{ "data": { "a": { "slug": "azure-openai", "name": "Azure OpenAI in Foundry Models", "vendor": "Microsoft", "vendorUrl": "https://azure.microsoft.com", "kind": "model", "category": "inference", "summary": "Microsoft Azure's hosted API for OpenAI's GPT models and other Foundry Models sold by Azure, such as DeepSeek, Llama, Mistral and Grok, called through an OpenAI-compatible v1 endpoint on each customer's Azure resource.", "url": "https://www.anchorterminal.com/tools/azure-openai", "markdownUrl": "https://www.anchorterminal.com/tools/azure-openai.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/azure-openai.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/azure-openai.json", "dns": "azure-openai.grade.anchorterminal.com", "repo": "https://github.com/Azure/azure-rest-api-specs", "license": "Proprietary service under the Microsoft Product Terms. The v1 OpenAPI spec is MIT, and the OpenAI SDKs the docs use are Apache-2.0", "transports": [ "http" ], "remoteUrl": "https://\u003cresource\u003e.openai.azure.com/openai/v1", "packages": [ { "registry": "pypi", "name": "openai" }, { "registry": "npm", "name": "openai" }, { "registry": "npm", "name": "@azure/openai" } ], "auth": "mixed", "authNotes": "`api-key` header with one of the resource's two regenerable keys, or a Microsoft Entra ID bearer token (scope https://ai.azure.com/.default) with the Cognitive Services OpenAI User role. Key authentication can be disabled per resource (`disableLocalAuth`). Each model must be deployed in the resource before it can be called, by deployment name.", "pricing": "usage", "pricingNotes": "Pay per token on an Azure subscription. Global Standard GPT-6 and GPT-6.1 prices match OpenAI's list (GPT-6.1 Sol $2/$10, GPT-6.1 Terra $1/$5 per million tokens), Data Zone costs 10% more, long-context requests cost 2x input and 1.5x output, cached input 0.1x, cache writes 1.25x, Flex half price and priority processing 2x (GPT-6 Sol). Batch is 50% off Global Standard. Provisioned throughput is billed per PTU hour. Prices from the Azure Retail Prices API, because the pricing page fills its table with JavaScript (checked 2026-11-06).", "priceSummary": "from $0.10 / 1M in", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the Foundry docs, the v1 OpenAPI spec or the pricing page. Access needs an Azure subscription with a payment method (checked 2026-11-06).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 454039, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://learn.microsoft.com/en-us/azure/foundry/openai/", "rateLimitsUrl": "https://learn.microsoft.com/en-us/azure/foundry/openai/quotas-limits", "openapi": "https://github.com/Azure/azure-rest-api-specs/blob/main/specification/ai/data-plane/OpenAI.v1/azure-v1-v1-generated.json", "capabilities": [ "inference.llm", "inference.open-weights" ], "tags": [ "official", "hosted", "model", "card-required", "openapi", "openai-compatible", "closed-source", "enterprise", "eu", "python", "typescript", "status-page", "bug-bounty" ], "lastRelease": "2026-10-26", "graded": true, "anchor": { "graded": true, "score": 80, "grade": "A", "agentReady": true, "rank": 14, "ranked": true, "rankOf": 1486, "categoryRank": 4, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 98, "maintenance": 86, "payments": 20, "reliability": 80, "schema": 87, "security": 95, "transparency": 83 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "An OpenAI-compatible v1 API with a public OpenAPI spec, Entra ID roles in place of shared keys and FedRAMP High scope, with GPT-6 and GPT-6.1 at OpenAI's list prices on Global Standard. Access needs an Azure subscription with a card and a deployment per model, and a 29 September 2026 incident caused about six hours of failures in Sweden Central.", "bestFor": "Teams on Azure that need OpenAI models with Entra ID, private networking, EU or US data zones or FedRAMP scope, and one resource that also serves DeepSeek, Llama, Mistral and Grok models.", "strengths": [ "Public OpenAPI 3.2 spec for the v1 API, 71 paths covering Responses, Chat Completions, batches, files and vector stores", "Microsoft Entra ID tokens with Azure roles, and key authentication can be switched off per resource", "GA models carry a retirement date 18 months after launch, set at release and readable through the Models API", "Data Zone deployments keep processing inside the EU or US, and Azure OpenAI is in FedRAMP High scope", "GPT-6 Astra, Sol and Luna at $10/$50, $2/$10 and $0.10/$0.50 per million tokens on Global Standard" ], "weaknesses": [ "Intermittent failures and 5xx errors in Sweden Central for about six hours on 29 September 2026", "An Azure subscription with a card, a resource and a model deployment come before the first call", "No llms.txt, and no Azure OpenAI what's new page was found; the Foundry one still covered August on 6 November", "No retention period stated for prompts kept for human abuse review, and Responses data is kept 30 days by default", "The retirement schedule lists two `gpt-realtime-mini` versions twice with different retirement dates, and no GPT-6 retirement dates yet" ], "agentNotes": [ "Point the OpenAI SDK at https://\u003cresource\u003e.openai.azure.com/openai/v1/ and pass the deployment name as `model`, not the model id", "Prefer Entra ID with the Cognitive Services OpenAI User role over the resource key, which opens the whole data plane", "On 429 wait for `retry-after-ms`, then back off with jitter. The OpenAI SDK retries twice by default", "Set `store: false` on Responses calls you don't need kept. Stored responses persist 30 days by default", "Keep remote MCP approvals on for servers you don't control. They're required by default" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "A", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 80 } ], "editorialScores": { "ergonomics": 98, "maintenance": 86, "payments": 20, "reliability": 80, "schema": 87, "security": 95, "transparency": 77 }, "provenanceScore": 88, "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": { "install": "pip install openai azure-identity # or: npm i openai @azure/identity", "http": "curl \"https://$AZURE_OPENAI_RESOURCE.openai.azure.com/openai/v1/responses\" \\\n -H \"api-key: $AZURE_OPENAI_API_KEY\" -H \"content-type: application/json\" \\\n -d '{\"model\":\"\u003cyour-deployment-name\u003e\",\"input\":\"hello\"}'" }, "letme": { "capability": "https://letme.dev/inference.llm", "tool": "https://letme.dev/azure-openai" }, "sameCompany": [ "azure-foundry-fine-tuning", "azure-ai-content-safety", "azure-speech-to-text", "azure-text-to-speech", "microsoft-agent-framework", "microsoft-execution-containers", "microsoft-entra-agent-id", "azure-key-vault", "bing-grounding", "azure-document-intelligence", "azure-devops-mcp", "microsoft-learn-mcp", "tokeneconomizer", "playwright-mcp", "azure-mcp", "azure-maps", "azure-translator", "microsoft-graph-calendar", "azure-blob-storage", "onedrive-sharepoint", "microsoft-teams", "dynamics-365-sales", "copilot-studio-mcp", "power-automate", "foundry-local", "microsoft-decision-1", "microsoft-advertising-api", "microsoft-excel-graph", "outlook-mail-graph", "microsoft-graph-people", "mage-vl-cowork" ], "area": "models", "unitPrices": [ { "item": "GPT-6.1 Sol input, Global Standard", "unit": "1m-tokens", "usd": 2, "note": "short context, Retail Prices API meter effective 2026-10-01" }, { "item": "GPT-6.1 Sol output, Global Standard", "unit": "1m-tokens", "usd": 10, "note": "short context" }, { "item": "GPT-6.1 Terra input, Global Standard", "unit": "1m-tokens", "usd": 1, "note": "short context" }, { "item": "GPT-6.1 Terra output, Global Standard", "unit": "1m-tokens", "usd": 5, "note": "short context" }, { "item": "GPT-6 Astra input, Global Standard", "unit": "1m-tokens", "usd": 10, "note": "short context" }, { "item": "GPT-6 Astra output, Global Standard", "unit": "1m-tokens", "usd": 50, "note": "short context" } ], "provenance": { "legalEntity": "Microsoft Corporation", "domain": "microsoft.com", "domainRegistered": "1991-05-02", "domainNote": "Endpoints are on openai.azure.com and cognitiveservices.azure.com. microsoft.com publishes a security.txt, but it passed its Expires date on 2026-09-23 and was still expired on 2026-11-06.", "endpointOnVendorDomain": true, "terms": "https://www.microsoft.com/licensing/terms/product/ForOnlineServices/all", "privacy": "https://privacy.microsoft.com/en-us/privacystatement", "statusPage": "https://azure.status.microsoft/en-us/status", "changelog": "https://learn.microsoft.com/en-us/azure/foundry/whats-new-foundry", "securityTxt": "expired", "checked": "2026-11-06", "score": 88 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/azure-openai.json", "live": { "slug": "azure-openai", "probe": { "target": "https://\u003cresource\u003e.openai.azure.com/openai/v1", "method": "get", "lastAt": "2026-11-07T18:20:12.145420458Z", "lastOk": false, "lastStatus": 0, "lastMs": 0, "lastNote": "DNS lookup failed", "authRequired": false, "uptime24h": 0, "uptime30d": 0, "p50ms24h": 0, "p95ms24h": 0, "samples24h": 200, "samples30d": 200, "days": [ { "date": "2026-11-06", "probes": 13, "ok": 0 }, { "date": "2026-11-07", "probes": 187, "ok": 0 } ], "outages": [ { "start": "2026-11-06T22:45:05.888142257Z", "end": "0001-01-01T00:00:00Z", "note": "DNS lookup failed" } ] }, "versions": [ { "registry": "npm", "name": "@azure/openai", "version": "2.0.0", "seenAt": "2026-11-06T23:09:28.988578937Z" }, { "registry": "npm", "name": "openai", "version": "7.53.0", "seenAt": "2026-11-06T23:09:28.954764315Z" }, { "registry": "pypi", "name": "openai", "version": "3.46.0", "released": "2026-11-05", "seenAt": "2026-11-06T23:09:28.844701934Z" } ], "githubStars": 3113, "npmWeekly": 56543040, "pypiWeekly": 91156146, "securityTxt": { "url": "https://microsoft.com/.well-known/security.txt", "state": "valid", "expires": "2027-10-27T16:00:00.000Z", "checkedAt": "2026-11-07T16:02:01.196666056Z" }, "pages": [ { "url": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-07T14:13:01.613678733Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "51438ff38076" } ], "updatedAt": "2026-11-07T18:20:12.145420458Z" } }, "answer": "Azure OpenAI in Foundry Models scores 80 (A) on agent readiness against Muse Spark Open's 53.4 (D), and leads in 6 of 7 scored categories. Muse Spark Open leads on payments \u0026 pricing.", "b": { "slug": "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": 944, "ranked": true, "rankOf": 1486, "categoryRank": 32, "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": "2026-11-07T16:02:03.890144289Z" }, "llmsTxt": { "url": "https://dev.meta.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:33:19.416673459Z" }, "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": "2026-11-07T14:12:09.389199467Z", "changedAt": "2026-11-07T14:12:09.389199467Z", "fingerprint": "e60ed3d2f0c5" } ], "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": "2026-11-06T23:49:25.225778715Z" } }, "updatedAt": "2026-11-07T16:02:03.890144289Z" } }, "edges": [ { "by": 51, "category": "security", "leads": "azure-openai", "name": "Security \u0026 auth", "reasons": { "a": "Model reading. Microsoft Entra ID tokens with Azure roles (the Cognitive Services OpenAI User role for calls), managed identities, and key authentication that can be disabled per resource, or two regenerable resource keys in the `api-key` header. No documented route puts the key in a URL query string (30). Prompts, completions, embeddings and training data aren't used to train foundation models without the customer's permission or instruction, per the data privacy page updated 4 August 2026 (20). Flagged prompts and completions may be stored in the customer's geography for human abuse review, with no retention period stated, and approved customers can turn that storage off through modified abuse monitoring. Responses API data is kept 30 days by default unless `store` is false (12 of 15). Azure Monitor resource logs and the subscription activity log, as read in the Foundry fine-tuning dossier (15). MSRC coordinated disclosure policy and Microsoft's bounty programme, both named in microsoft.com's security.txt, and Azure OpenAI is listed in FedRAMP High and DoD IL2 scope in Azure public regions. The security.txt passed its Expires date on 2026-09-23 and was still expired on 6 November, which the Bedrock and S3 dossiers mark down by 2, applied here too (18 of 20, down from 20 on 6 October for consistency).", "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": 95, "b": 44 } }, { "by": 38, "category": "reliability", "leads": "azure-openai", "name": "Reliability", "reasons": { "a": "Azure status page with post-incident reviews, listing Azure OpenAI Service, Foundry Models and Foundry Agent Service as components (20). One incident in the 90 days to 6 November 2026 names Azure OpenAI, and no review after it does, intermittent request failures, higher latency and HTTP 5xx errors in Sweden Central from 10:03 to 15:58 UTC on 29 September 2026 (tracking 7QL5-Z50), counted as one major outage as in the Foundry fine-tuning dossier. The 23 July West US review and the 30 September gateway incident don't name it (10). Quota tiers from Free to Tier 6 with TPM and RPM per model and deployment type, 1,000 RPM and 1,000,000 TPM for each GPT-6 model on Global Standard at Tier 1 (15). 