{
  "data": {
    "a": {
      "slug": "gpt-6-2-astra",
      "name": "GPT-6.2 Astra",
      "vendor": "OpenAI",
      "vendorUrl": "https://openai.com",
      "company": "openai.com",
      "kind": "model",
      "category": "inference",
      "summary": "GPT-6.2 Astra is OpenAI's most capable model in its API, for demanding reasoning, coding and computer use, with a 1.05M-token context, 128K output, text and images in, at $8 input and $40 output per million tokens.",
      "url": "https://www.anchorterminal.com/tools/gpt-6-2-astra",
      "markdownUrl": "https://www.anchorterminal.com/tools/gpt-6-2-astra.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/gpt-6-2-astra.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/gpt-6-2-astra.json",
      "dns": "gpt-6-2-astra.grade.anchorterminal.com",
      "license": "Closed model, used through the OpenAI API under OpenAI's Services Agreement",
      "transports": [],
      "remoteUrl": "https://api.openai.com/v1",
      "packages": [],
      "auth": "api-key",
      "authNotes": "`Authorization: Bearer` with an OpenAI project key, per the OpenAI API listing. Project keys can be restricted per endpoint, and some models and tools need business or ID verification first.",
      "pricing": "usage",
      "pricingNotes": "$8 per million input tokens and $40 output (20% below GPT-6 Astra's $10 and $50), cached input $0.40, 30-minute cache writes $10 and 12-hour writes $20. Over 272K input tokens, input and cache rates double and output costs 1.5 times. Batch and Flex half price, Fast mode twice Standard, Ultrafast 3 times Standard until 28 February 2027 and 6 times from 1 March 2027. Rate limits start at the Build tier, reached at $5 of credit, per the OpenAI API listing (checked 2026-11-18).",
      "priceSummary": "Pay per use",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 on OpenAI's pricing page, which bills tokens to prepaid credit on an account (checked 2026-11-18).",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-18"
      },
      "docsUrl": "https://developers.openai.com/api/docs/models/gpt-6.2-astra",
      "llmsTxt": "https://developers.openai.com/llms.txt",
      "openapi": "https://github.com/openai/openai-openapi",
      "capabilities": [
        "inference.llm"
      ],
      "tags": [
        "official",
        "hosted",
        "model",
        "multimodal",
        "vision",
        "reasoning",
        "long-context",
        "tool-calling",
        "usage-priced",
        "card-required",
        "closed-source",
        "llms-txt",
        "openapi",
        "new"
      ],
      "lastRelease": "2026-11-17",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 85.8,
        "grade": "AA",
        "agentReady": true,
        "rank": 6,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 3,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 98,
          "maintenance": 87,
          "payments": 45,
          "reliability": 75,
          "schema": 100,
          "security": 100,
          "transparency": 90
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-18"
        },
        "negative": 0,
        "verdict": "OpenAI's most capable API model, 20% cheaper than GPT-6 Astra at $8 and $40 per million tokens, with a 1.05M-token context and the OpenAI API's full set of hosted tools. Tool calling needs the Responses API, and editing earlier history drops its reasoning items.",
        "bestFor": "Long, demanding reasoning, coding and computer-use work through the Responses API.",
        "strengths": [
          "$8 input and $40 output per million tokens, 20% below GPT-6 Astra, with cached input at $0.40",
          "1.05M-token context and 128K output, text and images in",
          "Hosted tools in Responses, from web and file search to computer use, MCP, Skills and tool search",
          "Zero Data Retention for approved organisations, with US and EU data residency",
          "The OpenAI API's status page, per-tier rate limits, official OpenAPI document and dated changelog"
        ],
        "weaknesses": [
          "Tool calling works only through the Responses API, not Chat Completions",
          "Editing earlier history, downgrading the model or changing the end user drops reasoning items, which OpenAI says can cost quality and tokens",
          "Rated Critical for cybersecurity under OpenAI's framework, so some requests meet cyber safeguards",
          "Over 272K input tokens the whole request costs more: input and cache rates double, output 1.5 times",
          "Prices need an account and prepaid credit, with no free route for an agent"
        ],
        "agentNotes": [
          "Call https://api.openai.com/v1/responses with model gpt-6.2-astra and your project key",
          "Use the Responses API whenever the model has to call tools",
          "Don't set reasoning effort to none; the API rejects it",
          "Keep earlier turns unchanged and pass prior output items back in order, including encrypted reasoning items",
          "Stay under 272K input tokens where you can, since a longer request is billed at the long-context rate"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "AA",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 85.8
          }
        ],
        "editorialScores": {
          "ergonomics": 98,
          "maintenance": 87,
          "payments": 45,
          "reliability": 75,
          "schema": 100,
          "security": 100,
          "transparency": 85
        },
        "provenanceScore": 95,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-18",
            "maintenance": "2026-11-18",
            "payments": "2026-11-18",
            "reliability": "2026-11-18",
            "schema": "2026-11-18",
            "security": "2026-11-18",
            "transparency": "2026-11-18"
          },
          "last": "2026-11-18",
          "oldest": "2026-11-18",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "http": "curl https://api.openai.com/v1/responses \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" -H \"content-type: application/json\" \\\n  -d '{\"model\":\"gpt-6.2-astra\",\"input\":\"hello\"}'"
      },
      "letme": {
        "capability": "https://letme.dev/inference.llm",
        "tool": "https://letme.dev/gpt-6-2-astra"
      },
      "sameCompany": [
        "openai-embeddings",
        "openai-guardrails",
        "openai-moderation",
        "openai-image-api",
        "openai-sora",
        "openai-speech-to-text",
        "gpt-live",
        "openai-realtime",
        "openai-agents-sdk",
        "openai-decisions-api",
        "openai-agents-api",
        "openai-codex",
        "openai-dots",
        "gpt-oss-120b",
        "gpt-oss-20b"
      ],
      "sameModel": [
        "openai-api"
      ],
      "area": "models",
      "unitPrices": [
        {
          "item": "GPT-6.2 Astra input",
          "unit": "1m-tokens",
          "usd": 8,
          "note": "Over 272K input tokens $16; Fast mode $16"
        },
        {
          "item": "GPT-6.2 Astra cached input",
          "unit": "1m-tokens",
          "usd": 0.4,
          "note": "30-minute write $10, 12-hour write $20"
        },
        {
          "item": "GPT-6.2 Astra output",
          "unit": "1m-tokens",
          "usd": 40,
          "note": "Over 272K input tokens $60; Fast mode $80"
        }
      ],
      "provenance": {
        "legalEntity": "OpenAI OpCo, LLC",
        "domain": "openai.com",
        "domainRegistered": "2007-01-19",
        "domainNote": "openai.com was registered in 2007, before OpenAI existed.",
        "endpointOnVendorDomain": true,
        "terms": "https://openai.com/policies/services-agreement/",
        "privacy": "https://openai.com/policies/privacy-policy/",
        "statusPage": "https://status.openai.com",
        "changelog": "https://developers.openai.com/api/docs/changelog",
        "securityTxt": "valid",
        "checked": "2026-11-18",
        "notes": [
          "Company and platform facts are the OpenAI API listing's (checked 1 November 2026): OpenAI OpCo, LLC under the Services Agreement; status page at status.openai.com; dated changelog; security.txt per that check.",
          "developers.openai.com and deploymentsafety.openai.com allowed our reader on 18 November. openai.com answered 403, so the announcement wasn't read and no figure from it is used."
