots.txt allow our reader on the pages read on 9 November. domainRegistered is carried from the meta-model-api listing's RDAP reading." ], "score": 64 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/muse-ember.json", "live": { "slug": "muse-ember", "probe": { "target": "https://api.meta.ai/v1", "method": "get", "lastAt": "2026-11-09T20:50:02.257490788Z", "lastOk": true, "lastStatus": 404, "lastMs": 46, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 48, "p95ms24h": 72, "samples24h": 10, "samples30d": 10, "days": [ { "date": "2026-11-09", "probes": 10, "ok": 10 } ], "since": "2026-11-09T19:55:51.172718582Z" }, "updatedAt": "2026-11-09T20:50:02.257490788Z" }, "streak": { "days": 0, "from": "2026-11-09", "sinceWatching": true, "best": 0 } }, "answer": "Nemotron 3.5 Super VL scores 59.3 (C) on agent readiness against Muse Ember's 51.8 (D), and leads in 5 of 7 scored categories. Muse Ember leads on agent ergonomics and security \u0026 auth.", "b": { "slug": "nemotron-3-5-super-vl", "name": "Nemotron 3.5 Super VL", "vendor": "NVIDIA", "vendorUrl": "https://www.nvidia.com/en-us/ai-data-science/foundation-models/nemotron/", "kind": "model", "category": "inference", "summary": "Nemotron 3.5 Super VL is NVIDIA's open-weight vision-language model for agents, a 120B mixture of experts with 12B active parameters that reads text, images and video. NVIDIA hosts a free trial endpoint, and the weights are under OpenMDW-1.1.", "url": "https://www.anchorterminal.com/tools/nemotron-3-5-super-vl", "markdownUrl": "https://www.anchorterminal.com/tools/nemotron-3-5-super-vl.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/nemotron-3-5-super-vl.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/nemotron-3-5-super-vl.json", "dns": "nemotron-3-5-super-vl.grade.anchorterminal.com", "repo": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16", "license": "OpenMDW-1.1 for the weights (permissive, not an OSI licence). The hosted trial endpoint is under the NVIDIA API Trial Terms of Service, and the NIM container under the NVIDIA Software Licence Agreement", "transports": [ "http" ], "remoteUrl": "https://integrate.api.nvidia.com/v1", "packages": [ { "registry": "pypi", "name": "langchain-nvidia-ai-endpoints" } ], "auth": "api-key", "authNotes": "Bearer key (`nvapi-...`) in the Authorization header, generated by a signed-in person at build.nvidia.com/settings. NVIDIA's NGC docs say personal keys are limited to the services and role chosen at creation and take an expiry date, and organisation administrators can create service keys scoped to actions. The same key pulls the NIM container from nvcr.io. The Hugging Face weights are ungated and need no key.", "pricing": "free", "pricingNotes": "The hosted endpoint is free with no card, for prototyping, research and testing only, at up to 40 requests a minute and 10,000 a day. Production use needs a partner endpoint, such as Crusoe or DeepInfra at $0.10 input and $0.40 output per million tokens on OpenRouter, or self-hosting, where the NIM needs NVIDIA AI Enterprise at $4,500 a GPU a year (checked 2026-10-17).", "priceSummary": "from $0.15 / 1M in", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 on build.nvidia.com, the OpenAPI file or the NIM docs. The hosted endpoint is free behind a key and has no payment route (checked 2026-10-17).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-17" }, "docsUrl": "https://build.nvidia.com/nvidia/nemotron-3.5-super-vl-120b-a12b", "llmsTxt": "https://build.nvidia.com/llms.txt", "openapi": "https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-3_5-super-vl-120b-a12b-infer", "capabilities": [ "inference.open-weights", "inference.llm", "inference.local" ], "tags": [ "model", "open-weights", "hosted", "free", "no-card", "trial", "multimodal", "openai-compatible", "openapi", "llms-txt", "gpu", "new" ], "lastRelease": "2026-10-15", "graded": true, "anchor": { "graded": true, "score": 59.3, "grade": "C", "agentReady": false, "rank": 709, "ranked": true, "rankOf": 1515, "categoryRank": 25, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 65, "maintenance": 71, "payments": 35, "reliability": 58, "schema": 74, "security": 54, "transparency": 58 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-04" }, "negative": 0, "verdict": "NVIDIA's free endpoint takes OpenAI-format requests with typed tool calls, JSON Schema output and an OpenAPI 3.1 file, and the weights run anywhere under a permissive licence. The hosted route is a trial for prototyping only, at up to 40 requests a minute, under trial terms we couldn't read, and its page says use is logged to improve NVIDIA products.", "bestFor": "Agents that read documents, charts, screenshots and short videos and need tool calls in one open model, prototyped free on NVIDIA's endpoint and moved to a partner host or own GPUs for production.", "strengths": [ "OpenAPI 3.1 file for the hosted chat endpoint, with enums for `reasoning_effort`, `tool_choice` and `response_format`", "Tool calls with `tool_choice` auto, none, required or a named function, parallel calls, and `json_schema` structured output", "Weights in BF16 and NVFP4 under OpenMDW-1.1, a permissive licence with no field-of-use limits, plus open datasets and training recipes", "Free hosted endpoint with no card, on the same base URL and key as NVIDIA's other catalogue models", "Up to 1M tokens of context in the weights, and reasoning that can be switched off per request" ], "weaknesses": [ "NVIDIA says its hosted endpoints are for prototyping, research and testing only, and production use needs a partner endpoint or self-hosting", "Rate limit of up to 40 requests a minute and 10,000 a day, which NVIDIA says can vary with other users' traffic", "The NVIDIA API Trial Terms of Service, which govern the hosted endpoint, are on a host whose robots.txt answered access denied, so we didn't read them", "The hosted page lists 262K tokens of context while the card says 1M, and labels the model early access while the card says GA", "No changelog, deprecation policy or SLA for the hosted catalogue was found" ], "agentNotes": [ "Set `chat_template_kwargs` to `{\"enable_thinking\": false}` for short tasks. Reasoning is on by default, and reasoning tokens share the `max_tokens` budget", "Read reasoning from `reasoning_content` and the answer from `content`, and set `stream` explicitly since the API reference defaults it to true", "Don't send confidential or personal data to the hosted trial. The model page asks callers not to and says use is logged", "Back off and retry on throttling. Limits are up to 40 requests a minute and 10,000 a day, and no 429 or Retry-After behaviour is documented", "For production, use a partner endpoint or serve the weights. When self-hosting with NVIDIA's vLLM command, drop `--allowed-local-media-path=/` unless clients are trusted", "Set `NVIDIA_USAGE_TELEMETRY_ENABLED=false` if you use `langchain-nvidia-ai-endpoints` and don't want aggregate usage counts sent to NVIDIA" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 59.3 } ], "editorialScores": { "ergonomics": 65, "maintenance": 71, "payments": 35, "reliability": 58, "schema": 74, "security": 54, "transparency": 38 }, "provenanceScore": 77, "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": "2026-11-04", "oldest": "2026-11-04", "stale": false, "staleAfterDays": 90 } }, "connect": { "http": "curl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -H \"Accept: application/json\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"model\": \"nvidia/nemotron-3.5-super-vl-120b-a12b\",\n \"messages\": [{\"role\": \"user\", \"content\": \"Which number is larger, 9.11 or 9.8?