429 responses carry `retry-after-ms`, every response carries `x-ratelimit-*` headers, and the quota guide gives exponential backoff with jitter and SDK retry settings (15). The models page says models sold by Azure are covered by Azure service-level agreements and links the Online Services SLA. The consolidated SLA document wouldn't download on 6 October and wasn't retried on 6 November, so the clause rests on Microsoft's docs, read the same way as the 5 October Azure Speech check (10). The v1 API is GA and the GPT-6 models carry no preview label (10).", "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": 80, "b": 42 } }, { "by": 30, "category": "payments", "leads": "muse-spark-open", "name": "Payments \u0026 pricing", "reasons": { "a": "No x402, MPP or L402 (0). Per-1M-token prices are public in the Azure Retail Prices API without a login, while the pricing page fills its table with JavaScript and showed GPT-6 prices as pending on 6 October (20). The quota tiers include a Free tier, but an Azure subscription needs a payment method (0). A person signs up for Azure in a browser and creates a resource and a deployment before the first call (0).", "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": 30, "category": "transparency", "leads": "azure-openai", "name": "Transparency \u0026 trust", "reasons": { "a": "Closed service under the Microsoft Product Terms, with the v1 spec under MIT and the OpenAI SDKs under Apache-2.0 (15). The data privacy page agrees with the product terms on no training and states where data is processed and stored by deployment type, but gives no retention period for the human-review store and sits beside a 30-day default for Responses data (24 of 30). A published lifecycle policy and a retirement schedule with dates and replacements, but on 6 November the schedule listed `gpt-realtime-mini` 2025-10-06 and 2025-12-15 twice each with different retirement dates, and no GPT-6 model yet (18 of 20, down from 20). Data locations stated for Standard, Data Zone and Global deployments, and a public sub-processor list per the 5 October Azure Speech check, not re-read (20).", "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": 83, "b": 53 } }, { "by": 29, "category": "ergonomics", "leads": "azure-openai", "name": "Agent ergonomics", "reasons": { "a": "Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Tool use with parallel calls and a forced call by naming the function in `tool_choice`, 18 of 20 because `gpt-6.1-sol` calls tools only through the Responses API (18). Strict structured outputs (15). Prompt caching from 1,024 tokens, cached input at 0.1x on GPT-6 ($1 per million on Astra) and cache writes at 1.25x from GPT-5.6 on, with explicit breakpoints (15). 1,050,000-token context on GPT-6 and GPT-6.1, input capped at 922,000 (15). Batch at 50% off Global Standard with a 24-hour target (10). The docs use OpenAI's own SDKs for Python, JavaScript, C#, Go and Java against the v1 endpoint (10). 429 and quota errors documented with retry headers (15). Calls name a deployment rather than a model, so each model must be deployed in the resource first, which the model checklist doesn't score.", "b": "Model reading of the checklist (tool use, structured output, caching, context, throughput, defaults and SDKs, errors). OpenAI-format tools and parallel calls come back as `tool_calls`, and the template supports namespaced tools and deferred loading through a `tool_search` tool. A forced `tool_choice` is not documented (17 of 20). JSON mode and JSON Schema come from each runtime's guided decoding, which Meta's docs show for TensorRT-LLM only (8 of 15). Prefix caching is the runtime's. Meta's SGLang command turns on hierarchical caching, and Dynamo routes each request to the worker holding its cached context (8 of 10). 1,048,576-token context, with sliding-window attention on 46 of 62 layers holding KV memory down (15 of 15). Draft models for speculative decoding in SGLang and vLLM, and no batch mode of its own (7 of 10). Any OpenAI SDK works against a local server, but reasoning can't be turned off, defaults to the most expensive level, and needs streaming, a `max_tokens` budget for reasoning and the right stop tokens (6 of 15). The template raises named errors for an unsupported reasoning effort, tool arguments passed as a string and a tool message with no name. Server errors are the runtime's (8 of 15). 17 + 8 + 8 + 15 + 7 + 6 + 8 = 69." }, "scores": { "a": 98, "b": 69 } }, { "by": 26, "category": "schema", "leads": "azure-openai", "name": "Schema \u0026 documentation", "reasons": { "a": "OpenAPI 3.2 spec for the v1 data plane in Azure/azure-rest-api-specs (`azure-v1-v1-generated.json`, 71 paths and 852 schemas), linked from the v1 API page (25). No llms.txt at learn.microsoft.com (404). Learn pages offer Copy Markdown and the Markdown sources are public in MicrosoftDocs/azure-ai-docs, last merged 5 October (5 of 10). The models page lists each model's capabilities, context and API support, but the model choice guide, dated 19 May 2026, doesn't cover GPT-6 (15 of 20). Structured outputs with `strict: true` on schemas and function tools, though not together with parallel function calls (15). Examples in Python, C#, JavaScript, Go, Java and REST, and an error table on the quotas page with a fix for 429 and other codes (15). The v1 path replaces monthly `api-version` values, with preview capabilities opted into by header, a dated API version changelog and dated model versions. On 6 November the Foundry what's new still covered August, though updated on 5 November, and no Azure OpenAI what's new was found at learn.microsoft.com/en-us/azure/foundry/openai/whats-new, which answered 404 (12 of 15).", "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": 87, "b": 61 } } ], "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Microsoft", "b": "Meta", "name": "Vendor" }, { "a": "https://\u003cresource\u003e.openai.azure.com/openai/v1", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "OAuth or key", "b": "None", "name": "Auth" }, { "a": "Pay per use", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under the Microsoft Product Terms. The v1 OpenAPI spec is MIT, and the OpenAI SDKs the docs use are Apache-2.0", "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": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-26", "b": "2026-10-15", "name": "Last release" }, { "a": "no date given", "b": "2026-10-15", "name": "Terms last updated" }, { "a": "2026-09-01", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "yes", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "yes", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "yes", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "454k npm/wk", "b": "none", "name": "Popularity" } ], "faq": [ { "answer": "Azure OpenAI in Foundry Models scores 80 (A) on agent readiness against Muse Spark Open's 53.4 (D), and leads in 6 of 7 scored categories. Muse Spark Open leads on payments \u0026 pricing.", "question": "Which is better for AI agents, Azure OpenAI in Foundry Models or Muse Spark Open?" }, { "answer": "Azure OpenAI in Foundry Models takes an API key or an OAuth sign-in. Muse Spark Open needs no key.", "question": "Do