        ],
        "score": 95
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/gpt-6-2-astra.json",
      "live": {
        "slug": "gpt-6-2-astra",
        "probe": {
          "target": "https://api.openai.com/v1",
          "method": "get",
          "lastAt": "2026-11-18T23:01:32.852519736Z",
          "lastOk": true,
          "lastStatus": 404,
          "lastMs": 227,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 170,
          "p95ms24h": 333,
          "samples24h": 221,
          "samples30d": 221,
          "days": [
            {
              "date": "2026-11-18",
              "probes": 221,
              "ok": 221
            }
          ],
          "since": "2026-11-18T00:59:21.516492113Z"
        },
        "vendorStatus": {
          "page": "https://status.openai.com",
          "indicator": "none",
          "summary": "All Systems Operational",
          "checkedAt": "2026-11-18T23:00:29.24923944Z"
        },
        "securityTxt": {
          "url": "https://openai.com/.well-known/security.txt",
          "state": "valid",
          "checkedAt": "2026-11-18T16:29:37.978845519Z"
        },
        "llmsTxt": {
          "url": "https://developers.openai.com/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-11-18T16:14:34.66688774Z"
        },
        "pages": [
          {
            "url": "https://developers.openai.com/api/docs/changelog",
            "kind": "changelog",
            "status": 200,
            "checkedAt": "2026-11-18T21:38:17.732790708Z",
            "changedAt": "2026-11-18T21:38:17.732790708Z",
            "fingerprint": "34c7f1890db0"
          },
          {
            "url": "https://openai.com/policies/privacy-policy/",
            "kind": "privacy",
            "status": 403,
            "checkedAt": "2026-11-18T21:49:34.857287938Z",
            "changedAt": "2026-10-11T19:31:08.710809907Z",
            "fingerprint": "604e9f69c16a"
          },
          {
            "url": "https://openai.com/policies/services-agreement/",
            "kind": "terms",
            "status": 403,
            "checkedAt": "2026-11-18T21:49:36.922507461Z",
            "changedAt": "2026-10-04T15:46:24.458479472Z",
            "fingerprint": "46a4b30744ca"
          }
        ],
        "updatedAt": "2026-11-18T23:01:32.852519736Z"
      },
      "streak": {
        "days": 0,
        "from": "2026-11-18",
        "sinceWatching": true,
        "best": 0
      }
    },
    "answer": "GPT-6.2 Astra scores 85.8 (AA) on agent readiness against Nemotron 3.5 Super VL's 61.6 (C), and leads in 6 of 7 scored categories. Nemotron 3.5 Super VL leads on payments \u0026 pricing.",
    "b": {
      "slug": "nemotron-3-5-super-vl",
      "name": "Nemotron 3.5 Super VL",
      "vendor": "NVIDIA",
      "vendorUrl": "https://www.nvidia.com/en-us/ai-data-science/foundation-models/nemotron/",
      "company": "nvidia.com",
      "kind": "model",
      "category": "inference",
      "summary": "Nemotron 3.5 Super VL is NVIDIA's open-weight vision-language model for agents, a 120B mixture of experts with 12B active parameters that reads text, images and video. NVIDIA hosts a free trial endpoint, and the weights are under OpenMDW-1.1.",
      "url": "https://www.anchorterminal.com/tools/nemotron-3-5-super-vl",
      "markdownUrl": "https://www.anchorterminal.com/tools/nemotron-3-5-super-vl.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/nemotron-3-5-super-vl.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/nemotron-3-5-super-vl.json",
      "dns": "nemotron-3-5-super-vl.grade.anchorterminal.com",
      "repo": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16",
      "license": "OpenMDW-1.1 for the weights (permissive, not an OSI licence). The hosted trial endpoint is under the NVIDIA API Trial Terms of Service, and the NIM container under the NVIDIA Software Licence Agreement",
      "transports": [
        "http"
      ],
      "remoteUrl": "https://integrate.api.nvidia.com/v1",
      "packages": [
        {
          "registry": "pypi",
          "name": "langchain-nvidia-ai-endpoints"
        }
      ],
      "auth": "api-key",
      "authNotes": "Bearer key (`nvapi-...`) in the Authorization header, generated by a signed-in person at build.nvidia.com/settings. NVIDIA's NGC docs say personal keys are limited to the services and role chosen at creation and take an expiry date, and organisation administrators can create service keys scoped to actions. The same key pulls the NIM container from nvcr.io. The Hugging Face weights are ungated and need no key.",
      "pricing": "free",
      "pricingNotes": "The hosted endpoint is free with no card, for prototyping, research and testing only, at up to 40 requests a minute and 10,000 a day. Production use needs a partner endpoint, such as Crusoe or DeepInfra at $0.10 input and $0.40 output per million tokens on OpenRouter, or self-hosting, where the NIM needs NVIDIA AI Enterprise at $4,500 a GPU a year (checked 2026-10-17).",
      "priceSummary": "from $0.15 / 1M in",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 on build.nvidia.com, the OpenAPI file or the NIM docs. The hosted endpoint is free behind a key and has no payment route (checked 2026-10-17).",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-10-17"
      },
      "docsUrl": "https://build.nvidia.com/nvidia/nemotron-3.5-super-vl-120b-a12b",
      "llmsTxt": "https://build.nvidia.com/llms.txt",
      "openapi": "https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-3_5-super-vl-120b-a12b-infer",
      "capabilities": [
        "inference.open-weights",
        "inference.llm",
        "inference.local"
      ],
      "tags": [
        "model",
        "open-weights",
        "hosted",
        "free",
        "no-card",
        "trial",
        "multimodal",
        "openai-compatible",
        "openapi",
        "llms-txt",
        "gpu",
        "new"
      ],
      "lastRelease": "2026-10-15",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 61.6,
        "grade": "C",
        "agentReady": false,
        "rank": 720,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 30,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 65,
          "maintenance": 71,
          "payments": 53,
          "reliability": 58,
          "schema": 74,
          "security": 54,
          "transparency": 58
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-04"
        },
        "negative": 0,
        "verdict": "NVIDIA's free endpoint takes OpenAI-format requests with typed tool calls, JSON Schema output and an OpenAPI 3.1 file, and the weights run anywhere under a permissive licence. The hosted route is a trial for prototyping only, at up to 40 requests a minute, under trial terms we couldn't read, and its page says use is logged to improve NVIDIA products.",
        "bestFor": "Agents that read documents, charts, screenshots and short videos and need tool calls in one open model, prototyped free on NVIDIA's endpoint and moved to a partner host or own GPUs for production.",
        "strengths": [
          "OpenAPI 3.1 file for the hosted chat endpoint, with enums for `reasoning_effort`, `tool_choice` and `response_format`",
          "Tool calls with `tool_choice` auto, none, required or a named function, parallel calls, and `json_schema` structured output",
          "Weights in BF16 and NVFP4 under OpenMDW-1.1, a permissive licence with no field-of-use limits, plus open datasets and training recipes",
          "Free hosted endpoint with no card, on the same base URL and key as NVIDIA's other catalogue models",
          "Up to 1M tokens of context in the weights, and reasoning that can be switched off per request"
        ],
        "weaknesses": [
          "NVIDIA says its hosted endpoints are for prototyping, research and testing only, and production use needs a partner endpoint or self-hosting",
          "Rate limit of up to 40 requests a minute and 10,000 a day, which NVIDIA says can vary with other users' traffic",
          "The NVIDIA API Trial Terms of Service, which govern the hosted endpoint, are on a host whose robots.txt answered access denied, so we didn't read them",
          "The hosted page lists 262K tokens of context while the card says 1M, and labels the model early access while the card says GA",
          "No changelog, deprecation policy or SLA for the hosted catalogue was found"
        ],
        "agentNotes": [
          "Set `chat_template_kwargs` to `{\"enable_thinking\": false}` for short tasks. Reasoning is on by default, and reasoning tokens share the `max_tokens` budget",
          "Read reasoning from `reasoning_content` and the answer from `content`, and set `stream` explicitly since the API reference defaults it to true",
          "Don't send confidential or personal data to the hosted trial. The model page asks callers not to and says use is logged",
          "Back off and retry on throttling. Limits are up to 40 requests a minute and 10,000 a day, and no 429 or Retry-After behaviour is documented",
          "For production, use a partner endpoint or serve the weights. When self-hosting with NVIDIA's vLLM command, drop `--allowed-local-media-path=/` unless clients are trusted",
          "Set `NVIDIA_USAGE_TELEMETRY_ENABLED=false` if you use `langchain-nvidia-ai-endpoints` and don't want aggregate usage counts sent to NVIDIA"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 4,
        "avgRating": 3,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "C",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 61.6