\"}],\n \"temperature\": 1.0,\n \"top_p\": 0.95,\n \"max_tokens\": 8192,\n \"chat_template_kwargs\": {\"enable_thinking\": true},\n \"stream\": true\n }'" }, "letme": { "capability": "https://letme.dev/inference.open-weights", "tool": "https://letme.dev/nemotron-3-5-super-vl" }, "sameCompany": [ "nvidia-nemo-retriever", "nemo-guardrails", "nemotron-3-5-asr-streaming-0-6b", "parakeet-tdt-0-6b-v3", "nemotron-3-5-parse", "cosmos-reason2-2b", "nemotron-3-5-bolt-e4b-4gb", "nemotron-3-nano-30b-a3b", "nemotron-3-nano-4b", "nemotron-3-nano-omni-30b-a3b-reasoning", "nemotron-3-super-120b-a12b", "nemotron-3-ultra-550b-a55b", "nemotron-3-5-lightning-30b-a3b" ], "family": { "lab": "NVIDIA (Nemotron)", "family": "Nemotron 3", "url": "https://www.anchorterminal.com/open-weights/#nvidia", "others": [ { "name": "Nemotron 3 Nano 30B-A3B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", "params": "30B total, 3B active (31.6B per the safetensors index)", "listing": "https://www.anchorterminal.com/tools/nemotron-3-nano-30b-a3b" }, { "name": "Nemotron 3 Nano 30B-A3B Base", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16", "params": "30B total, 3B active" }, { "name": "Nemotron 3 Super 120B-A12B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "params": "120B total, 12B active", "listing": "https://www.anchorterminal.com/tools/nemotron-3-super-120b-a12b" }, { "name": "Nemotron 3 Super 120B-A12B Base", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16", "params": "120B total, 12B active" }, { "name": "Nemotron 3 Nano 4B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16", "params": "4B", "listing": "https://www.anchorterminal.com/tools/nemotron-3-nano-4b" }, { "name": "Nemotron 3 Nano Omni 30B-A3B Reasoning", "url": "https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16", "params": "30B total, 3B active", "listing": "https://www.anchorterminal.com/tools/nemotron-3-nano-omni-30b-a3b-reasoning" }, { "name": "Nemotron 3 Ultra 550B-A55B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "params": "550B total, 55B active", "listing": "https://www.anchorterminal.com/tools/nemotron-3-ultra-550b-a55b" }, { "name": "Nemotron 3 Ultra 550B-A55B Base", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16", "params": "550B total, 55B active" }, { "name": "Nemotron 3 Ultra 550B-A55B GenRM", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-GenRM", "params": "550B total, 55B active" }, { "name": "Nemotron 3.5 Lightning 30B-A3B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", "params": "30B total, 3B active", "listing": "https://www.anchorterminal.com/tools/nemotron-3-5-lightning-30b-a3b" }, { "name": "Nemotron 3.5 Lightning 30B-A3B Base", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16", "params": "30B total, 3B active" }, { "name": "Nemotron 3.5 Super VL 120B-A12B Base", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16", "params": "120B total, 12B active" }, { "name": "Nemotron 3.5 Bolt 74B-A9B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16", "params": "74B total, 9B active" }, { "name": "Nemotron 3.5 Bolt E4B 4GB", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB", "params": "8B total, 4B effective", "listing": "https://www.anchorterminal.com/tools/nemotron-3-5-bolt-e4b-4gb" }, { "name": "Nemotron Labs 3 Elastic 30B-A3B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B-BF16", "params": "30B total, 3B active" }, { "name": "Nemotron Labs 3 Puzzle 75B-A9B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-BF16", "params": "75B total, 9B active" }, { "name": "Nemotron 3 Labs Ultra Math SFT", "url": "https://huggingface.co/nvidia/Nemotron-3-Labs-Ultra-Math-SFT", "params": "550B total, 55B active" }, { "name": "Nemotron 3 Labs Ultra Math RL", "url": "https://huggingface.co/nvidia/Nemotron-3-Labs-Ultra-Math-RL", "params": "550B total, 55B active" }, { "name": "Nemotron Labs 3 Competitive Coding 550B-A55B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-3-Competitive-Coding-550B-A55B-NVFP4", "params": "550B total, 55B active" }, { "name": "nemotron-3.5-asr-streaming-0.6b", "url": "https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b", "params": "0.6B (638M per the safetensors count)", "listing": "https://www.anchorterminal.com/tools/nemotron-3-5-asr-streaming-0-6b" }, { "name": "Nemotron 3.5 Parse", "url": "https://huggingface.co/nvidia/Nemotron-3.5-Parse", "params": "0.631B (630,800,496 trainable parameters per the card)", "listing": "https://www.anchorterminal.com/tools/nemotron-3-5-parse" } ], "olderCount": 47, "unrestrictedCopies": 4 }, "area": "models", "provenance": { "legalEntity": "NVIDIA Corporation", "domain": "nvidia.com", "domainRegistered": "1993-04-20", "endpointOnVendorDomain": true, "terms": "https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf", "privacy": "https://www.nvidia.com/en-us/about-nvidia/privacy-policy/", "statusPage": "https://status.ngc.nvidia.com", "changelog": "", "securityTxt": "none", "checked": "2026-10-17", "notes": [ "The card names NVIDIA Corporation as model developer. The hosted endpoint is on integrate.api.nvidia.com and the model page on build.nvidia.com, both under nvidia.com. RDAP gives a registration date of 20 April 1993.", "The model page names the NVIDIA API Trial Terms of Service, a PDF on assets.ngc.nvidia.com, as the governing terms of the hosted trial. That host's robots.txt answered with an S3 AccessDenied error, so the PDF was not read, as for the nvidia-nemo-retriever listing.", "The privacy policy is NVIDIA's general policy, effective 22 September 2025. It does not address prompts sent to the API catalogue. The model page's consent text says use is logged for security and to improve NVIDIA products and services, and that the logged data for improvement is not linked to the user's identity.", "status.ngc.nvidia.com is a Statuspage site with components for NVIDIA Build and Cloud Functions, the service the hosted endpoints run on per the error URNs in the OpenAPI file.", "No changelog for the API catalogue or the model was found. The Hugging Face commit history records card revisions from 12 to 16 October 2026.", "www.nvidia.com/.well-known/security.txt answered 403 and build.nvidia.com/.well-known/security.txt returned the site's HTML page. Vulnerability reports go to NVIDIA PSIRT, linked from the model card." ], "score": 77 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/nemotron-3-5-super-vl.json", "live": { "slug": "nemotron-3-5-super-vl", "probe": { "target": "https://integrate.api.nvidia.com/v1", "method": "get", "lastAt": "2026-11-09T20:50:02.716579466Z", "lastOk": true, "lastStatus": 404, "lastMs": 58, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 51, "p95ms24h": 106, "samples24h": 244, "samples30d": 5656, "days": [ { "date": "2026-10-17", "probes": 21, "ok": 21 }, { "date": "2026-10-18", "probes": 256, "ok": 256 }, { "date": "2026-10-19", "probes": 255, "ok": 255 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 253, "ok": 253 }, { "date": "2026-10-22", "probes": 253, "ok": 253 }, { "date": "2026-10-23", "probes": 248, "ok": 248 }, { "date": "2026-10-24", "probes": 251, "ok": 251 }, { "date": "2026-10-25", "probes": 250, "ok": 250 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 251, "ok": 251 }, { "date": "2026-10-29", "probes": 248, "ok": 248 }, { "date": "2026-10-30", "probes": 249, "ok": 249 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 248, "ok": 248 }, { "date": "2026-11-04", "probes": 246, "ok": 246 }, { "date": "2026-11-05", "probes": 185, "ok": 185 }, { "date": "2026-11-06", "probes": 241, "ok": 241 }, { "date": "2026-11-07", "probes": 243, "ok": 243 }, { "date": "2026-11-08", "probes": 243, "ok": 243 }, { "date": "2026-11-09", "probes": 212, "ok": 212 } ], "since": "2026-10-17T00:00:00Z" }, "vendorStatus": { "page": "https://status.ngc.nvidia.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-09T20:46:34.613191899Z" }, "versions": [ { "registry": "pypi", "name": "langchain-nvidia-ai-endpoints", "version": "1.5.0", "released": "2026-10-14", "seenAt": "2026-11-09T02:42:33.566841498Z" } ], "pypiWeekly": 148188, "securityTxt": { "url": "https://nvidia.com/.well-known/security.txt", "state": "unknown", "checkedAt": "2026-11-09T16:06:56.882608758Z" }, "llmsTxt": { "url": "https://build.nvidia.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-09T15:40:20.844357139Z" }, "domain": { "domain": "nvidia.com", "registered": "1993-04-20", "source": "https://rdap.verisign.com/com/v1/domain/nvidia.com", "checkedAt": "2026-11-08T15:03:11.895084282Z" }, "models": { "nvidia/nemotron-3.5-super-vl": { "openrouterId": "nvidia/nemotron-3.5-super-vl", "tools": true, "structuredOutputs": true, "jsonMode": true, "reasoning": true, "input": [ "image", "text", "video" ], "promptCaching": true, "contextTokens": 1048576, "maxOutput": 943718, "checkedAt": "2026-11-08T23:49:27.027409601Z" } }, "updatedAt": "2026-11-09T20:50:02.716579466Z" }, "streak": { "days": 23, "from": "2026-10-17", "sinceWatching": true, "best": 23 } }, "edges": [ { "by": 25, "category": "maintenance", "leads": "nemotron-3-5-super-vl", "name": "Maintenance \u0026 community", "reasons": { "a": "Model reading. Released 9 November 2026 (30). No deprecation policy or notice period found, per the platform reading (0 of 12). Dated launches on the API, the latest Muse Wonder on 12 October and Muse Ember on 9 November (8 of 8). No Model API changelog; a help centre with tickets (8 of 15). No SDK of Meta's own (0 of 15, 0 of 10). 30 + 0 + 8 + 8 + 0 = 46.", "b": "Released on 15 October 2026. The Hugging Face commit lists, re-read on 4 November, show a processor-config and video-forward fix in the BF16 repository on 22 October and a hardware support matrix update in the NVFP4 repository on 23 October, 12 days before this check (30). NVIDIA released three Nemotron 3.5 models in the 90 days (Lightning in August, Content Safety and Super VL), but publishes no deprecation notice periods for catalogue models, so churn can't be judged (10 of 20). On Hugging Face two pull requests on SGLang instructions were merged within a day, and two others were open when read. Support for the free tier is the developer forum (15 of 25). NVIDIA maintains `langchain-nvidia-ai-endpoints` (1.5.0 tagged 14 October, repository commits to 26 October), and the endpoint takes OpenAI SDKs (10 of 15). Day-one recipes for vLLM 0.32.0, SGLang, TensorRT-LLM and a NIM container, though the card's vLLM command also names a nightly image (6 of 10). 