Azure OpenAI in Foundry Models and Muse Spark Open need an API key?" }, { "answer": "Azure OpenAI in Foundry Models has a hosted endpoint at https://\u003cresource\u003e.openai.azure.com/openai/v1. No hosted endpoint is listed for Muse Spark Open.", "question": "Can an agent call Azure OpenAI in Foundry Models and Muse Spark Open without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 80 against 42", "Schema \u0026 documentation, 87 against 61", "Agent ergonomics, 98 against 69", "Security \u0026 auth, 95 against 44", "Maintenance \u0026 community, 86 against 60", "Transparency \u0026 trust, 83 against 53" ], "also": [ "Agent-ready, a grade of BB or better", "A hosted endpoint, with nothing to install" ], "goodFor": "Teams on Azure that need OpenAI models with Entra ID, private networking, EU or US data zones or FedRAMP scope, and one resource that also serves DeepSeek, Llama, Mistral and Grok models.", "slug": "azure-openai", "watchFor": "Intermittent failures and 5xx errors in Sweden Central for about six hours on 29 September 2026" }, { "aheadOn": [ "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": { "azure-openai": 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/amazon-bedrock-vs-azure-openai.json", "title": "Amazon Bedrock vs Azure OpenAI in Foundry Models", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-azure-openai" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-muse-spark-open.json", "title": "Amazon Bedrock vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-muse-spark-open" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-azure-openai.json", "title": "Claude API vs Azure OpenAI in Foundry Models", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-azure-openai" }, { "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-azure-openai.json", "title": "Antseed vs Azure OpenAI in Foundry Models", "url": "https://www.anchorterminal.com/compare/antseed-vs-azure-openai" }, { "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/azure-openai-vs-blockrun-ai.json", "title": "Azure OpenAI in Foundry Models vs BlockRun.AI", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-blockrun-ai" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-cerebras-inference.json", "title": "Azure OpenAI in Foundry Models vs Cerebras Inference", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-cerebras-inference" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-cloudflare-ai-gateway.json", "title": "Azure OpenAI in Foundry Models vs Cloudflare AI Gateway", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-cloudflare-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-cloudflare-workers-ai.json", "title": "Azure OpenAI in Foundry Models vs Cloudflare Workers AI", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-cloudflare-workers-ai" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-cohere-chat.json", "title": "Azure OpenAI in Foundry Models vs Cohere Chat API (Command models)", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-cohere-chat" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-deepinfra.json", "title": "Azure OpenAI in Foundry Models vs DeepInfra", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-deepinfra" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-deepseek-api.json", "title": "Azure OpenAI in Foundry Models vs DeepSeek API", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-deepseek-api" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-eden-ai.json", "title": "Azure OpenAI in Foundry Models vs Eden AI", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-eden-ai" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-elorian-glimpse.json", "title": "Azure OpenAI in Foundry Models vs Glimpse", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-elorian-glimpse" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-fireworks-inference.json", "title": "Azure OpenAI in Foundry Models vs Fireworks AI Inference", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-fireworks-inference" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-gemini-api.json", "title": "Azure OpenAI in Foundry Models vs Gemini Developer API", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-gemini-api" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-groq.json", "title": "Azure OpenAI in Foundry Models vs GroqCloud", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-groq" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-hugging-face-inference-providers.json", "title": "Azure OpenAI in Foundry Models vs Hugging Face Inference Providers", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-hugging-face-inference-providers" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-inkling-2-small.json", "title": "Azure OpenAI in Foundry Models vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-jais-3.json", "title": "Azure OpenAI in Foundry Models vs Jais 3", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-meta-model-api.json", "title": "Azure OpenAI in Foundry Models vs Meta Model API", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-minimax-api.json", "title": "Azure OpenAI in Foundry Models vs MiniMax API", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-minimax-api" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-mistral-api.json", "title": "Azure OpenAI in Foundry Models vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-mistral-api" }, { "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/azure-openai-vs-novita-ai.json", "title": "Azure OpenAI in Foundry Models vs Novita AI", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-novita-ai" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-openai-api.json", "title": "Azure OpenAI in Foundry Models vs OpenAI API", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-openai-api" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-openrouter.json", "title": "Azure OpenAI in Foundry Models vs OpenRouter", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-openrouter" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-prism-inference.json", "title": "Azure OpenAI in Foundry Models vs Prism Inference", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-ramp-router.json", "title": "Azure OpenAI in Foundry Models vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-reflection-beam.json", "title": "Azure OpenAI in Foundry Models vs Beam 1.0", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-reflection-beam" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-routerplus.json", "title": "Azure OpenAI in Foundry Models vs RouterPlus", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-routerplus" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-sambanova.json", "title": "Azure OpenAI in Foundry Models vs