          }
        ],
        "editorialScores": {
          "ergonomics": 65,
          "maintenance": 71,
          "payments": 53,
          "reliability": 58,
          "schema": 74,
          "security": 54,
          "transparency": 38
        },
        "provenanceScore": 77,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-04",
            "maintenance": "2026-11-04",
            "payments": "2026-11-04",
            "reliability": "2026-11-04",
            "schema": "2026-11-04",
            "security": "2026-11-04",
            "transparency": "2026-11-04"
          },
          "last": "2026-11-04",
          "lastMoved": "2026-11-13",
          "oldest": "2026-11-04",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "http": "curl https://integrate.api.nvidia.com/v1/chat/completions \\\n  -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n  -H \"Accept: application/json\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"model\": \"nvidia/nemotron-3.5-super-vl-120b-a12b\",\n    \"messages\": [{\"role\": \"user\", \"content\": \"Which number is larger, 9.11 or 9.8?\"}],\n    \"temperature\": 1.0,\n    \"top_p\": 0.95,\n    \"max_tokens\": 8192,\n    \"chat_template_kwargs\": {\"enable_thinking\": true},\n    \"stream\": true\n  }'"
      },
      "letme": {
        "capability": "https://letme.dev/inference.open-weights",
        "tool": "https://letme.dev/nemotron-3-5-super-vl"
      },
      "sameCompany": [
        "nvidia-nemo-retriever",
        "nemo-guardrails",
        "nemotron-3-5-asr-streaming-0-6b",
        "nemotron-3-5-transcribe-30b-a4b",
        "parakeet-tdt-0-6b-v3",
        "parakeet-unified-en-0-6b",
        "nemotron-3-5-parse",
        "cosmos-reason2-2b",
        "nemotron-3-5-bolt-e4b-4gb",
        "nemotron-3-nano-30b-a3b",
        "nemotron-3-nano-4b",
        "nemotron-3-nano-omni-30b-a3b-reasoning",
        "nemotron-3-super-120b-a12b",
        "nemotron-3-ultra-550b-a55b",
        "nemotron-3-5-lightning-30b-a3b"
      ],
      "family": {
        "lab": "NVIDIA (Nemotron)",
        "family": "Nemotron 3",
        "url": "https://www.anchorterminal.com/open-weights/#nvidia",
        "others": [
          {
            "name": "Nemotron 3 Nano 30B-A3B",
            "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16",
            "params": "30B total, 3B active (31.6B per the safetensors index)",
            "listing": "https://www.anchorterminal.com/tools/nemotron-3-nano-30b-a3b"
          },
          {
            "name": "Nemotron 3 Nano 30B-A3B Base",
            "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16",
            "params": "30B total, 3B active"
          },
          {
            "name": "Nemotron 3 Super 120B-A12B",
            "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
            "params": "120B total, 12B active",
            "listing": "https://www.anchorterminal.com/tools/nemotron-3-super-120b-a12b"
          },
          {
            "name": "Nemotron 3 Super 120B-A12B Base",
            "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16",
            "params": "120B total, 12B active"
          },
          {
            "name": "Nemotron 3 Nano 4B",
            "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16",
            "params": "4B",
            "listing": "https://www.anchorterminal.com/tools/nemotron-3-nano-4b"
          },
          {
            "name": "Nemotron 3 Nano Omni 30B-A3B Reasoning",
            "url": "https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16",
            "params": "30B total, 3B active",
            "listing": "https://www.anchorterminal.com/tools/nemotron-3-nano-omni-30b-a3b-reasoning"
          },
          {
            "name": "Nemotron 3 Ultra 550B-A55B",
            "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16",
            "params": "550B total, 55B active",
            "listing": "https://www.anchorterminal.com/tools/nemotron-3-ultra-550b-a55b"
          },
          {
            "name": "Nemotron 3 Ultra 550B-A55B Base",
            "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16",
            "params": "550B total, 55B active"
          },
          {
            "name": "Nemotron 3 Ultra 550B-A55B GenRM",
            "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-GenRM",
            "params": "550B total, 55B active"
          },
          {
            "name": "Nemotron 3.5 Lightning 30B-A3B",
            "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16",
            "params": "30B total, 3B active",
            "listing": "https://www.anchorterminal.com/tools/nemotron-3-5-lightning-30b-a3b"
          },
          {
            "name": "Nemotron 3.5 Lightning 30B-A3B Base",
            "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16",
            "params": "30B total, 3B active"
          },
          {
            "name": "Nemotron 3.5 Super VL 120B-A12B Base",
            "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16",
            "params": "120B total, 12B active"
          },
          {
            "name": "Nemotron 3.5 Bolt 74B-A9B",
            "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16",
            "params": "74B total, 9B active"
          },
          {
            "name": "Nemotron 3.5 Bolt E4B 4GB",
            "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB",
            "params": "8B total, 4B effective",
            "listing": "https://www.anchorterminal.com/tools/nemotron-3-5-bolt-e4b-4gb"
          },
          {
            "name": "Nemotron Labs 3 Elastic 30B-A3B",
            "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B-BF16",
            "params": "30B total, 3B active"
          },
          {
            "name": "Nemotron Labs 3 Puzzle 75B-A9B",
            "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-BF16",
            "params": "75B total, 9B active"
          },
          {
            "name": "Nemotron 3 Labs Ultra Math SFT",
            "url": "https://huggingface.co/nvidia/Nemotron-3-Labs-Ultra-Math-SFT",
            "params": "550B total, 55B active"
          },
          {
            "name": "Nemotron 3 Labs Ultra Math RL",
            "url": "https://huggingface.co/nvidia/Nemotron-3-Labs-Ultra-Math-RL",
            "params": "550B total, 55B active"
          },
          {
            "name": "Nemotron Labs 3 Competitive Coding 550B-A55B",
            "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-3-Competitive-Coding-550B-A55B-NVFP4",
            "params": "550B total, 55B active"
          },
          {
            "name": "nemotron-3.5-asr-streaming-0.6b",
            "url": "https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b",
            "params": "0.6B (638M per the safetensors count)",
            "listing": "https://www.anchorterminal.com/tools/nemotron-3-5-asr-streaming-0-6b"
          },
          {
            "name": "Nemotron 3.5 Parse",
            "url": "https://huggingface.co/nvidia/Nemotron-3.5-Parse",
            "params": "0.631B (630,800,496 trainable parameters per the card)",
            "listing": "https://www.anchorterminal.com/tools/nemotron-3-5-parse"
          },
          {
            "name": "Nemotron 3.5 Transcribe 30B-A4B",
            "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B",
            "params": "30B total, about 4.3B active (33,697,781,029 by the Hub's safetensors count)",
            "listing": "https://www.anchorterminal.com/tools/nemotron-3-5-transcribe-30b-a4b"
          }
        ],
        "olderCount": 47,
        "unrestrictedCopies": 4
      },
      "area": "models",
      "provenance": {
        "legalEntity": "NVIDIA Corporation",
        "domain": "nvidia.com",
        "domainRegistered": "1993-04-20",
        "endpointOnVendorDomain": true,
        "terms": "https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf",
        "privacy": "https://www.nvidia.com/en-us/about-nvidia/privacy-policy/",
        "statusPage": "https://status.ngc.nvidia.com",
        "changelog": "",
        "securityTxt": "none",
        "checked": "2026-10-17",
        "notes": [
          "The card names NVIDIA Corporation as model developer. The hosted endpoint is on integrate.api.nvidia.com and the model page on build.nvidia.com, both under nvidia.com. RDAP gives a registration date of 20 April 1993.",
          "The model page names the NVIDIA API Trial Terms of Service, a PDF on assets.ngc.nvidia.com, as the governing terms of the hosted trial. That host's robots.txt answered with an S3 AccessDenied error, so the PDF was not read, as for the nvidia-nemo-retriever listing.",
          "The privacy policy is NVIDIA's general policy, effective 22 September 2025. It does not address prompts sent to the API catalogue. The model page's consent text says use is logged for security and to improve NVIDIA products and services, and that the logged data for improvement is not linked to the user's identity.",
          "status.ngc.nvidia.com is a Statuspage site with components for NVIDIA Build and Cloud Functions, the service the hosted endpoints run on per the error URNs in the OpenAPI file.",
          "No changelog for the API catalogue or the model was found. The Hugging Face commit history records card revisions from 12 to 16 October 2026.",
          "www.nvidia.com/.well-known/security.txt answered 403 and build.nvidia.com/.well-known/security.txt returned the site's HTML page. Vulnerability reports go to NVIDIA PSIRT, linked from the model card."