30+10+15+10+6 = 71." }, "scores": { "a": 46, "b": 71 } }, { "by": 18, "category": "reliability", "leads": "nemotron-3-5-super-vl", "name": "Reliability", "reasons": { "a": "Model reading, for the surface it's called on, Meta Model API. No status page with readable history, per the meta-model-api listing's 4 November check (0), so no readable incident history (5). Rate limits published per team and per model, 3,000 RPM and 4,000,000 TPM for muse-ember-1.0, read 9 November (15). 429 and 503 with Retry-After, backoff guidance and rate-limit headers, per the meta-model-api listing (15). No SLA found (0). Muse Ember carries no preview label, but the API opened as a public preview in July and no general-availability notice was found, so half, as for the platform (5). 0 + 5 + 15 + 15 + 0 + 5 = 40.", "b": "Hosted reading, for NVIDIA's trial endpoint. status.ngc.nvidia.com is a Statuspage site with NVIDIA Build and Cloud Functions components and a readable history (20). In the 90 days to 4 November, re-read from history.atom, two incidents, both minor for an API caller, and none posted since 29 September. SMS verification for NVIDIA Build was unavailable in China from 23 to 29 September, which affects sign-up, and on 10 August new Cloud Functions deployments failed for about three hours while existing deployments kept running (20). build.nvidia.com gives limits of up to 40 requests a minute and 10,000 a day, and says they vary by model and with other users' traffic (12 of 15). The OpenAPI file documents a 202 pending result with an `NVCF-REQID` to poll, but no 429, Retry-After or backoff guidance, and NVIDIA's FAQ says to expect long waits under load (3 of 15). No SLA for the trial. NVIDIA's SLAs come with AI Enterprise for self-hosted software (0). The card says v1.0 GA, but the hosted page calls the model early access and NVIDIA calls the catalogue a trial for prototyping only (3 of 10). The model page re-read on 4 November still says early access, with a free endpoint marked available and 40 rpm. 20+20+12+3+0+3 = 58." }, "scores": { "a": 40, "b": 58 } }, { "by": 15, "category": "payments", "leads": "nemotron-3-5-super-vl", "name": "Payments \u0026 pricing", "reasons": { "a": "Published rubric. No payment protocol (0). Per-token prices for both tiers published without a login, read 9 November (20). No free API allowance found; billing needs a card, per the platform reading (0). Browser sign-up (0). 0 + 20 + 0 + 0 = 20.", "b": "No x402, MPP or L402 (0). The hosted endpoint is free and says so without a login, and the production routes are priced in public (AI Enterprise at $4,500 a GPU a year, partner hosts per million tokens), but the free endpoint can't be used in production and has no per-call price of its own (15 of 20). Free with no card per build.nvidia.com/llms.txt (20). A person signs in at build.nvidia.com, which uses SMS verification per the status page, to generate a key. No keyless or programmatic route (0). 35." }, "scores": { "a": 20, "b": 35 } }, { "by": 14, "category": "schema", "leads": "nemotron-3-5-super-vl", "name": "Schema \u0026 documentation", "reasons": { "a": "Model reading. No OpenAPI file; the Markdown reference is the contract, per the meta-model-api listing (0). llms.txt and Markdown copies of every page (10). The Muse Ember page and choose-a-model page say what to hand it and what not to (hard single-shot coding, knowledge-heavy questions, visual coding), with model ID, inputs, context, max output and effort range (18 of 20). JSON Schema tools and output, reasoning effort an enum, per the platform reading (12 of 15). Curl, Python and TypeScript examples and the platform's error guide (15). A versioned model ID and a dated launch post, with no API changelog (5 of 15). 0 + 10 + 18 + 12 + 15 + 5 = 60.", "b": "Model reading. An OpenAPI 3.1 file for this model's `/chat/completions` on docs.api.nvidia.com, with typed request and response schemas (25). build.nvidia.com/llms.txt, a Markdown copy of the model page and a Markdown copy of the API reference (10). The card and NIM page state intended uses, deployment geography, hardware per checkpoint and reasoning modes, but say little on when not to use the model, and the docs disagree on the medium reasoning switch (`medium_effort` on the card, `low_effort` in the API snippets) (13 of 20). Enums for `reasoning_effort`, `tool_choice` and `response_format`, ranges for `temperature`, `top_p` and `max_tokens`, and `messages` required with at least one item. `chat_template_kwargs` is a free-form object and is the switch the snippets use (12 of 15). Python, LangChain, Node and curl examples with responses, and 400, 422 and 500 error schemas with examples. No 429 (11 of 15). No changelog for the catalogue or the model. The OpenAPI version is 1.0.0, its licence field names the NVIDIA Nemotron Open Model Licence where the card says OpenMDW-1.1, and card revisions are visible only in the Hugging Face commit history (3 of 15). 74." }, "scores": { "a": 60, "b": 74 } }, { "by": 10, "category": "security", "leads": "muse-ember", "name": "Security \u0026 auth", "reasons": { "a": "Platform readings are the meta-model-api listing's of 4 November. Team keys, named, revocable, no scopes (20 of 30). Standard mode only, so content isn't used to train Meta models under the terms, with safety use reserved (17 of 20). Retention 'as needed' with zero retention through sales (10 of 15). Usage dashboard by model, no per-call log (5 of 15). No security.txt on dev.meta.ai, a bug bounty and a security commitments page, no named certification (12 of 20). 20 + 17 + 10 + 5 + 12 = 64.", "b": "Model reading. `nvapi-` bearer keys sent in a header. NVIDIA's NGC docs say personal keys are limited to the services and role chosen at creation and take an expiry, and service keys can be scoped to actions (25 of 30). Inference only, with no write operation, but no zero-retention option for the hosted trial was found, and the model page asks callers not to send confidential or personal data (8 of 20). The model reads web pages, PDFs and images an agent passes it, and NVIDIA publishes safety, bias and privacy subcards, but no prompt-injection guidance or results were found (5 of 15). No per-call log for API callers was found, only rate limits shown in the account (3 of 15). NVIDIA PSIRT runs coordinated disclosure and publishes security bulletins, linked from the card, the reading nvidia-nemo-retriever and nemo-guardrails give the same programme (13). www.nvidia.com/.well-known/security.txt answered 403 per the 2 November check and build.nvidia.com has none, and no certification or bug bounty for the API catalogue was found (13 of 20). 25+8+5+3+13 = 54." }, "scores": { "a": 64, "b": 54 } }, { "by": 7, "category": "ergonomics", "leads": "muse-ember", "name": "Agent ergonomics", "reasons": { "a": "Model reading. Tool calls, parallel calls, computer use and search grounding, with tool_choice limited to auto per the platform reading (15 of 20). Strict structured output (15). Automatic prompt caching, cached input at 4% of the input price (15). A 1,048,576-token context, but requests over 200K input tokens bill at three times the rate for the whole request (12 of 15). No batch endpoint (0). No SDK of Meta's own; OpenAI and Anthropic SDKs against compatible endpoints (0). OpenAI-style errors with fixes and retryable codes (15). 15 + 15 + 15 + 12 + 0 + 0 + 15 = 72.", "b": "Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). OpenAI-format tools, `tool_choice` auto, none, required or a named function, and parallel calls on by default (20 of 20). `response_format` with `json_schema` and `strict` in the OpenAPI file. Not tested by us (12 of 15). The card describes prefix caching for self-hosted serving, but no caching on the hosted endpoint is documented (2 of 10). 1M tokens in the weights, but the hosted page lists 262K, and completions are capped at 131,072 tokens (12 of 15). No batch mode (0 of 10). Any OpenAI SDK works with the base URL, and NVIDIA maintains `langchain-nvidia-ai-endpoints`. Only `messages` is required, but reasoning defaults to on at high effort and the reference defaults `stream` to true (10 of 15). Errors carry a message, type and request id, with no 429 or rate-limit body documented (9 of 15). 