SambaCloud", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-sambanova" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-siliconflow.json", "title": "Azure OpenAI in Foundry Models vs SiliconFlow", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-siliconflow" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-simplismart.json", "title": "Azure OpenAI in Foundry Models vs Simplismart", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-simplismart" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-stepfun-api.json", "title": "Azure OpenAI in Foundry Models vs StepFun API", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-stepfun-api" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-swe-2-flash.json", "title": "Azure OpenAI in Foundry Models vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-tencent-tokenhub.json", "title": "Azure OpenAI in Foundry Models vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-together-inference.json", "title": "Azure OpenAI in Foundry Models vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-together-inference" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-vercel-ai-gateway.json", "title": "Azure OpenAI in Foundry Models vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-vertex-ai.json", "title": "Azure OpenAI in Foundry Models vs Vertex AI (Gemini Enterprise Agent Platform)", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-vertex-ai" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-xai-api.json", "title": "Azure OpenAI in Foundry Models vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-xai-api" }, { "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-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-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-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-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-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-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/eden-ai-vs-muse-spark-open.json", "title": "Eden AI vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/eden-ai-vs-muse-spark-open" }, { "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-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-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-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/hugging-face-inference-providers-vs-muse-spark-open.json", "title": "Hugging Face Inference Providers vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-muse-spark-open" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-spark-open.json", "title": "Inkling 2 Small vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-spark-open" }, { "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" }, { "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-vertex-ai.json", "title": "Muse Spark Open vs Vertex AI (Gemini Enterprise Agent Platform)", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-vertex-ai" }, { "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-xai-api.json", "title": "Muse Spark Open vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-xai-api" } ], "panel": null, "scores": [ { "azure-openai": 80, "by": 38, "edge": "azure-openai", "key": "reliability", "muse-spark-open": 42, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "azure-openai": 87, "by": 26, "edge": "azure-openai", "key": "schema", "muse-spark-open": 61, "name": "Schema \u0026 documentation", "weight": 13 }, { "azure-openai": 98, "by": 29, "edge": "azure-openai", "key": "ergonomics", "muse-spark-open": 69, "name": "Agent ergonomics", "weight": 13 }, { "azure-openai": 95, "by": 51, "edge": "azure-openai", "key": "security", "muse-spark-open": 44, "name": "Security \u0026 auth", "weight": 14 }, { "azure-openai": 20, "by": 30, "edge": "muse-spark-open", "key": "payments", "muse-spark-open": 50, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "azure-openai": 86, "by": 26, "edge": "azure-openai", "key": "maintenance", "muse-spark-open": 60, "name": "Maintenance \u0026 community", "weight": 7 }, { "azure-openai": 83, "by": 30, "edge": "azure-openai", "key": "transparency", "muse-spark-open": 53, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Azure OpenAI in Foundry Models scores 80 (A) on agent readiness against Muse Spark Open's 53.4 (D), and leads in 6 of 7 scored categories. Muse Spark Open leads on payments \u0026 pricing. Both do llm inference.", "tasks": [ { "a": "$110", "b": "$2.03", "cheaper": "muse-spark-open", "task": "Research a product and write a sourced report", "what": "gpt-6-astra on Azure OpenAI in Foundry Models, meta/muse-spark-open on Muse Spark Open" }, { "a": "$25.07", "b": "$0.63", "cheaper": "muse-spark-open", "task": "Build a small four-page website", "what": "gpt-6-astra on Azure OpenAI in Foundry Models, meta/muse-spark-open on Muse Spark Open" }, { "a": "$5.41", "b": "$0.15", "cheaper": "muse-spark-open", "task": "Find and fix a bug in a large codebase", "what": "gpt-6-astra on Azure OpenAI in Foundry Models, meta/muse-spark-open on Muse Spark Open" } ], "tutorials": [], "verdicts": { "azure-openai": "An OpenAI-compatible v1 API with a public OpenAPI spec, Entra ID roles in place of shared keys and FedRAMP High scope, with GPT-6 and GPT-6.1 at OpenAI's list prices on Global Standard. Access needs an Azure subscription with a card and a deployment per model, and a 29 September 2026 incident caused about six hours of failures in Sweden Central.", "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/azure-openai-vs-muse-spark-open", "json": "https://www.anchorterminal.com/compare/azure-openai-vs-muse-spark-open.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/azure-openai-vs-muse-spark-open.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/azure-openai-vs-muse-spark-open.min.md" }, "markdown": "Azure OpenAI in Foundry Models scores 80 (A) on agent readiness against Muse Spark Open's 53.4 (D), and leads in 6 of 7 scored categories. Muse Spark Open leads on payments \u0026 pricing. Both do llm inference.\n\n- Azure OpenAI in Foundry Models: grade A, 80/100, rank #14 of 1486. Markdown https://www.anchorterminal.com/tools/azure-openai.md · JSON https://www.anchorterminal.com/api/v1/tools/azure-openai.json\n- Muse Spark Open: grade D, 53.4/100, rank #944 of 1486. 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 830 models comparisons: https://www.anchorterminal.com/compare/inference/index.md\n\n## Which one, for what\n\n### Azure OpenAI in Foundry Models (A)\n\nGood for: Teams on Azure that need OpenAI models with Entra ID, private networking, EU or US data zones or FedRAMP scope, and one resource that also serves DeepSeek, Llama, Mistral and Grok models.