        ],
        "score": 77
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/nemotron-3-5-super-vl.json",
      "live": {
        "slug": "nemotron-3-5-super-vl",
        "probe": {
          "target": "https://integrate.api.nvidia.com/v1",
          "method": "get",
          "lastAt": "2026-11-18T23:01:42.471853352Z",
          "lastOk": true,
          "lastStatus": 404,
          "lastMs": 95,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 50,
          "p95ms24h": 175,
          "samples24h": 241,
          "samples30d": 7840,
          "days": [
            {
              "date": "2026-10-18",
              "probes": 256,
              "ok": 256
            },
            {
              "date": "2026-10-19",
              "probes": 255,
              "ok": 255
            },
            {
              "date": "2026-10-20",
              "probes": 252,
              "ok": 252
            },
            {
              "date": "2026-10-21",
              "probes": 253,
              "ok": 253
            },
            {
              "date": "2026-10-22",
              "probes": 253,
              "ok": 253
            },
            {
              "date": "2026-10-23",
              "probes": 248,
              "ok": 248
            },
            {
              "date": "2026-10-24",
              "probes": 251,
              "ok": 251
            },
            {
              "date": "2026-10-25",
              "probes": 250,
              "ok": 250
            },
            {
              "date": "2026-10-26",
              "probes": 252,
              "ok": 252
            },
            {
              "date": "2026-10-27",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-10-28",
              "probes": 251,
              "ok": 251
            },
            {
              "date": "2026-10-29",
              "probes": 248,
              "ok": 248
            },
            {
              "date": "2026-10-30",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-10-31",
              "probes": 251,
              "ok": 251
            },
            {
              "date": "2026-11-01",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-11-02",
              "probes": 250,
              "ok": 250
            },
            {
              "date": "2026-11-03",
              "probes": 248,
              "ok": 248
            },
            {
              "date": "2026-11-04",
              "probes": 246,
              "ok": 246
            },
            {
              "date": "2026-11-05",
              "probes": 185,
              "ok": 185
            },
            {
              "date": "2026-11-06",
              "probes": 241,
              "ok": 241
            },
            {
              "date": "2026-11-07",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-08",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-09",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-10",
              "probes": 244,
              "ok": 244
            },
            {
              "date": "2026-11-11",
              "probes": 244,
              "ok": 244
            },
            {
              "date": "2026-11-12",
              "probes": 245,
              "ok": 245
            },
            {
              "date": "2026-11-13",
              "probes": 238,
              "ok": 238
            },
            {
              "date": "2026-11-14",
              "probes": 244,
              "ok": 244
            },
            {
              "date": "2026-11-15",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-16",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-17",
              "probes": 242,
              "ok": 242
            },
            {
              "date": "2026-11-18",
              "probes": 231,
              "ok": 231
            }
          ],
          "since": "2026-10-17T00:00:00Z"
        },
        "vendorStatus": {
          "page": "https://status.ngc.nvidia.com",
          "indicator": "none",
          "summary": "All Systems Operational",
          "checkedAt": "2026-11-18T23:00:49.796050871Z"
        },
        "versions": [
          {
            "registry": "pypi",
            "name": "langchain-nvidia-ai-endpoints",
            "version": "1.5.0",
            "released": "2026-10-14",
            "seenAt": "2026-11-18T18:11:04.365619988Z"
          }
        ],
        "pypiWeekly": 124464,
        "securityTxt": {
          "url": "https://nvidia.com/.well-known/security.txt",
          "state": "unknown",
          "checkedAt": "2026-11-18T16:30:06.787926111Z"
        },
        "llmsTxt": {
          "url": "https://build.nvidia.com/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-11-18T16:15:22.398438972Z"
        },
        "domain": {
          "domain": "nvidia.com",
          "registered": "1993-04-20",
          "source": "https://rdap.verisign.com/com/v1/domain/nvidia.com",
          "checkedAt": "2026-11-15T15:15:54.279575834Z"
        },
        "models": {
          "nvidia/nemotron-3.5-super-vl": {
            "openrouterId": "nvidia/nemotron-3.5-super-vl",
            "tools": true,
            "structuredOutputs": true,
            "jsonMode": true,
            "reasoning": true,
            "input": [
              "image",
              "text",
              "video"
            ],
            "promptCaching": true,
            "contextTokens": 1048576,
            "maxOutput": 235929,
            "checkedAt": "2026-11-17T23:49:36.802198339Z"
          }
        },
        "updatedAt": "2026-11-18T23:01:42.471853352Z"
      },
      "streak": {
        "days": 32,
        "from": "2026-10-17",
        "sinceWatching": true,
        "best": 32
      }
    },
    "edges": [
      {
        "by": 46,
        "category": "security",
        "leads": "gpt-6-2-astra",
        "name": "Security \u0026 auth",
        "reasons": {
          "a": "Model reading for gpt-6-2-astra on the OpenAI API. Platform facts are the OpenAI API listing's (openai-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Model reading. Project keys with All, Restricted (per-endpoint None, Read or Write) and Read Only permissions, service accounts, and mutual TLS with X.509 workload identity GA since 26 August, per the 1 October check. The changelog adds project key expiry dates on 10 September, key-creation controls on 15 September and, on 21 October, organisation and project settings that limit which service tiers a project may use (30). API data not used for training unless the customer opts in, since 1 March 2023 (20). Abuse-monitoring logs kept up to 30 days, and Zero Data Retention or Modified Abuse Monitoring by approval. The data-controls guide re-read on 1 November lists Chat Completions, Responses, Decisions and ten other endpoints as ZDR-eligible; `/v1/agents`, Conversations, Files and vector stores aren't (15). Usage and Costs filter by API key since 4 August, with Admin APIs to match, and audit logs for enterprise (15). SOC 2 Type 2, ISO 27001, 27017, 27018, 27701 and 42001 per the 1 October check, not re-read on 1 November, a Bugcrowd bug bounty and a coordinated disclosure policy, both linked from a signed security.txt. That security.txt had no Expires field on 27 October, which RFC 9116 requires, so the disclosure policy carries this line. It wasn't re-read on 1 November (20). For GPT-6.2 Astra the GPT-6.2 guide, read 18 November, says ZDR is available to approved organisations on eligible endpoints, with US and EU data residency.",
          "b": "Model reading. `nvapi-` bearer keys sent in a header. NVIDIA's NGC docs say personal keys are limited to the services and role chosen at creation and take an expiry, and service keys can be scoped to actions (25 of 30). Inference only, with no write operation, but no zero-retention option for the hosted trial was found, and the model page asks callers not to send confidential or personal data (8 of 20). The model reads web pages, PDFs and images an agent passes it, and NVIDIA publishes safety, bias and privacy subcards, but no prompt-injection guidance or results were found (5 of 15). No per-call log for API callers was found, only rate limits shown in the account (3 of 15). NVIDIA PSIRT runs coordinated disclosure and publishes security bulletins, linked from the card, the reading nvidia-nemo-retriever and nemo-guardrails give the same programme (13). www.nvidia.com/.well-known/security.txt answered 403 per the 2 November check and build.nvidia.com has none, and no certification or bug bounty for the API catalogue was found (13 of 20). 25+8+5+3+13 = 54."
        },
        "scores": {
          "a": 100,
          "b": 54
        }
      },
      {
        "by": 33,
        "category": "ergonomics",
        "leads": "gpt-6-2-astra",
        "name": "Agent ergonomics",
        "reasons": {
          "a": "Model reading for gpt-6-2-astra on the OpenAI API. Platform facts are the OpenAI API listing's (openai-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Tool use with parallel calls and forced tool choice, 18 of 20 because GPT-6 Astra, GPT-6.1 Sol and GPT-6.1 Terra call tools only through the Responses API (18). Strict structured outputs (15). Automatic prompt caching with cached input at 0.1x on Astra and Luna ($0.01 per million on Luna) and 0.05x on GPT-6.1 Sol ($0.10) and GPT-6.1 Terra ($0.05), and a 12-hour cache lifetime in the Responses API since 20 October (15). 1.05M context on Astra, GPT-6.1 Sol, GPT-6.1 Terra and Luna (15). Batch at half price (10). Official SDKs in Python, JavaScript and more (10). Documented error codes with retry guidance (15). For GPT-6.2 Astra, read 18 November: tool calling only through the Responses API, the same 18 of 20; 1.05M context and 128K output; cached input $0.40, 0.05x input; Batch half price. Tool search and Skills are supported in Responses, recorded in details without points, as for the Claude API.",
          "b": "Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). OpenAI-format tools, `tool_choice` auto, none, required or a named function, and parallel calls on by default (20 of 20). `response_format` with `json_schema` and `strict` in the OpenAPI file. Not tested by us (12 of 15). The card describes prefix caching for self-hosted serving, but no caching on the hosted endpoint is documented (2 of 10). 1M tokens in the weights, but the hosted page lists 262K, and completions are capped at 131,072 tokens (12 of 15). No batch mode (0 of 10). Any OpenAI SDK works with the base URL, and NVIDIA maintains `langchain-nvidia-ai-endpoints`. Only `messages` is required, but reasoning defaults to on at high effort and the reference defaults `stream` to true (10 of 15). Errors carry a message, type and request id, with no 429 or rate-limit body documented (9 of 15). 65."