65." }, "scores": { "a": 72, "b": 65 } } ], "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Meta", "b": "NVIDIA", "name": "Vendor" }, { "a": "https://api.meta.ai/v1", "b": "https://integrate.api.nvidia.com/v1", "name": "Hosted endpoint" }, { "a": "", "b": "HTTP", "name": "Transports" }, { "a": "API key", "b": "API key", "name": "Auth" }, { "a": "Pay per use", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Closed model, used through Meta Model API and Muse Code under the Meta Model API Terms of Service (last updated 9 October 2026). No open weights; Meta's open-weight models are Muse Spark Open and Muse Glimmer", "b": "OpenMDW-1.1 for the weights (permissive, not an OSI licence). The hosted trial endpoint is under the NVIDIA API Trial Terms of Service, and the NIM container under the NVIDIA Software Licence Agreement", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-11-09", "b": "2026-10-15", "name": "Last release" }, { "a": "2026-10-02", "b": "not read yet", "name": "Terms last updated" }, { "a": "couldn't be read", "b": "no date given", "name": "Privacy policy last updated" }, { "a": "yes", "b": "not read yet", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "not read yet", "name": "Terms restrict automated access" }, { "a": "yes", "b": "not read yet", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not read yet", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "not read yet", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "3/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Nemotron 3.5 Super VL scores 59.3 (C) on agent readiness against Muse Ember's 51.8 (D), and leads in 5 of 7 scored categories. Muse Ember leads on agent ergonomics and security \u0026 auth.", "question": "Which is better for AI agents, Muse Ember or Nemotron 3.5 Super VL?" }, { "answer": "Both need an API key.", "question": "Do Muse Ember and Nemotron 3.5 Super VL need an API key?" }, { "answer": "Yes. Muse Ember has a hosted endpoint at https://api.meta.ai/v1 and Nemotron 3.5 Super VL at https://integrate.api.nvidia.com/v1.", "question": "Can an agent call Muse Ember and Nemotron 3.5 Super VL without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Agent ergonomics, 72 against 65", "Security \u0026 auth, 64 against 54" ], "also": null, "goodFor": "Agents that hand out many small, bounded tasks (sub-agents, tool loops, routing, extraction over thousands of files) and want a cheap multimodal model with a 1M context behind the same API as a bigger Muse model.", "slug": "muse-ember", "watchFor": "No weights and no parameter count published, so it can't be run locally" }, { "aheadOn": [ "Reliability, 58 against 40", "Schema \u0026 documentation, 74 against 60", "Payments \u0026 pricing, 35 against 20", "Maintenance \u0026 community, 71 against 46", "Transparency \u0026 trust, 58 against 53" ], "also": [ "Free to start without a card" ], "goodFor": "Agents that read documents, charts, screenshots and short videos and need tool calls in one open model, prototyped free on NVIDIA's endpoint and moved to a partner host or own GPUs for production.", "slug": "nemotron-3-5-super-vl", "watchFor": "NVIDIA says its hosted endpoints are for prototyping, research and testing only, and production use needs a partner endpoint or self-hosting" } ], "history": { "muse-ember": null, "nemotron-3-5-super-vl": [ { "causes": [ "correction" ], "date": "2026-11-04", "delta": 0.5, "from": 58.8, "fromGrade": "C", "to": 59.3, "toGrade": "C" }, { "causes": [ "method" ], "date": "2026-10-30", "delta": -0.2, "from": 59, "fromGrade": "C", "to": 58.8, "toGrade": "C" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 58.9, "fromGrade": "C", "to": 59, "toGrade": "C" } ] }, "job": { "capability": "inference.llm", "name": "LLM inference" }, "others": [ { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-muse-ember.json", "title": "Amazon Bedrock vs Muse Ember", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-nemotron-3-5-super-vl.json", "title": "Amazon Bedrock vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-muse-ember.json", "title": "Claude API vs Muse Ember", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-nemotron-3-5-super-vl.json", "title": "Claude API vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/antseed-vs-muse-ember.json", "title": "Antseed vs Muse Ember", "url": "https://www.anchorterminal.com/compare/antseed-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/antseed-vs-nemotron-3-5-super-vl.json", "title": "Antseed vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/antseed-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-muse-ember.json", "title": "Azure OpenAI in Foundry Models vs Muse Ember", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-nemotron-3-5-super-vl.json", "title": "Azure OpenAI in Foundry Models vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-muse-ember.json", "title": "BlockRun.AI vs Muse Ember", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-nemotron-3-5-super-vl.json", "title": "BlockRun.AI vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/cerebras-inference-vs-muse-ember.json", "title": "Cerebras Inference vs Muse Ember", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/cerebras-inference-vs-nemotron-3-5-super-vl.json", "title": "Cerebras Inference vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-muse-ember.json", "title": "Cloudflare AI Gateway vs Muse Ember", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-nemotron-3-5-super-vl.json", "title": "Cloudflare AI Gateway vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-muse-ember.json", "title": "Cloudflare Workers AI vs Muse Ember", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-nemotron-3-5-super-vl.json", "title": "Cloudflare Workers AI vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-muse-ember.json", "title": "Cohere Chat API (Command models) vs Muse Ember", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-nemotron-3-5-super-vl.json", "title": "Cohere Chat API (Command models) vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/deepinfra-vs-muse-ember.json", "title": "DeepInfra vs Muse Ember", "url": "https://www.anchorterminal.com/compare/deepinfra-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/deepinfra-vs-nemotron-3-5-super-vl.json", "title": "DeepInfra vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/deepinfra-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/deepseek-api-vs-muse-ember.json", "title": "DeepSeek API vs Muse Ember", "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/deepseek-api-vs-nemotron-3-5-super-vl.json", "title": "DeepSeek API vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/eden-ai-vs-muse-ember.json", "title": "Eden AI vs Muse Ember", "url": "https://www.anchorterminal.com/compare/eden-ai-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/eden-ai-vs-nemotron-3-5-super-vl.json", "title": "Eden AI vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/eden-ai-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-muse-ember.json", "title": "Glimpse vs Muse Ember", "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-nemotron-3-5-super-vl.json", "title": "Glimpse vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-muse-ember.json", "title": "Fireworks AI Inference vs Muse Ember", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-nemotron-3-5-super-vl.json", "title": "Fireworks AI Inference vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/gemini-api-vs-muse-ember.json", "title": "Gemini Developer API vs Muse Ember", "url": "https://www.anchorterminal.com/compare/gemini-api-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/gemini-api-vs-nemotron-3-5-super-vl.json", "title": "Gemini Developer API vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/gemini-api-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/groq-vs-muse-ember.json", "title": "GroqCloud vs Muse Ember", "url": "https://www.anchorterminal.com/compare/groq-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/groq-vs-nemotron-3-5-super-vl.json", "title": "GroqCloud vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/groq-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-muse-ember.json", "title": "Hugging Face Inference Providers vs Muse Ember", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-ember.json", "title": "Inkling 2 Small vs Muse Ember", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-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/jais-3-vs-muse-ember.json", "title": "Jais 3 vs Muse Ember", "url": "https://www.anchorterminal.com/compare/jais-3-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-nemotron-3-5-super-vl.json", "title": "Jais 3 vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/jais-3-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-muse-ember.json", "title": "Meta Model API vs Muse Ember", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-nemotron-3-5-super-vl.json", "title": "Meta Model API vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/minimax-api-vs-muse-ember.json", "title": "MiniMax API vs Muse