\n\nAhead on:\n- Reliability, 80 against 42\n- Schema \u0026 documentation, 87 against 61\n- Agent ergonomics, 98 against 69\n- Security \u0026 auth, 95 against 44\n- Maintenance \u0026 community, 86 against 60\n- Transparency \u0026 trust, 83 against 53\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- A hosted endpoint, with nothing to install\n\nWatch for: Intermittent failures and 5xx errors in Sweden Central for about six hours on 29 September 2026\n\n### Muse Spark Open (D)\n\nGood for: A team with a four-GPU Blackwell node, or two to four Mac Studios, that wants a 1M-token multimodal coding and agent model on its own hardware with no prompts leaving it.\n\nAhead on:\n- Payments \u0026 pricing, 50 against 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### Security \u0026 auth: Azure OpenAI in Foundry Models +51\n\n- Azure OpenAI in Foundry Models (95): Model reading. Microsoft Entra ID tokens with Azure roles (the Cognitive Services OpenAI User role for calls), managed identities, and key authentication that can be disabled per resource, or two regenerable resource keys in the `api-key` header. No documented route puts the key in a URL query string (30). Prompts, completions, embeddings and training data aren't used to train foundation models without the customer's permission or instruction, per the data privacy page updated 4 August 2026 (20). Flagged prompts and completions may be stored in the customer's geography for human abuse review, with no retention period stated, and approved customers can turn that storage off through modified abuse monitoring. Responses API data is kept 30 days by default unless `store` is false (12 of 15). Azure Monitor resource logs and the subscription activity log, as read in the Foundry fine-tuning dossier (15). MSRC coordinated disclosure policy and Microsoft's bounty programme, both named in microsoft.com's security.txt, and Azure OpenAI is listed in FedRAMP High and DoD IL2 scope in Azure public regions. The security.txt passed its Expires date on 2026-09-23 and was still expired on 6 November, which the Bedrock and S3 dossiers mark down by 2, applied here too (18 of 20, down from 20 on 6 October for consistency).\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: Azure OpenAI in Foundry Models +38\n\n- Azure OpenAI in Foundry Models (80): Azure status page with post-incident reviews, listing Azure OpenAI Service, Foundry Models and Foundry Agent Service as components (20). One incident in the 90 days to 6 November 2026 names Azure OpenAI, and no review after it does, intermittent request failures, higher latency and HTTP 5xx errors in Sweden Central from 10:03 to 15:58 UTC on 29 September 2026 (tracking 7QL5-Z50), counted as one major outage as in the Foundry fine-tuning dossier. The 23 July West US review and the 30 September gateway incident don't name it (10). Quota tiers from Free to Tier 6 with TPM and RPM per model and deployment type, 1,000 RPM and 1,000,000 TPM for each GPT-6 model on Global Standard at Tier 1 (15). 429 responses carry `retry-after-ms`, every response carries `x-ratelimit-*` headers, and the quota guide gives exponential backoff with jitter and SDK retry settings (15). The models page says models sold by Azure are covered by Azure service-level agreements and links the Online Services SLA. The consolidated SLA document wouldn't download on 6 October and wasn't retried on 6 November, so the clause rests on Microsoft's docs, read the same way as the 5 October Azure Speech check (10). The v1 API is GA and the GPT-6 models carry no preview label (10).\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### Payments \u0026 pricing: Muse Spark Open +30\n\n- Azure OpenAI in Foundry Models (20): No x402, MPP or L402 (0). Per-1M-token prices are public in the Azure Retail Prices API without a login, while the pricing page fills its table with JavaScript and showed GPT-6 prices as pending on 6 October (20). The quota tiers include a Free tier, but an Azure subscription needs a payment method (0). A person signs up for Azure in a browser and creates a resource and a deployment before the first call (0).\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### Transparency \u0026 trust: Azure OpenAI in Foundry Models +30\n\n- Azure OpenAI in Foundry Models (83): Closed service under the Microsoft Product Terms, with the v1 spec under MIT and the OpenAI SDKs under Apache-2.0 (15). The data privacy page agrees with the product terms on no training and states where data is processed and stored by deployment type, but gives no retention period for the human-review store and sits beside a 30-day default for Responses data (24 of 30). A published lifecycle policy and a retirement schedule with dates and replacements, but on 6 November the schedule listed `gpt-realtime-mini` 2025-10-06 and 2025-12-15 twice each with different retirement dates, and no GPT-6 model yet (18 of 20, down from 20). Data locations stated for Standard, Data Zone and Global deployments, and a public sub-processor list per the 5 October Azure Speech check, not re-read (20).\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### Agent ergonomics: Azure OpenAI in Foundry Models +29\n\n- Azure OpenAI in Foundry Models (98): Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Tool use with parallel calls and a forced call by naming the function in `tool_choice`, 18 of 20 because `gpt-6.1-sol` calls tools only through the Responses API (18). Strict structured outputs (15). Prompt caching from 1,024 tokens, cached input at 0.1x on GPT-6 ($1 per million on Astra) and cache writes at 1.25x from GPT-5.6 on, with explicit breakpoints (15). 1,050,000-token context on GPT-6 and GPT-6.1, input capped at 922,000 (15). Batch at 50% off Global Standard with a 24-hour target (10). The docs use OpenAI's own SDKs for Python, JavaScript, C#, Go and Java against the v1 endpoint (10). 429 and quota errors documented with retry headers (15). Calls name a deployment rather than a model, so each model must be deployed in the resource first, which the model checklist doesn't score.\n- Muse Spark Open (69): Model reading of the checklist (tool use, structured output, caching, context, throughput, defaults and SDKs, errors). OpenAI-format tools and parallel calls come back as `tool_calls`, and the template supports namespaced tools and deferred loading through a `tool_search` tool. A forced `tool_choice` is not documented (17 of 20). JSON mode and JSON Schema come from each runtime's guided decoding, which Meta's docs show for TensorRT-LLM only (8 of 15). Prefix caching is the runtime's. Meta's SGLang command turns on hierarchical caching, and Dynamo routes each request to the worker holding its cached context (8 of 10). 