        },
        "scores": {
          "a": 98,
          "b": 65
        }
      },
      {
        "by": 32,
        "category": "transparency",
        "leads": "gpt-6-2-astra",
        "name": "Transparency \u0026 trust",
        "reasons": {
          "a": "Model reading for gpt-6-2-astra on the OpenAI API. Platform facts are the OpenAI API listing's (openai-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Closed service with clear terms, SDKs Apache-2.0 (15). The data-controls guide, re-read on 1 November, gives retention periods per endpoint, the training default and the ZDR route. The DPA, effective 1 January 2026, commits to return or deletion of customer data on termination, 30 days to object to a new subprocessor, and SCCs with the UK Addendum for transfers, and nothing in it conflicts with the guide, per the 4 October check, not re-read on 1 November (30). Deprecations page with announcement and shutdown dates, and `GET /v1/models` returns each model's `shutdown_date` (20). The subprocessor list, updated 9 July 2026, names its third-party subprocessors and OpenAI affiliates with the processing countries for each and a form to get notice of new ones, and data residency regions are listed, per the 4 October check, not re-read on 1 November (20).",
          "b": "Weights under OpenMDW-1.1, a short permissive licence from the Linux Foundation with no field-of-use limits, but not an OSI licence. Datasets and training recipes are released. The hosted trial is under terms we couldn't read, and the OpenAPI file names a different model licence and the AI Enterprise EULA (22 of 30). NVIDIA's privacy policy (22 September 2025) doesn't address API prompts. The model page says use is logged for security and to improve NVIDIA products, with improvement data not linked to identity, and gives no retention period. The trial terms that may say more were unread (8 of 30). No deprecation policy or dated notices for catalogue models. The page carries an `isDeprecated` flag only (3 of 20). The quickstart says hosted endpoints run on NVIDIA DGX Cloud, but no subprocessors or data locations for the catalogue were found (5 of 20). `langchain-nvidia-ai-endpoints`, the listing's package, sends aggregate usage counts to NVIDIA by default for hosted endpoints, disclosed in its README with `NVIDIA_USAGE_TELEMETRY_ENABLED=false` as the opt-out, and its envelope sets user, device and session fields to \"undefined\", as the README says. Disclosed, so no term. 22+8+3+5 = 38."
        },
        "scores": {
          "a": 90,
          "b": 58
        }
      },
      {
        "by": 26,
        "category": "schema",
        "leads": "gpt-6-2-astra",
        "name": "Schema \u0026 documentation",
        "reasons": {
          "a": "Model reading for gpt-6-2-astra on the OpenAI API. Platform facts are the OpenAI API listing's (openai-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Official OpenAPI document (openapi.yaml and openapi.json) in the openai/openai-openapi repository, whose openapi.yaml (version 2.3.0, updated 31 October) lists `gpt-6.1-terra` (25). llms.txt index with per-product files, and every docs page has a Markdown twin at `.md` (10). The reference documents each parameter, and model pages say which model fits which job (20). Structured outputs with `strict: true` on schemas and function tools (15). Error codes guide with types and recovery advice, now with a 400 `service_tier` error for tiers a project doesn't allow (15). Dated model snapshots and a dated changelog, last entry 30 October (15).",
          "b": "Model reading. An OpenAPI 3.1 file for this model's `/chat/completions` on docs.api.nvidia.com, with typed request and response schemas (25). build.nvidia.com/llms.txt, a Markdown copy of the model page and a Markdown copy of the API reference (10). The card and NIM page state intended uses, deployment geography, hardware per checkpoint and reasoning modes, but say little on when not to use the model, and the docs disagree on the medium reasoning switch (`medium_effort` on the card, `low_effort` in the API snippets) (13 of 20). Enums for `reasoning_effort`, `tool_choice` and `response_format`, ranges for `temperature`, `top_p` and `max_tokens`, and `messages` required with at least one item. `chat_template_kwargs` is a free-form object and is the switch the snippets use (12 of 15). Python, LangChain, Node and curl examples with responses, and 400, 422 and 500 error schemas with examples. No 429 (11 of 15). No changelog for the catalogue or the model. The OpenAPI version is 1.0.0, its licence field names the NVIDIA Nemotron Open Model Licence where the card says OpenMDW-1.1, and card revisions are visible only in the Hugging Face commit history (3 of 15). 74."
        },
        "scores": {
          "a": 100,
          "b": 74
        }
      },
      {
        "by": 17,
        "category": "reliability",
        "leads": "gpt-6-2-astra",
        "name": "Reliability",
        "reasons": {
          "a": "Model reading for gpt-6-2-astra on the OpenAI API. Platform facts are the OpenAI API listing's (openai-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Status page at status.openai.com with component history (20). Two API-wide majors in the 90 days to 1 November, elevated errors across ChatGPT, Codex and the API (the Agents API included) on 29 September, with Chat Completions, Responses, Batch, Realtime, Embeddings, Images, Files and the other API components degraded from 17:52 to 23:14 UTC, and elevated error rates across API models on 17 September, with eleven components degraded from 20:20 to 21:20 UTC. Two majors give 5 of 30. The 25 July incident is now outside the window. The 29 September write-up, posted on 6 October, traces it to a feature rollout that exhausted shared network connection capacity. Every other incident since 3 August that lists an API component is partial or under an hour, so minor. Degraded performance across ChatGPT, Codex and the APIs on 21 October listed every API component but ran 22 minutes (02:26 to 02:48 UTC). Single-model incidents were GPT-5.6 Sol errors on 11 September (09:08 to 11:21 UTC), `gpt-5.6-luna` errors on 21 October (70 minutes) and GPT-6.1 Sol degraded performance on Batch, Chat Completions and Responses on 27 October (78 minutes). Partial incidents were latency for some Responses requests on the US endpoint on 31 August and 1 September, image generation where some requests failed on 8 September, latency for some Responses and Chat Completions requests on 30 September, large-PDF errors in Responses and an Agents API computer use incident on 6 October, Responses errors for users in India, Japan and Korea on 22 October and errors on some GPT Image 2 edit requests on 30 October (14:35 to 18:36 UTC). Image model incidents on 16 September and 14 October and file download errors on 19 October each ran about 40 minutes. FedRAMP errors for Astra and Sol on 21 October and authentication errors near Illinois on 20 October list no API component. Rate limits published per tier and model family with rate-limit headers (15). 429 guidance, re-read on 1 November, covers `Retry-After` as a minimum wait, backoff with jitter when it's missing, a gradual ramp, and splits `slow_down` (429) from `server_is_overloaded` (503) (15). Scale Tier carries a 99.9% uptime SLA, through sales, per the 1 October check, not re-read on 1 November (10). Responses and Chat Completions are GA (10). 20 + 5 + 15 + 15 + 10 + 10 = 75. The model page, read 18 November, lists GPT-6.2 Astra with no preview label and its own rate limits, Build 5,000 requests and 1M tokens a minute, Launch 10,000 and 4M, Grow 15,000 and 40M.",
          "b": "Hosted reading, for NVIDIA's trial endpoint. status.ngc.nvidia.com is a Statuspage site with NVIDIA Build and Cloud Functions components and a readable history (20). In the 90 days to 4 November, re-read from history.atom, two incidents, both minor for an API caller, and none posted since 29 September. SMS verification for NVIDIA Build was unavailable in China from 23 to 29 September, which affects sign-up, and on 10 August new Cloud Functions deployments failed for about three hours while existing deployments kept running (20). build.nvidia.com gives limits of up to 40 requests a minute and 10,000 a day, and says they vary by model and with other users' traffic (12 of 15). The OpenAPI file documents a 202 pending result with an `NVCF-REQID` to poll, but no 429, Retry-After or backoff guidance, and NVIDIA's FAQ says to expect long waits under load (3 of 15). No SLA for the trial. NVIDIA's SLAs come with AI Enterprise for self-hosted software (0). The card says v1.0 GA, but the hosted page calls the model early access and NVIDIA calls the catalogue a trial for prototyping only (3 of 10). The model page re-read on 4 November still says early access, with a free endpoint marked available and 40 rpm. 20+20+12+3+0+3 = 58."