Ember", "url": "https://www.anchorterminal.com/compare/minimax-api-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/minimax-api-vs-nemotron-3-5-super-vl.json", "title": "MiniMax API vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/minimax-api-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-muse-ember.json", "title": "Mistral AI API vs Muse Ember", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-nemotron-3-5-super-vl.json", "title": "Mistral AI API vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-muse-spark-open.json", "title": "Muse Ember vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-muse-spark-open" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-novita-ai.json", "title": "Muse Ember vs Novita AI", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-novita-ai" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-openai-api.json", "title": "Muse Ember vs OpenAI API", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-openai-api" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-openrouter.json", "title": "Muse Ember vs OpenRouter", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-openrouter" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-prism-inference.json", "title": "Muse Ember vs Prism Inference", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-ramp-router.json", "title": "Muse Ember vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-reflection-beam.json", "title": "Muse Ember vs Beam 1.0", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-reflection-beam" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-routerplus.json", "title": "Muse Ember vs RouterPlus", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-routerplus" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-sambanova.json", "title": "Muse Ember vs SambaCloud", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-sambanova" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-siliconflow.json", "title": "Muse Ember vs SiliconFlow", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-siliconflow" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-simplismart.json", "title": "Muse Ember vs Simplismart", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-simplismart" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-stepfun-api.json", "title": "Muse Ember vs StepFun API", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-stepfun-api" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-swe-2-flash.json", "title": "Muse Ember vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-tencent-tokenhub.json", "title": "Muse Ember vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-together-inference.json", "title": "Muse Ember vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-together-inference" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-vercel-ai-gateway.json", "title": "Muse Ember vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-vertex-ai.json", "title": "Muse Ember vs Vertex AI (Gemini Enterprise Agent Platform)", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-vertex-ai" }, { "json": "https://www.anchorterminal.com/compare/muse-ember-vs-xai-api.json", "title": "Muse Ember vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-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/nemotron-3-5-super-vl-vs-openai-api.json", "title": "Nemotron 3.5 Super VL vs OpenAI API", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-openai-api" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-openrouter.json", "title": "Nemotron 3.5 Super VL vs OpenRouter", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-openrouter" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-ramp-router.json", "title": "Nemotron 3.5 Super VL vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-routerplus.json", "title": "Nemotron 3.5 Super VL vs RouterPlus", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-routerplus" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-stepfun-api.json", "title": "Nemotron 3.5 Super VL vs StepFun API", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-stepfun-api" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-swe-2-flash.json", "title": "Nemotron 3.5 Super VL vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-vercel-ai-gateway.json", "title": "Nemotron 3.5 Super VL vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-xai-api.json", "title": "Nemotron 3.5 Super VL vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-nemotron-3-5-super-vl.json", "title": "Hugging Face Inference Providers vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-novita-ai.json", "title": "Nemotron 3.5 Super VL vs Novita AI", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-novita-ai" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-prism-inference.json", "title": "Nemotron 3.5 Super VL vs Prism Inference", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-reflection-beam.json", "title": "Nemotron 3.5 Super VL vs Beam 1.0", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-reflection-beam" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-sambanova.json", "title": "Nemotron 3.5 Super VL vs SambaCloud", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-sambanova" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-siliconflow.json", "title": "Nemotron 3.5 Super VL vs SiliconFlow", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-siliconflow" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-simplismart.json", "title": "Nemotron 3.5 Super VL vs Simplismart", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-simplismart" }, { "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/nemotron-3-5-super-vl-vs-together-inference.json", "title": "Nemotron 3.5 Super VL vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-together-inference" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-underdog.json", "title": "Nemotron 3.5 Super VL vs Underdog", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-underdog" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-vertex-ai.json", "title": "Nemotron 3.5 Super VL vs Vertex AI (Gemini Enterprise Agent Platform)", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-vertex-ai" } ], "panel": null, "scores": [ { "by": 18, "edge": "nemotron-3-5-super-vl", "key": "reliability", "muse-ember": 40, "name": "Reliability", "nemotron-3-5-super-vl": 58, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 14, "edge": "nemotron-3-5-super-vl", "key": "schema", "muse-ember": 60, "name": "Schema \u0026 documentation", "nemotron-3-5-super-vl": 74, "weight": 13 }, { "by": 7, "edge": "muse-ember", "key": "ergonomics", "muse-ember": 72, "name": "Agent ergonomics", "nemotron-3-5-super-vl": 65, "weight": 13 }, { "by": 10, "edge": "muse-ember", "key": "security", "muse-ember": 64, "name": "Security \u0026 auth", "nemotron-3-5-super-vl": 54, "weight": 14 }, { "by": 15, "edge": "nemotron-3-5-super-vl", "key": "payments", "muse-ember": 20, "name": "Payments \u0026 pricing", "nemotron-3-5-super-vl": 35, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 25, "edge": "nemotron-3-5-super-vl", "key": "maintenance", "muse-ember": 46, "name": "Maintenance \u0026 community", "nemotron-3-5-super-vl": 71, "weight": 7 }, { "by": 5, "edge": "nemotron-3-5-super-vl", "key": "transparency", "muse-ember": 53, "name": "Transparency \u0026 trust", "nemotron-3-5-super-vl": 58, "weight": 7 } ], "summary": "Nemotron 3.5 Super VL scores 59.3 (C) on agent readiness against Muse Ember's 51.8 (D), and leads in 5 of 7 scored categories. Muse Ember leads on agent ergonomics and security \u0026 auth. Both do llm inference.", "tasks": null, "tutorials": [], "verdicts": { "muse-ember": "A cheap, capable model for the repeated parts of agent work, at $0.10 and $0.50 per million tokens with a 1M context and Meta's figures putting it level with Claude Haiku 5.5 on fewer tokens. Launched today on an API with no readable status page, SLA or deprecation policy, and closed, with no weights.", "nemotron-3-5-super-vl": "NVIDIA's free endpoint takes OpenAI-format requests with typed tool calls, JSON Schema output and an OpenAPI 3.1 file, and the weights run anywhere under a permissive licence. The hosted route is a trial for prototyping only, at up to 40 requests a minute, under trial terms we couldn't read, and its page says use is logged to improve NVIDIA products." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/muse-ember-vs-nemotron-3-5-super-vl", "json": "https://www.anchorterminal.com/compare/muse-ember-vs-nemotron-3-5-super-vl.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/muse-ember-vs-nemotron-3-5-super-vl.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/muse-ember-vs-nemotron-3-5-super-vl.min.md" }, "markdown": "Nemotron 3.5 Super VL scores 59.3 (C) on agent readiness against Muse Ember's 51.8 (D), and leads in 5 of 7 scored categories. Muse Ember leads on agent ergonomics and security \u0026 auth. Both do llm inference.