1,048,576-token context, with sliding-window attention on 46 of 62 layers holding KV memory down (15 of 15). Draft models for speculative decoding in SGLang and vLLM, and no batch mode of its own (7 of 10). Any OpenAI SDK works against a local server, but reasoning can't be turned off, defaults to the most expensive level, and needs streaming, a `max_tokens` budget for reasoning and the right stop tokens (6 of 15). The template raises named errors for an unsupported reasoning effort, tool arguments passed as a string and a tool message with no name. Server errors are the runtime's (8 of 15). 17 + 8 + 8 + 15 + 7 + 6 + 8 = 69.\n\n### Schema \u0026 documentation: Azure OpenAI in Foundry Models +26\n\n- Azure OpenAI in Foundry Models (87): OpenAPI 3.2 spec for the v1 data plane in Azure/azure-rest-api-specs (`azure-v1-v1-generated.json`, 71 paths and 852 schemas), linked from the v1 API page (25). No llms.txt at learn.microsoft.com (404). Learn pages offer Copy Markdown and the Markdown sources are public in MicrosoftDocs/azure-ai-docs, last merged 5 October (5 of 10). The models page lists each model's capabilities, context and API support, but the model choice guide, dated 19 May 2026, doesn't cover GPT-6 (15 of 20). Structured outputs with `strict: true` on schemas and function tools, though not together with parallel function calls (15). Examples in Python, C#, JavaScript, Go, Java and REST, and an error table on the quotas page with a fix for 429 and other codes (15). The v1 path replaces monthly `api-version` values, with preview capabilities opted into by header, a dated API version changelog and dated model versions. On 6 November the Foundry what's new still covered August, though updated on 5 November, and no Azure OpenAI what's new was found at learn.microsoft.com/en-us/azure/foundry/openai/whats-new, which answered 404 (12 of 15).\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 | Azure OpenAI in Foundry Models | Muse Spark Open | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 80 | 42 | Azure OpenAI in Foundry Models +38 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 87 | 61 | Azure OpenAI in Foundry Models +26 |\n| Agent ergonomics | 13% (16.2 this run) | 98 | 69 | Azure OpenAI in Foundry Models +29 |\n| Security \u0026 auth | 14% (17.5 this run) | 95 | 44 | Azure OpenAI in Foundry Models +51 |\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) | 86 | 60 | Azure OpenAI in Foundry Models +26 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 83 | 53 | Azure OpenAI in Foundry Models +30 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **80 · A** | **53.4 · D** | |\n\n## Facts side by side\n\n| Fact | Azure OpenAI in Foundry Models | Muse Spark Open |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Microsoft | Meta |\n| Hosted endpoint | `https://\u003cresource\u003e.openai.azure.com/openai/v1` | no (local only) |\n| Transports | HTTP | HTTP |\n| Auth | OAuth or key | None |\n| Pricing | Pay per use | Free |\n| x402 | no | no |\n| Licence | Proprietary service under the Microsoft Product Terms. The v1 OpenAPI spec is MIT, and the OpenAI SDKs the docs use are Apache-2.0 | 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 | no | yes |\n| Last release | 2026-10-26 | 2026-10-15 |\n| Terms last updated | no date given | 2026-10-15 |\n| Privacy policy last updated | 2026-09-01 | no document linked |\n| Customer content may train models | yes | not found in the text |\n| Terms restrict automated access | yes | not found in the text |\n| Terms restrict benchmarking | yes | not found in the text |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | not found in the text | not found in the text |\n| Popularity | 454k npm/wk | none |\n\n## What the same task costs\n\n| Task | Azure OpenAI in Foundry Models | Muse Spark Open |\n| --- | --- | --- |\n| Research a product and write a sourced report | $110 | $2.03 |\n| Build a small four-page website | $25.07 | $0.63 |\n| Find and fix a bug in a large codebase | $5.41 | $0.15 |\n\n## How the scores have moved\n\n### Azure OpenAI in Foundry Models\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**Azure OpenAI in Foundry Models.** An OpenAI-compatible v1 API with a public OpenAPI spec, Entra ID roles in place of shared keys and FedRAMP High scope, with GPT-6 and GPT-6.1 at OpenAI's list prices on Global Standard. Access needs an Azure subscription with a card and a deployment per model, and a 29 September 2026 incident caused about six hours of failures in Sweden Central.\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### Azure OpenAI in Foundry Models\n\n1. Point the OpenAI SDK at https://\u003cresource\u003e.openai.azure.com/openai/v1/ and pass the deployment name as `model`, not the model id\n2. Prefer Entra ID with the Cognitive Services OpenAI User role over the resource key, which opens the whole data plane\n3. On 429 wait for `retry-after-ms`, then back off with jitter. The OpenAI SDK retries twice by default\n4. Set `store: false` on Responses calls you don't need kept. Stored responses persist 30 days by default\n5. Keep remote MCP approvals on for servers you don't control. They're required by default\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, Azure OpenAI in Foundry Models or Muse Spark Open?\n\nAzure OpenAI in Foundry Models scores 80 (A) on agent readiness against Muse Spark Open's 53.4 (D), and leads in 6 of 7 scored categories. Muse Spark Open leads on payments \u0026 pricing.\n\n### Do Azure OpenAI in Foundry Models and Muse Spark Open need an API key?\n\nAzure OpenAI in Foundry Models takes an API key or an OAuth sign-in. Muse Spark Open needs no key.\n\n### Can an agent call Azure OpenAI in Foundry Models and Muse Spark Open without installing anything?\n\nAzure OpenAI in Foundry Models has a hosted endpoint at https://\u003cresource\u003e.openai.azure.com/openai/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/azure-openai-vs-muse-spark-open.json, and with the fewest tokens: https://www.anchorterminal.com/compare/azure-openai-vs-muse-spark-open.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"azure-openai\", \"b\": \"muse-spark-open\"}`. From a terminal: `anchor compare azure-openai muse-spark-open`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/azure-openai.json and https://www.anchorterminal.com/api/v1/tools/muse-spark-open.json\n\n## Other comparisons with Azure OpenAI in Foundry Models or Muse Spark Open\n\n- [Amazon Bedrock vs Azure OpenAI in Foundry Models](https://www.anchorterminal.com/compare/amazon-bedrock-vs-azure-openai.md)\n- [Amazon Bedrock vs Muse Spark Open](https://www.anchorterminal.com/compare/amazon-bedrock-vs-muse-spark-open.md)\n- [Claude API vs Azure OpenAI in Foundry Models](https://www.anchorterminal.com/compare/anthropic-api-vs-azure-openai.md)\n- [Claude API vs Muse Spark Open](https://www.anchorterminal.com/compare/anthropic-api-vs-muse-spark-open.md)\n- [Antseed vs Azure OpenAI in Foundry Models](https://www.anchorterminal.com/compare/antseed-vs-azure-openai.md)\n- [Antseed vs Muse Spark Open](https://www.anchorterminal.com/compare/antseed-vs-muse-spark-open.md)\n- [Azure