        },
        "scores": {
          "a": 75,
          "b": 58
        }
      },
      {
        "by": 16,
        "category": "maintenance",
        "leads": "gpt-6-2-astra",
        "name": "Maintenance \u0026 community",
        "reasons": {
          "a": "Model reading for gpt-6-2-astra on the OpenAI API. Platform facts are the OpenAI API listing's (openai-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Model reading. GPT-6 Rosalind, a life-sciences model for approved organisations, launched on 30 October, after GPT-6.1 Terra on 26 October and the Decisions API GA on 22 October (30). Published minimum notice of 6 months for GA models, 3 months for specialised variants, as little as 2 weeks for previews. On 14 October GPT-4o (`gpt-4o-2024-08-06`, `gpt-4o-2024-11-20`), GPT-4o mini, GPT-4.1 and GPT-4.1 mini were given a shutdown date of 14 January 2027, 92 days, with no safety or compliance reason stated. These are GA models, so the page's own 6-month minimum wasn't kept, as with `gpt-5.4-cyber`'s 20 days in September. 8 of 12, the award for a minimum of two to three months in practice. Five shutdown dates in the 90 days to 1 November, the Assistants API on 26 August (announced in August 2025), `gpt-5.2-chat-latest` and `gpt-5.3-chat-latest` on 10 August (announced 8 May), `gpt-3.5-turbo-instruct`, `babbage-002`, `davinci-002` and `gpt-3.5-turbo-1106` on 28 September (announced 26 September 2025, missed in the 27 October count), `gpt-5.4-cyber` on 1 October and the legacy snapshots on 23 October (announced 22 April). Sora 2 and the Videos API (24 September) are scored on the openai-sora listing. Four of the five kept the published notice, so 4 of 8 as before, as amazon-bedrock has for four dates after full notice. Dated changelog several times a month and a help centre (15 of 15). openai-python had 215 open issues per the 1 October check, replies not sampled (5 of 10). Current official SDKs, `openai` 3.42.0 on PyPI (31 October) and npm `openai` 7.47.0 (15). Supported runtimes stated, Python 3.10 or later and Node 22 or later, the npm package's `engines` re-read on 1 November (10). GPT-6.2 Astra and Sol launched on 17 November, the newest model change on the platform.",
          "b": "Released on 15 October 2026. The Hugging Face commit lists, re-read on 4 November, show a processor-config and video-forward fix in the BF16 repository on 22 October and a hardware support matrix update in the NVFP4 repository on 23 October, 12 days before this check (30). NVIDIA released three Nemotron 3.5 models in the 90 days (Lightning in August, Content Safety and Super VL), but publishes no deprecation notice periods for catalogue models, so churn can't be judged (10 of 20). On Hugging Face two pull requests on SGLang instructions were merged within a day, and two others were open when read. Support for the free tier is the developer forum (15 of 25). NVIDIA maintains `langchain-nvidia-ai-endpoints` (1.5.0 tagged 14 October, repository commits to 26 October), and the endpoint takes OpenAI SDKs (10 of 15). Day-one recipes for vLLM 0.32.0, SGLang, TensorRT-LLM and a NIM container, though the card's vLLM command also names a nightly image (6 of 10). 30+10+15+10+6 = 71."
        },
        "scores": {
          "a": 87,
          "b": 71
        }
      }
    ],
    "facts": [
      {
        "a": "Model API",
        "b": "Model API",
        "name": "Kind"
      },
      {
        "a": "OpenAI",
        "b": "NVIDIA",
        "name": "Vendor"
      },
      {
        "a": "https://api.openai.com/v1",
        "b": "https://integrate.api.nvidia.com/v1",
        "name": "Hosted endpoint"
      },
      {
        "a": "",
        "b": "HTTP",
        "name": "Transports"
      },
      {
        "a": "API key",
        "b": "API key",
        "name": "Auth"
      },
      {
        "a": "Pay per use",
        "b": "Free",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "Closed model, used through the OpenAI API under OpenAI's Services Agreement",
        "b": "OpenMDW-1.1 for the weights (permissive, not an OSI licence). The hosted trial endpoint is under the NVIDIA API Trial Terms of Service, and the NIM container under the NVIDIA Software Licence Agreement",
        "name": "Licence"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "llms.txt"
      },
      {
        "a": "2026-11-17",
        "b": "2026-10-15",
        "name": "Last release"
      },
      {
        "a": "couldn't be read",
        "b": "not read yet",
        "name": "Terms last updated"
      },
      {
        "a": "couldn't be read",
        "b": "no date given",
        "name": "Privacy policy last updated"
      },
      {
        "a": "couldn't be read",
        "b": "not read yet",
        "name": "Customer content may train models"
      },
      {
        "a": "couldn't be read",
        "b": "not read yet",
        "name": "Terms restrict automated access"
      },
      {
        "a": "couldn't be read",
        "b": "not read yet",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "couldn't be read",
        "b": "not read yet",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "couldn't be read",
        "b": "not read yet",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "none",
        "b": "3/5 (4)",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "GPT-6.2 Astra scores 85.8 (AA) on agent readiness against Nemotron 3.5 Super VL's 61.6 (C), and leads in 6 of 7 scored categories. Nemotron 3.5 Super VL leads on payments \u0026 pricing.",
        "question": "Which is better for AI agents, GPT-6.2 Astra or Nemotron 3.5 Super VL?"
      },
      {
        "answer": "Both need an API key.",
        "question": "Do GPT-6.2 Astra and Nemotron 3.5 Super VL need an API key?"