\n\n- Muse Ember: grade D, 51.8/100, rank #1017 of 1515. Markdown https://www.anchorterminal.com/tools/muse-ember.md · JSON https://www.anchorterminal.com/api/v1/tools/muse-ember.json\n- Nemotron 3.5 Super VL: grade C, 59.3/100, rank #709 of 1515. Markdown https://www.anchorterminal.com/tools/nemotron-3-5-super-vl.md · JSON https://www.anchorterminal.com/api/v1/tools/nemotron-3-5-super-vl.json\n- Best model APIs and inference for AI agents: https://www.anchorterminal.com/best/inference/index.md\n- All 871 models comparisons: https://www.anchorterminal.com/compare/inference/index.md\n\n## Which one, for what\n\n### Muse Ember (D)\n\nGood for: Agents that hand out many small, bounded tasks (sub-agents, tool loops, routing, extraction over thousands of files) and want a cheap multimodal model with a 1M context behind the same API as a bigger Muse model.\n\nAhead on:\n- Agent ergonomics, 72 against 65\n- Security \u0026 auth, 64 against 54\n\nWatch for: No weights and no parameter count published, so it can't be run locally\n\n### Nemotron 3.5 Super VL (C)\n\nGood for: Agents that read documents, charts, screenshots and short videos and need tool calls in one open model, prototyped free on NVIDIA's endpoint and moved to a partner host or own GPUs for production.\n\nAhead on:\n- Reliability, 58 against 40\n- Schema \u0026 documentation, 74 against 60\n- Payments \u0026 pricing, 35 against 20\n- Maintenance \u0026 community, 71 against 46\n- Transparency \u0026 trust, 58 against 53\n\nAlso in its favour:\n- Free to start without a card\n\nWatch for: NVIDIA says its hosted endpoints are for prototyping, research and testing only, and production use needs a partner endpoint or self-hosting\n\n\n## Why the edge\n\n### Maintenance \u0026 community: Nemotron 3.5 Super VL +25\n\n- Muse Ember (46): Model reading. Released 9 November 2026 (30). No deprecation policy or notice period found, per the platform reading (0 of 12). Dated launches on the API, the latest Muse Wonder on 12 October and Muse Ember on 9 November (8 of 8). No Model API changelog; a help centre with tickets (8 of 15). No SDK of Meta's own (0 of 15, 0 of 10). 30 + 0 + 8 + 8 + 0 = 46.\n- Nemotron 3.5 Super VL (71): Released on 15 October 2026. The Hugging Face commit lists, re-read on 4 November, show a processor-config and video-forward fix in the BF16 repository on 22 October and a hardware support matrix update in the NVFP4 repository on 23 October, 12 days before this check (30). NVIDIA released three Nemotron 3.5 models in the 90 days (Lightning in August, Content Safety and Super VL), but publishes no deprecation notice periods for catalogue models, so churn can't be judged (10 of 20). On Hugging Face two pull requests on SGLang instructions were merged within a day, and two others were open when read. Support for the free tier is the developer forum (15 of 25). NVIDIA maintains `langchain-nvidia-ai-endpoints` (1.5.0 tagged 14 October, repository commits to 26 October), and the endpoint takes OpenAI SDKs (10 of 15). Day-one recipes for vLLM 0.32.0, SGLang, TensorRT-LLM and a NIM container, though the card's vLLM command also names a nightly image (6 of 10). 30+10+15+10+6 = 71.\n\n### Reliability: Nemotron 3.5 Super VL +18\n\n- Muse Ember (40): Model reading, for the surface it's called on, Meta Model API. No status page with readable history, per the meta-model-api listing's 4 November check (0), so no readable incident history (5). Rate limits published per team and per model, 3,000 RPM and 4,000,000 TPM for muse-ember-1.0, read 9 November (15). 429 and 503 with Retry-After, backoff guidance and rate-limit headers, per the meta-model-api listing (15). No SLA found (0). Muse Ember carries no preview label, but the API opened as a public preview in July and no general-availability notice was found, so half, as for the platform (5). 0 + 5 + 15 + 15 + 0 + 5 = 40.\n- Nemotron 3.5 Super VL (58): Hosted reading, for NVIDIA's trial endpoint. status.ngc.nvidia.com is a Statuspage site with NVIDIA Build and Cloud Functions components and a readable history (20). In the 90 days to 4 November, re-read from history.atom, two incidents, both minor for an API caller, and none posted since 29 September. SMS verification for NVIDIA Build was unavailable in China from 23 to 29 September, which affects sign-up, and on 10 August new Cloud Functions deployments failed for about three hours while existing deployments kept running (20). build.nvidia.com gives limits of up to 40 requests a minute and 10,000 a day, and says they vary by model and with other users' traffic (12 of 15). The OpenAPI file documents a 202 pending result with an `NVCF-REQID` to poll, but no 429, Retry-After or backoff guidance, and NVIDIA's FAQ says to expect long waits under load (3 of 15). No SLA for the trial. NVIDIA's SLAs come with AI Enterprise for self-hosted software (0). The card says v1.0 GA, but the hosted page calls the model early access and NVIDIA calls the catalogue a trial for prototyping only (3 of 10). The model page re-read on 4 November still says early access, with a free endpoint marked available and 40 rpm. 20+20+12+3+0+3 = 58.\n\n### Payments \u0026 pricing: Nemotron 3.5 Super VL +15\n\n- Muse Ember (20): Published rubric. No payment protocol (0). Per-token prices for both tiers published without a login, read 9 November (20). No free API allowance found; billing needs a card, per the platform reading (0). Browser sign-up (0). 0 + 20 + 0 + 0 = 20.\n- Nemotron 3.5 Super VL (35): No x402, MPP or L402 (0). The hosted endpoint is free and says so without a login, and the production routes are priced in public (AI Enterprise at $4,500 a GPU a year, partner hosts per million tokens), but the free endpoint can't be used in production and has no per-call price of its own (15 of 20). Free with no card per build.nvidia.com/llms.txt (20). A person signs in at build.nvidia.com, which uses SMS verification per the status page, to generate a key. No keyless or programmatic route (0). 35.\n\n### Schema \u0026 documentation: Nemotron 3.5 Super VL +14\n\n- Muse Ember (60): Model reading. No OpenAPI file; the Markdown reference is the contract, per the meta-model-api listing (0). llms.txt and Markdown copies of every page (10). The Muse Ember page and choose-a-model page say what to hand it and what not to (hard single-shot coding, knowledge-heavy questions, visual coding), with model ID, inputs, context, max output and effort range (18 of 20). JSON Schema tools and output, reasoning effort an enum, per the platform reading (12 of 15). Curl, Python and TypeScript examples and the platform's error guide (15). A versioned model ID and a dated launch post, with no API changelog (5 of 15). 0 + 10 + 18 + 12 + 15 + 5 = 60.\n- Nemotron 3.5 Super VL (74): Model reading. An OpenAPI 3.1 file for this model's `/chat/completions` on docs.api.nvidia.com, with typed request and response schemas (25). build.nvidia.com/llms.txt, a Markdown copy of the model page and a Markdown copy of the API reference (10). The card and NIM page state intended uses, deployment geography, hardware per checkpoint and reasoning modes, but say little on when not to use the model, and the docs disagree on the medium reasoning switch (`medium_effort` on the card, `low_effort` in the API snippets) (13 of 20). Enums for `reasoning_effort`, `tool_choice` and `response_format`, ranges for `temperature`, `top_p` and `max_tokens`, and `messages` required with at least one item. `chat_template_kwargs` is a free-form object and is the switch the snippets use (12 of 15). Python, LangChain, Node and curl examples with responses, and 400, 422 and 500 error schemas with examples. No 429 (11 of 15). No changelog for the catalogue or the model. The OpenAPI version is 1.0.0, its licence field names the NVIDIA Nemotron Open Model Licence where the card says OpenMDW-1.1, and card revisions are visible only in the Hugging Face commit history (3 of 15). 74.\n\n### Security \u0026 auth: Muse Ember +10\n\n- Muse Ember (64): Platform readings are the meta-model-api listing's of 4 November. Team keys, named, revocable, no scopes (20 of 30). Standard mode only, so content isn't used to train Meta models under the terms, with safety use reserved (17 of 20). Retention 'as needed' with zero retention through sales (10 of 15). Usage dashboard by model, no per-call log (5 of 15). No security.txt on dev.meta.ai, a bug bounty and a security commitments page, no named certification (12 of 20). 20 + 17 + 10 + 5 + 12 = 64.