OpenAI in Foundry Models vs BlockRun.AI](https://www.anchorterminal.com/compare/azure-openai-vs-blockrun-ai.md)\n- [Azure OpenAI in Foundry Models vs Cerebras Inference](https://www.anchorterminal.com/compare/azure-openai-vs-cerebras-inference.md)\n- [Azure OpenAI in Foundry Models vs Cloudflare AI Gateway](https://www.anchorterminal.com/compare/azure-openai-vs-cloudflare-ai-gateway.md)\n- [Azure OpenAI in Foundry Models vs Cloudflare Workers AI](https://www.anchorterminal.com/compare/azure-openai-vs-cloudflare-workers-ai.md)\n- [Azure OpenAI in Foundry Models vs Cohere Chat API (Command models)](https://www.anchorterminal.com/compare/azure-openai-vs-cohere-chat.md)\n- [Azure OpenAI in Foundry Models vs DeepInfra](https://www.anchorterminal.com/compare/azure-openai-vs-deepinfra.md)\n- [Azure OpenAI in Foundry Models vs DeepSeek API](https://www.anchorterminal.com/compare/azure-openai-vs-deepseek-api.md)\n- [Azure OpenAI in Foundry Models vs Eden AI](https://www.anchorterminal.com/compare/azure-openai-vs-eden-ai.md)\n- [Azure OpenAI in Foundry Models vs Glimpse](https://www.anchorterminal.com/compare/azure-openai-vs-elorian-glimpse.md)\n- [Azure OpenAI in Foundry Models vs Fireworks AI Inference](https://www.anchorterminal.com/compare/azure-openai-vs-fireworks-inference.md)\n- [Azure OpenAI in Foundry Models vs Gemini Developer API](https://www.anchorterminal.com/compare/azure-openai-vs-gemini-api.md)\n- [Azure OpenAI in Foundry Models vs GroqCloud](https://www.anchorterminal.com/compare/azure-openai-vs-groq.md)\n- [Azure OpenAI in Foundry Models vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/azure-openai-vs-hugging-face-inference-providers.md)\n- [Azure OpenAI in Foundry Models vs Inkling 2 Small](https://www.anchorterminal.com/compare/azure-openai-vs-inkling-2-small.md)\n- [Azure OpenAI in Foundry Models vs Jais 3](https://www.anchorterminal.com/compare/azure-openai-vs-jais-3.md)\n- [Azure OpenAI in Foundry Models vs Meta Model API](https://www.anchorterminal.com/compare/azure-openai-vs-meta-model-api.md)\n- [Azure OpenAI in Foundry Models vs MiniMax API](https://www.anchorterminal.com/compare/azure-openai-vs-minimax-api.md)\n- [Azure OpenAI in Foundry Models vs Mistral AI API](https://www.anchorterminal.com/compare/azure-openai-vs-mistral-api.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- [Azure OpenAI in Foundry Models vs Novita AI](https://www.anchorterminal.com/compare/azure-openai-vs-novita-ai.md)\n- [Azure OpenAI in Foundry Models vs OpenAI API](https://www.anchorterminal.com/compare/azure-openai-vs-openai-api.md)\n- [Azure OpenAI in Foundry Models vs OpenRouter](https://www.anchorterminal.com/compare/azure-openai-vs-openrouter.md)\n- [Azure OpenAI in Foundry Models vs Prism Inference](https://www.anchorterminal.com/compare/azure-openai-vs-prism-inference.md)\n- [Azure OpenAI in Foundry Models vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/azure-openai-vs-ramp-router.md)\n- [Azure OpenAI in Foundry Models vs Beam 1.0](https://www.anchorterminal.com/compare/azure-openai-vs-reflection-beam.md)\n- [Azure OpenAI in Foundry Models vs RouterPlus](https://www.anchorterminal.com/compare/azure-openai-vs-routerplus.md)\n- [Azure OpenAI in Foundry Models vs SambaCloud](https://www.anchorterminal.com/compare/azure-openai-vs-sambanova.md)\n- [Azure OpenAI in Foundry Models vs SiliconFlow](https://www.anchorterminal.com/compare/azure-openai-vs-siliconflow.md)\n- [Azure OpenAI in Foundry Models vs Simplismart](https://www.anchorterminal.com/compare/azure-openai-vs-simplismart.md)\n- [Azure OpenAI in Foundry Models vs StepFun API](https://www.anchorterminal.com/compare/azure-openai-vs-stepfun-api.md)\n- [Azure OpenAI in Foundry Models vs SWE-2 Flash](https://www.anchorterminal.com/compare/azure-openai-vs-swe-2-flash.md)\n- [Azure OpenAI in Foundry Models vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/azure-openai-vs-tencent-tokenhub.md)\n- [Azure OpenAI in Foundry Models vs Together AI Inference](https://www.anchorterminal.com/compare/azure-openai-vs-together-inference.md)\n- [Azure OpenAI in Foundry Models vs Vercel AI Gateway](https://www.anchorterminal.com/compare/azure-openai-vs-vercel-ai-gateway.md)\n- [Azure OpenAI in Foundry Models vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/azure-openai-vs-vertex-ai.md)\n- [Azure OpenAI in Foundry Models vs xAI API (Grok)](https://www.anchorterminal.com/compare/azure-openai-vs-xai-api.md)\n- [BlockRun.AI vs Muse Spark Open](https://www.anchorterminal.com/compare/blockrun-ai-vs-muse-spark-open.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 Muse Spark Open](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-muse-spark-open.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 Muse Spark Open](https://www.anchorterminal.com/compare/cohere-chat-vs-muse-spark-open.md)\n- [DeepInfra vs Muse Spark Open](https://www.anchorterminal.com/compare/deepinfra-vs-muse-spark-open.md)\n- [DeepSeek API vs Muse Spark Open](https://www.anchorterminal.com/compare/deepseek-api-vs-muse-spark-open.md)\n- [Eden AI vs Muse Spark Open](https://www.anchorterminal.com/compare/eden-ai-vs-muse-spark-open.md)\n- [Glimpse vs Muse Spark Open](https://www.anchorterminal.com/compare/elorian-glimpse-vs-muse-spark-open.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 Muse Spark Open](https://www.anchorterminal.com/compare/gemini-api-vs-muse-spark-open.md)\n- [GroqCloud vs Muse Spark Open](https://www.anchorterminal.com/compare/groq-vs-muse-spark-open.md)\n- [Hugging Face Inference Providers vs Muse Spark Open](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-muse-spark-open.md)\n- [Inkling 2 Small vs Muse Spark Open](https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-spark-open.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- [Muse Spark Open vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/muse-spark-open-vs-vertex-ai.md)\n- [Muse Spark Open vs xAI API (Grok)](https://www.anchorterminal.com/compare/muse-spark-open-vs-xai-api.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": "2026-11-07", "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": "Azure OpenAI in Foundry Models vs Muse Spark Open", "url": "" } ], "description": "Azure OpenAI in Foundry Models scores 80 (A) to Muse Spark Open's 53.4 (D) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Azure OpenAI in Foundry Models A 80", "Muse Spark Open D 53.4", "scores" ], "h1": "Azure OpenAI in Foundry Models vs Muse Spark Open", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/azure-openai-vs-muse-spark-open", "published": "2026-10-01", "section": "tools", "title": "Azure OpenAI in Foundry Models vs Muse Spark Open for AI agents (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-muse-spark-open" }, "tokens": { "markdown": 8050, "slim": 4280 }, "version": 1 }