      },
      {
        "answer": "Yes. GPT-6.2 Astra has a hosted endpoint at https://api.openai.com/v1 and Nemotron 3.5 Super VL at https://integrate.api.nvidia.com/v1.",
        "question": "Can an agent call GPT-6.2 Astra and Nemotron 3.5 Super VL without installing anything?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 75 against 58",
          "Schema \u0026 documentation, 100 against 74",
          "Agent ergonomics, 98 against 65",
          "Security \u0026 auth, 100 against 54",
          "Maintenance \u0026 community, 87 against 71",
          "Transparency \u0026 trust, 90 against 58"
        ],
        "also": [
          "Agent-ready, a grade of BB or better"
        ],
        "goodFor": "Long, demanding reasoning, coding and computer-use work through the Responses API.",
        "slug": "gpt-6-2-astra",
        "watchFor": "Tool calling works only through the Responses API, not Chat Completions"
      },
      {
        "aheadOn": [
          "Payments \u0026 pricing, 53 against 45"
        ],
        "also": [
          "Free to start without a card"
        ],
        "goodFor": "Agents that read documents, charts, screenshots and short videos and need tool calls in one open model, prototyped free on NVIDIA's endpoint and moved to a partner host or own GPUs for production.",
        "slug": "nemotron-3-5-super-vl",
        "watchFor": "NVIDIA says its hosted endpoints are for prototyping, research and testing only, and production use needs a partner endpoint or self-hosting"
      }
    ],
    "history": {
      "gpt-6-2-astra": null,
      "nemotron-3-5-super-vl": [
        {
          "causes": [
            "method"
          ],
          "date": "2026-11-13",
          "delta": 2.3,
          "from": 59.3,
          "fromGrade": "C",
          "to": 61.6,
          "toGrade": "C"
        },
        {
          "causes": [
            "correction"
          ],
          "date": "2026-11-04",
          "delta": 0.5,
          "from": 58.8,
          "fromGrade": "C",
          "to": 59.3,
          "toGrade": "C"
        },
        {
          "causes": [
            "method"
          ],
          "date": "2026-10-30",
          "delta": -0.2,
          "from": 59,
          "fromGrade": "C",
          "to": 58.8,
          "toGrade": "C"
        }
      ]
    },
    "job": {
      "capability": "inference.llm",
      "name": "LLM inference"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-gpt-6-2-astra.json",
        "title": "Amazon Bedrock vs GPT-6.2 Astra",
        "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-gpt-6-2-astra"
      },
      {
        "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-nemotron-3-5-super-vl.json",
        "title": "Amazon Bedrock vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-gpt-6-2-astra.json",
        "title": "Claude API vs GPT-6.2 Astra",
        "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-gpt-6-2-astra"
      },
      {
        "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-nemotron-3-5-super-vl.json",
        "title": "Claude API vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/antseed-vs-gpt-6-2-astra.json",
        "title": "Antseed vs GPT-6.2 Astra",
        "url": "https://www.anchorterminal.com/compare/antseed-vs-gpt-6-2-astra"
      },
      {
        "json": "https://www.anchorterminal.com/compare/antseed-vs-nemotron-3-5-super-vl.json",
        "title": "Antseed vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/antseed-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/azure-openai-vs-gpt-6-2-astra.json",
        "title": "Azure OpenAI in Foundry Models vs GPT-6.2 Astra",
        "url": "https://www.anchorterminal.com/compare/azure-openai-vs-gpt-6-2-astra"
      },
      {
        "json": "https://www.anchorterminal.com/compare/azure-openai-vs-nemotron-3-5-super-vl.json",
        "title": "Azure OpenAI in Foundry Models vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/azure-openai-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-gpt-6-2-astra.json",
        "title": "BlockRun.AI vs GPT-6.2 Astra",
        "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-gpt-6-2-astra"
      },
      {
        "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-nemotron-3-5-super-vl.json",
        "title": "BlockRun.AI vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cerebras-inference-vs-gpt-6-2-astra.json",
        "title": "Cerebras Inference vs GPT-6.2 Astra",
        "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-gpt-6-2-astra"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cerebras-inference-vs-nemotron-3-5-super-vl.json",
        "title": "Cerebras Inference vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/claude-fable-5-2-vs-gpt-6-2-astra.json",
        "title": "Claude Fable 5.2 vs GPT-6.2 Astra",
        "url": "https://www.anchorterminal.com/compare/claude-fable-5-2-vs-gpt-6-2-astra"
      },
      {
        "json": "https://www.anchorterminal.com/compare/claude-fable-5-2-vs-nemotron-3-5-super-vl.json",
        "title": "Claude Fable 5.2 vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/claude-fable-5-2-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-gpt-6-2-astra.json",
        "title": "Claude Mythos 5.2 vs GPT-6.2 Astra",
        "url": "https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-gpt-6-2-astra"
      },
      {
        "json": "https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-nemotron-3-5-super-vl.json",
        "title": "Claude Mythos 5.2 vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-gpt-6-2-astra.json",
        "title": "Cloudflare AI Gateway vs GPT-6.2 Astra",
        "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-gpt-6-2-astra"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-nemotron-3-5-super-vl.json",
        "title": "Cloudflare AI Gateway vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-gpt-6-2-astra.json",
        "title": "Cloudflare Workers AI vs GPT-6.2 Astra",
        "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-gpt-6-2-astra"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-nemotron-3-5-super-vl.json",
        "title": "Cloudflare Workers AI vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-gpt-6-2-astra.json",
        "title": "Cohere Chat API (Command models) vs GPT-6.2 Astra",
        "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-gpt-6-2-astra"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-nemotron-3-5-super-vl.json",
        "title": "Cohere Chat API (Command models) vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepinfra-vs-gpt-6-2-astra.json",
        "title": "DeepInfra vs GPT-6.2 Astra",
        "url": "https://www.anchorterminal.com/compare/deepinfra-vs-gpt-6-2-astra"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepinfra-vs-nemotron-3-5-super-vl.json",
        "title": "DeepInfra vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/deepinfra-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-api-vs-gpt-6-2-astra.json",
        "title": "DeepSeek API vs GPT-6.2 Astra",
        "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-gpt-6-2-astra"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-api-vs-nemotron-3-5-super-vl.json",
        "title": "DeepSeek API vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/eden-ai-vs-gpt-6-2-astra.json",
        "title": "Eden AI vs GPT-6.2 Astra",
        "url": "https://www.anchorterminal.com/compare/eden-ai-vs-gpt-6-2-astra"
      },
      {
        "json": "https://www.anchorterminal.com/compare/eden-ai-vs-nemotron-3-5-super-vl.json",
        "title": "Eden AI vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/eden-ai-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-gpt-6-2-astra.json",
        "title": "Glimpse vs GPT-6.2 Astra",
        "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-gpt-6-2-astra"
      },
      {
        "json": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-nemotron-3-5-super-vl.json",
        "title": "Glimpse vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-gpt-6-2-astra.json",
        "title": "Fireworks AI Inference vs GPT-6.2 Astra",
        "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-gpt-6-2-astra"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-nemotron-3-5-super-vl.json",
        "title": "Fireworks AI Inference vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-gpt-6-2-astra.json",
        "title": "Gemini 4 Carbon vs GPT-6.2 Astra",
        "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-gpt-6-2-astra"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-nemotron-3-5-super-vl.json",
        "title": "Gemini 4 Carbon vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-gpt-6-2-astra.json",
        "title": "Gemini 4 Hydrogen vs GPT-6.2 Astra",
        "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-gpt-6-2-astra"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-nemotron-3-5-super-vl.json",
        "title": "Gemini 4 Hydrogen vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-api-vs-gpt-6-2-astra.json",
        "title": "Gemini Developer API vs GPT-6.2 Astra",
        "url": "https://www.anchorterminal.com/compare/gemini-api-vs-gpt-6-2-astra"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-api-vs-nemotron-3-5-super-vl.json",
        "title": "Gemini Developer API vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/gemini-api-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-groq.json",
        "title": "GPT-6.2 Astra vs GroqCloud",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-groq"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-hugging-face-inference-providers.json",
        "title": "GPT-6.2 Astra vs Hugging Face Inference Providers",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-hugging-face-inference-providers"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-hy4.json",
        "title": "GPT-6.2 Astra vs Tencent Hy4",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-hy4"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-jais-3.json",
        "title": "GPT-6.2 Astra vs Jais 3",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-jais-3"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-meta-model-api.json",
        "title": "GPT-6.2 Astra vs Meta Model API",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-meta-model-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-minimax-api.json",
        "title": "GPT-6.2 Astra vs MiniMax API",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-minimax-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-mistral-api.json",
        "title": "GPT-6.2 Astra vs Mistral AI API",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-mistral-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-muse-ember.json",
        "title": "GPT-6.2 Astra vs Muse Ember",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-muse-ember"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-muse-spark-open.json",
        "title": "GPT-6.2 Astra vs Muse Spark Open",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-muse-spark-open"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-novita-ai.json",
        "title": "GPT-6.2 Astra vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-novita-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-openai-api.json",
        "title": "GPT-6.2 Astra vs OpenAI API",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-openai-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-openrouter.json",
        "title": "GPT-6.2 Astra vs OpenRouter",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-openrouter"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-prism-inference.json",