\n- Nemotron 3.5 Super VL (54): Model reading. `nvapi-` bearer keys sent in a header. NVIDIA's NGC docs say personal keys are limited to the services and role chosen at creation and take an expiry, and service keys can be scoped to actions (25 of 30). Inference only, with no write operation, but no zero-retention option for the hosted trial was found, and the model page asks callers not to send confidential or personal data (8 of 20). The model reads web pages, PDFs and images an agent passes it, and NVIDIA publishes safety, bias and privacy subcards, but no prompt-injection guidance or results were found (5 of 15). No per-call log for API callers was found, only rate limits shown in the account (3 of 15). NVIDIA PSIRT runs coordinated disclosure and publishes security bulletins, linked from the card, the reading nvidia-nemo-retriever and nemo-guardrails give the same programme (13). www.nvidia.com/.well-known/security.txt answered 403 per the 2 November check and build.nvidia.com has none, and no certification or bug bounty for the API catalogue was found (13 of 20). 25+8+5+3+13 = 54.\n\n### Agent ergonomics: Muse Ember +7\n\n- Muse Ember (72): Model reading. Tool calls, parallel calls, computer use and search grounding, with tool_choice limited to auto per the platform reading (15 of 20). Strict structured output (15). Automatic prompt caching, cached input at 4% of the input price (15). A 1,048,576-token context, but requests over 200K input tokens bill at three times the rate for the whole request (12 of 15). No batch endpoint (0). No SDK of Meta's own; OpenAI and Anthropic SDKs against compatible endpoints (0). OpenAI-style errors with fixes and retryable codes (15). 15 + 15 + 15 + 12 + 0 + 0 + 15 = 72.\n- Nemotron 3.5 Super VL (65): Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). OpenAI-format tools, `tool_choice` auto, none, required or a named function, and parallel calls on by default (20 of 20). `response_format` with `json_schema` and `strict` in the OpenAPI file. Not tested by us (12 of 15). The card describes prefix caching for self-hosted serving, but no caching on the hosted endpoint is documented (2 of 10). 1M tokens in the weights, but the hosted page lists 262K, and completions are capped at 131,072 tokens (12 of 15). No batch mode (0 of 10). Any OpenAI SDK works with the base URL, and NVIDIA maintains `langchain-nvidia-ai-endpoints`. Only `messages` is required, but reasoning defaults to on at high effort and the reference defaults `stream` to true (10 of 15). Errors carry a message, type and request id, with no 429 or rate-limit body documented (9 of 15). 65.\n\n## Score by category\n\n| Category | Weight | Muse Ember | Nemotron 3.5 Super VL | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 40 | 58 | Nemotron 3.5 Super VL +18 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 60 | 74 | Nemotron 3.5 Super VL +14 |\n| Agent ergonomics | 13% (16.2 this run) | 72 | 65 | Muse Ember +7 |\n| Security \u0026 auth | 14% (17.5 this run) | 64 | 54 | Muse Ember +10 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 35 | Nemotron 3.5 Super VL +15 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 46 | 71 | Nemotron 3.5 Super VL +25 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 53 | 58 | Nemotron 3.5 Super VL +5 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **51.8 · D** | **59.3 · C** | |\n\n## Facts side by side\n\n| Fact | Muse Ember | Nemotron 3.5 Super VL |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Meta | NVIDIA |\n| Hosted endpoint | `https://api.meta.ai/v1` | `https://integrate.api.nvidia.com/v1` |\n| Transports | | HTTP |\n| Auth | API key | API key |\n| Pricing | Pay per use | Free |\n| x402 | no | no |\n| Licence | Closed model, used through Meta Model API and Muse Code under the Meta Model API Terms of Service (last updated 9 October 2026). No open weights; Meta's open-weight models are Muse Spark Open and Muse Glimmer | OpenMDW-1.1 for the weights (permissive, not an OSI licence). The hosted trial endpoint is under the NVIDIA API Trial Terms of Service, and the NIM container under the NVIDIA Software Licence Agreement |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-11-09 | 2026-10-15 |\n| Terms last updated | 2026-10-02 | not read yet |\n| Privacy policy last updated | couldn't be read | no date given |\n| Customer content may train models | yes | not read yet |\n| Terms restrict automated access | not found in the text | not read yet |\n| Terms restrict benchmarking | yes | not read yet |\n| Terms or service can change without notice | not found in the text | not read yet |\n| Arbitration or class-action waiver | yes | not read yet |\n| Agent reviews | none | 3/5 (4) |\n\n## How the scores have moved\n\n### Muse Ember\n\nNo score change since it was listed.\n\n### Nemotron 3.5 Super VL\n\n- +0.5 on 4 November 2026: correction\n- -0.2 on 30 October 2026: checklist\n- +0.1 on 27 October 2026: checklist\n\n## Verdicts\n\n**Muse Ember.** A cheap, capable model for the repeated parts of agent work, at $0.10 and $0.50 per million tokens with a 1M context and Meta's figures putting it level with Claude Haiku 5.5 on fewer tokens. Launched today on an API with no readable status page, SLA or deprecation policy, and closed, with no weights.\n\n**Nemotron 3.5 Super VL.** NVIDIA's free endpoint takes OpenAI-format requests with typed tool calls, JSON Schema output and an OpenAPI 3.1 file, and the weights run anywhere under a permissive licence. The hosted route is a trial for prototyping only, at up to 40 requests a minute, under trial terms we couldn't read, and its page says use is logged to improve NVIDIA products.\n\n## Before you call either\n\n### Muse Ember\n\n1. Call https://api.meta.ai/v1/responses (or /chat/completions or /messages) with model muse-ember-1.0 and a bearer MODEL_API_KEY\n2. Set the effort explicitly, reasoning.effort on Responses or reasoning_effort on Chat Completions. It defaults to max, and none isn't accepted; minimal or low suits classification and routing\n3. Keep input under 200K tokens a request, cached tokens and previous_response_id history included, or the whole request bills at the long-context rate\n4. Use it for sub-agents and bounded repeated tasks, and a larger Muse model for the plan, as Meta advises\n5. Use strict structured output for extraction and routing steps\n6. In Claude Code, map the haiku alias and sub-agent model to muse-ember-1.0, per Meta's guide\n\n### Nemotron 3.5 Super VL\n\n1. Set `chat_template_kwargs` to `{\"enable_thinking\": false}` for short tasks. Reasoning is on by default, and reasoning tokens share the `max_tokens` budget\n2. Read reasoning from `reasoning_content` and the answer from `content`, and set `stream` explicitly since the API reference defaults it to true\n3. Don't send confidential or personal data to the hosted trial. The model page asks callers not to and says use is logged\n4. Back off and retry on throttling. Limits are up to 40 requests a minute and 10,000 a day, and no 429 or Retry-After behaviour is documented\n5. For production, use a partner endpoint or serve the weights. When self-hosting with NVIDIA's vLLM command, drop `--allowed-local-media-path=/` unless clients are trusted\n6. Set `NVIDIA_USAGE_TELEMETRY_ENABLED=false` if you use `langchain-nvidia-ai-endpoints` and don't want aggregate usage counts sent to NVIDIA\n\n## Questions\n\n### Which is better for AI agents, Muse Ember or Nemotron 3.5 Super VL?\n\nNemotron 3.5 Super VL scores 59.3 (C) on agent readiness against Muse Ember's 51.8 (D), and leads in 5 of 7 scored categories. Muse Ember leads on agent ergonomics and security \u0026 auth.\n\n### Do Muse Ember and Nemotron 3.5 Super VL need an API key?\n\nBoth need an API key.\n\n### Can an agent call Muse Ember and Nemotron 3.5 Super VL without installing anything?\n\nYes. Muse Ember has a hosted endpoint at https://api.meta.ai/v1 and Nemotron 3.5 Super VL at https://integrate.api.nvidia.com/v1.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/muse-ember-vs-nemotron-3-5-super-vl.json, and with the fewest tokens: https://www.anchorterminal.com/compare/muse-ember-vs-nemotron-3-5-super-vl.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"muse-ember\", \"b\": \"nemotron-3-5-super-vl\"}`. From a terminal: `anchor compare muse-ember nemotron-3-5-super-vl`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/muse-ember.json and https://www.anchorterminal.com/api/v1/tools/nemotron-3-5-super-vl.json\n\n## Other comparisons with Muse Ember or Nemotron 3.5 Super VL\n\n- [Amazon Bedrock vs Muse Ember](https://www.anchorterminal.com/compare/amazon-bedrock-vs-muse-ember.md)\n- [Amazon Bedrock vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/amazon-bedrock-vs-nemotron-3-5-super-vl.md)\n- [Claude API vs Muse Ember](https://www.anchorterminal.com/compare/anthropic-api-vs-muse-ember.md)\n- [Claude API vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/anthropic-api-vs-nemotron-3-5-super-vl.md)\n- [Antseed vs Muse Ember](https://www.anchorterminal.com/compare/antseed-vs-muse-ember.md)\n- [Antseed vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/antseed-vs-nemotron-3-5-super-vl.md)\n- [Azure OpenAI in Foundry Models vs Muse Ember](https://www.anchorterminal.com/compare/azure-openai-vs-muse-ember.md)\n- [Azure OpenAI in Foundry Models vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/azure-openai-vs-nemotron-3-5-super-vl.md)\n- [BlockRun.AI vs Muse Ember](https://www.anchorterminal.com/compare/blockrun-ai-vs-muse-ember.md)\n- [BlockRun.AI vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/blockrun-ai-vs-nemotron-3-5-super-vl.md)\n- [Cerebras Inference vs Muse Ember](https://www.anchorterminal.com/compare/cerebras-inference-vs-muse-ember.md)\n- [Cerebras Inference vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/cerebras-inference-vs-nemotron-3-5-super-vl.md)\n- [Cloudflare AI Gateway vs Muse Ember](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-muse-ember.md)\n- [Cloudflare AI Gateway vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-nemotron-3-5-super-vl.md)\n- [Cloudflare Workers AI vs Muse Ember](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-muse-ember.md)\n- [Cloudflare Workers AI vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-nemotron-3-5-super-vl.md)\n- [Cohere Chat API (Command models) vs Muse Ember](https://www.anchorterminal.com/compare/cohere-chat-vs-muse-ember.md)\n- [Cohere Chat API (Command models) vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/cohere-chat-vs-nemotron-3-5-super-vl.md)\n- [DeepInfra vs Muse Ember](https://www.anchorterminal.com/compare/deepinfra-vs-muse-ember.md)\n- [DeepInfra vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/deepinfra-vs-nemotron-3-5-super-vl.md)\n- [DeepSeek API vs Muse Ember](https://www.anchorterminal.com/compare/deepseek-api-vs-muse-ember.md)\n- [DeepSeek API vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/deepseek-api-vs-nemotron-3-5-super-vl.md)\n- [Eden AI vs Muse Ember](https://www.anchorterminal.com/compare/eden-ai-vs-muse-ember.md)\n- [Eden AI vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/eden-ai-vs-nemotron-3-5-super-vl.md)\n- [Glimpse vs Muse Ember](https://www.anchorterminal.com/compare/elorian-glimpse-vs-muse-ember.md)\n- [Glimpse vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/elorian-glimpse-vs-nemotron-3-5-super-vl.md)\n- [Fireworks AI Inference vs Muse Ember](https://www.anchorterminal.com/compare/fireworks-inference-vs-muse-ember.md)\n- [Fireworks AI Inference vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/fireworks-inference-vs-nemotron-3-5-super-vl.md)\n- [Gemini Developer API vs Muse Ember](https://www.anchorterminal.com/compare/gemini-api-vs-muse-ember.md)\n- [Gemini Developer API vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/gemini-api-vs-nemotron-3-5-super-vl.md)\n- [GroqCloud vs Muse Ember](https://www.anchorterminal.com/compare/groq-vs-muse-ember.md)\n- [GroqCloud vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/groq-vs-nemotron-3-5-super-vl.md)\n- [Hugging Face Inference Providers vs Muse Ember](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-muse-ember.md)\n- [Inkling 2 Small vs Muse Ember](https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-ember.md)\n- [Inkling 2 Small vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-5-super-vl.md)\n- [Jais 3 vs Muse Ember](https://www.anchorterminal.com/compare/jais-3-vs-muse-ember.md)\n- [Jais 3 vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/jais-3-vs-nemotron-3-5-super-vl.md)\n- [Meta Model API vs Muse Ember](https://www.anchorterminal.com/compare/meta-model-api-vs-muse-ember.md)\n- [Meta Model API vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/meta-model-api-vs-nemotron-3-5-super-vl.md)\n- [MiniMax API vs Muse Ember](https://www.anchorterminal.com/compare/minimax-api-vs-muse-ember.md)\n- [MiniMax API vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/minimax-api-vs-nemotron-3-5-super-vl.md)\n- [Mistral AI API vs Muse Ember](https://www.anchorterminal.com/compare/mistral-api-vs-muse-ember.md)\n- [Mistral AI API vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/mistral-api-vs-nemotron-3-5-super-vl.md)\n- [Muse Ember vs Muse Spark Open](https://www.anchorterminal.com/compare/muse-ember-vs-muse-spark-open.md)\n- [Muse Ember vs Novita AI](https://www.anchorterminal.com/compare/muse-ember-vs-novita-ai.md)\n- [Muse Ember vs OpenAI API](https://www.anchorterminal.com/compare/muse-ember-vs-openai-api.md)\n- [Muse Ember vs OpenRouter](https://www.anchorterminal.com/compare/muse-ember-vs-openrouter.md)\n- [Muse Ember vs Prism Inference](https://www.anchorterminal.com/compare/muse-ember-vs-prism-inference.md)\n- [Muse Ember vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/muse-ember-vs-ramp-router.md)\n- [Muse Ember vs Beam 1.0](https://www.anchorterminal.com/compare/muse-ember-vs-reflection-beam.md)\n- [Muse Ember vs RouterPlus](https://www.anchorterminal.com/compare/muse-ember-vs-routerplus.md)\n- [Muse Ember vs SambaCloud](https://www.anchorterminal.com/compare/muse-ember-vs-sambanova.md)\n- [Muse Ember vs SiliconFlow](https://www.anchorterminal.com/compare/muse-ember-vs-siliconflow.md)\n- [Muse Ember vs Simplismart](https://www.anchorterminal.com/compare/muse-ember-vs-simplismart.md)\n- [Muse Ember vs StepFun API](https://www.anchorterminal.com/compare/muse-ember-vs-stepfun-api.md)\n- [Muse Ember vs SWE-2 Flash](https://www.anchorterminal.com/compare/muse-ember-vs-swe-2-flash.md)\n- [Muse Ember vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/muse-ember-vs-tencent-tokenhub.md)\n- [Muse Ember vs Together AI Inference](https://www.anchorterminal.com/compare/muse-ember-vs-together-inference.md)\n- [Muse Ember vs Vercel AI Gateway](https://www.anchorterminal.com/compare/muse-ember-vs-vercel-ai-gateway.md)\n- [Muse Ember vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/muse-ember-vs-vertex-ai.md)\n- [Muse Ember vs xAI API (Grok)](https://www.anchorterminal.com/compare/muse-ember-vs-xai-api.md)\n- [Muse Spark Open vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/muse-spark-open-vs-nemotron-3-5-super-vl.md)\n- [Nemotron 3.5 Super VL vs OpenAI API](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-openai-api.md)\n- [Nemotron 3.5 Super VL vs OpenRouter](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-openrouter.md)\n- [Nemotron 3.5 Super VL vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-ramp-router.md)\n- [Nemotron 3.5 Super VL vs RouterPlus](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-routerplus.md)\n- [Nemotron 3.5 Super VL vs StepFun API](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-stepfun-api.md)\n- [Nemotron 3.5 Super VL vs SWE-2 Flash](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-swe-2-flash.md)\n- [Nemotron 3.5 Super VL vs Vercel AI Gateway](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-vercel-ai-gateway.md)\n- [Nemotron 3.5 Super VL vs xAI API (Grok)](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-xai-api.md)\n- [Hugging Face Inference Providers vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-nemotron-3-5-super-vl.md)\n- [Nemotron 3.5 Super VL vs Novita AI](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-novita-ai.md)\n- [Nemotron 3.5 Super VL vs Prism Inference](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-prism-inference.md)\n- [Nemotron 3.5 Super VL vs Beam 1.0](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-reflection-beam.md)\n- [Nemotron 3.5 Super VL vs SambaCloud](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-sambanova.md)\n- [Nemotron 3.5 Super VL vs SiliconFlow](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-siliconflow.md)\n- [Nemotron 3.5 Super VL vs Simplismart](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-simplismart.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- [Nemotron 3.5 Super VL vs Together AI Inference](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-together-inference.md)\n- [Nemotron 3.5 Super VL vs Underdog](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-underdog.md)\n- [Nemotron 3.5 Super VL vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-vertex-ai.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-09", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Muse Ember vs Nemotron 3.5 Super VL", "url": "" } ], "description": "Nemotron 3.5 Super VL scores 59.3 (C) to Muse Ember's 51.8 (D) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Muse Ember D 51.8", "Nemotron 3.5 Super VL C 59.3", "scores" ], "h1": "Muse Ember vs Nemotron 3.5 Super VL", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/muse-ember-vs-nemotron-3-5-super-vl", "published": "2026-10-01", "section": "tools", "title": "Muse Ember vs Nemotron 3.5 Super VL for AI agents (2026)", "toc": null, "updated": "2026-11-09", "url": "https://www.anchorterminal.com/compare/muse-ember-vs-nemotron-3-5-super-vl" }, "tokens": { "markdown": 6900, "slim": 1080 }, "version": 1 }