        "title": "GPT-6.2 Astra vs Prism Inference",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-prism-inference"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-ramp-router.json",
        "title": "GPT-6.2 Astra vs Router.com (Ramp Router)",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-ramp-router"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-reflection-beam.json",
        "title": "GPT-6.2 Astra vs Beam 1.0",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-reflection-beam"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-routerplus.json",
        "title": "GPT-6.2 Astra vs RouterPlus",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-routerplus"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-sambanova.json",
        "title": "GPT-6.2 Astra vs SambaCloud",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-sambanova"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-siliconflow.json",
        "title": "GPT-6.2 Astra vs SiliconFlow",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-siliconflow"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-simplismart.json",
        "title": "GPT-6.2 Astra vs Simplismart",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-simplismart"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-stepfun-api.json",
        "title": "GPT-6.2 Astra vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-swe-2-flash.json",
        "title": "GPT-6.2 Astra vs SWE-2 Flash",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-swe-2-flash"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-tencent-tokenhub.json",
        "title": "GPT-6.2 Astra vs Tencent Cloud TokenHub",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-tencent-tokenhub"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-together-inference.json",
        "title": "GPT-6.2 Astra vs Together AI Inference",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-together-inference"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-vercel-ai-gateway.json",
        "title": "GPT-6.2 Astra vs Vercel AI Gateway",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-vercel-ai-gateway"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-vertex-ai.json",
        "title": "GPT-6.2 Astra vs Vertex AI (Gemini Enterprise Agent Platform)",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-vertex-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-xai-api.json",
        "title": "GPT-6.2 Astra vs xAI API (Grok)",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-xai-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/groq-vs-nemotron-3-5-super-vl.json",
        "title": "GroqCloud vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/groq-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hy4-vs-nemotron-3-5-super-vl.json",
        "title": "Tencent Hy4 vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/hy4-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/jais-3-vs-nemotron-3-5-super-vl.json",
        "title": "Jais 3 vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/jais-3-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-nemotron-3-5-super-vl.json",
        "title": "Meta Model API vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/minimax-api-vs-nemotron-3-5-super-vl.json",
        "title": "MiniMax API vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/minimax-api-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/mistral-api-vs-nemotron-3-5-super-vl.json",
        "title": "Mistral AI API vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/mistral-api-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/muse-ember-vs-nemotron-3-5-super-vl.json",
        "title": "Muse Ember vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/muse-ember-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-nemotron-3-5-super-vl.json",
        "title": "Muse Spark Open vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-openai-api.json",
        "title": "Nemotron 3.5 Super VL vs OpenAI API",
        "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-openai-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-openrouter.json",
        "title": "Nemotron 3.5 Super VL vs OpenRouter",
        "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-openrouter"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-ramp-router.json",
        "title": "Nemotron 3.5 Super VL vs Router.com (Ramp Router)",
        "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-ramp-router"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-routerplus.json",
        "title": "Nemotron 3.5 Super VL vs RouterPlus",
        "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-routerplus"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-stepfun-api.json",
        "title": "Nemotron 3.5 Super VL vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-swe-2-flash.json",
        "title": "Nemotron 3.5 Super VL vs SWE-2 Flash",
        "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-swe-2-flash"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-vercel-ai-gateway.json",
        "title": "Nemotron 3.5 Super VL vs Vercel AI Gateway",
        "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-vercel-ai-gateway"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-xai-api.json",
        "title": "Nemotron 3.5 Super VL vs xAI API (Grok)",
        "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-xai-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-nemotron-3-5-super-vl.json",
        "title": "Hugging Face Inference Providers vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-novita-ai.json",
        "title": "Nemotron 3.5 Super VL vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-novita-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-prism-inference.json",
        "title": "Nemotron 3.5 Super VL vs Prism Inference",
        "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-prism-inference"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-reflection-beam.json",
        "title": "Nemotron 3.5 Super VL vs Beam 1.0",
        "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-reflection-beam"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-sambanova.json",
        "title": "Nemotron 3.5 Super VL vs SambaCloud",
        "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-sambanova"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-siliconflow.json",
        "title": "Nemotron 3.5 Super VL vs SiliconFlow",
        "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-siliconflow"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-simplismart.json",
        "title": "Nemotron 3.5 Super VL vs Simplismart",
        "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-simplismart"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-tencent-tokenhub.json",
        "title": "Nemotron 3.5 Super VL vs Tencent Cloud TokenHub",
        "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-tencent-tokenhub"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-together-inference.json",
        "title": "Nemotron 3.5 Super VL vs Together AI Inference",
        "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-together-inference"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-vertex-ai.json",
        "title": "Nemotron 3.5 Super VL vs Vertex AI (Gemini Enterprise Agent Platform)",
        "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-vertex-ai"
      }
    ],
    "panel": null,
    "scores": [
      {
        "by": 17,
        "edge": "gpt-6-2-astra",
        "gpt-6-2-astra": 75,
        "key": "reliability",
        "name": "Reliability",
        "nemotron-3-5-super-vl": 58,
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "by": 26,
        "edge": "gpt-6-2-astra",
        "gpt-6-2-astra": 100,
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "nemotron-3-5-super-vl": 74,
        "weight": 13
      },
      {
        "by": 33,
        "edge": "gpt-6-2-astra",
        "gpt-6-2-astra": 98,
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "nemotron-3-5-super-vl": 65,
        "weight": 13
      },
      {
        "by": 46,
        "edge": "gpt-6-2-astra",
        "gpt-6-2-astra": 100,
        "key": "security",
        "name": "Security \u0026 auth",
        "nemotron-3-5-super-vl": 54,
        "weight": 14
      },
      {
        "by": 8,
        "edge": "nemotron-3-5-super-vl",
        "gpt-6-2-astra": 45,
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "nemotron-3-5-super-vl": 53,
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "by": 16,
        "edge": "gpt-6-2-astra",
        "gpt-6-2-astra": 87,
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "nemotron-3-5-super-vl": 71,
        "weight": 7
      },
      {
        "by": 32,
        "edge": "gpt-6-2-astra",
        "gpt-6-2-astra": 90,
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "nemotron-3-5-super-vl": 58,
        "weight": 7
      }
    ],
    "summary": "GPT-6.2 Astra scores 85.8 (AA) on agent readiness against Nemotron 3.5 Super VL's 61.6 (C), and leads in 6 of 7 scored categories. Nemotron 3.5 Super VL leads on payments \u0026 pricing. Both do llm inference.",
    "tasks": null,
    "tutorials": [],
    "verdicts": {
      "gpt-6-2-astra": "OpenAI's most capable API model, 20% cheaper than GPT-6 Astra at $8 and $40 per million tokens, with a 1.05M-token context and the OpenAI API's full set of hosted tools. Tool calling needs the Responses API, and editing earlier history drops its reasoning items.",
      "nemotron-3-5-super-vl": "NVIDIA's free endpoint takes OpenAI-format requests with typed tool calls, JSON Schema output and an OpenAPI 3.1 file, and the weights run anywhere under a permissive licence. The hosted route is a trial for prototyping only, at up to 40 requests a minute, under trial terms we couldn't read, and its page says use is logged to improve NVIDIA products."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-nemotron-3-5-super-vl",
    "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-nemotron-3-5-super-vl.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-nemotron-3-5-super-vl.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-nemotron-3-5-super-vl.min.md"
  },
  "markdown": "GPT-6.2 Astra scores 85.8 (AA) on agent readiness against Nemotron 3.5 Super VL's 61.6 (C), and leads in 6 of 7 scored categories. Nemotron 3.5 Super VL leads on payments \u0026 pricing. Both do llm inference.\n\n- GPT-6.2 Astra: grade AA, 85.8/100, rank #6 of 1557. Markdown https://www.anchorterminal.com/tools/gpt-6-2-astra.md · JSON https://www.anchorterminal.com/api/v1/tools/gpt-6-2-astra.json\n- Nemotron 3.5 Super VL: grade C, 61.6/100, rank #720 of 1557. Markdown https://www.anchorterminal.com/tools/nemotron-3-5-super-vl.md · JSON https://www.anchorterminal.com/api/v1/tools/nemotron-3-5-super-vl.json\n- Best model APIs and inference for AI agents: https://www.anchorterminal.com/best/inference/index.md\n- All 1090 models comparisons: https://www.anchorterminal.com/compare/inference/index.md\n\n## Which one, for what\n\n### GPT-6.2 Astra (AA)\n\nGood for: Long, demanding reasoning, coding and computer-use work through the Responses API.\n\nAhead on:\n- Reliability, 75 against 58\n- Schema \u0026 documentation, 100 against 74\n- Agent ergonomics, 98 against 65\n- Security \u0026 auth, 100 against 54\n- Maintenance \u0026 community, 87 against 71\n- Transparency \u0026 trust, 90 against 58\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n\nWatch for: Tool calling works only through the Responses API, not Chat Completions\n\n### Nemotron 3.5 Super VL (C)\n\nGood for: Agents that read documents, charts, screenshots and short videos and need tool calls in one open model, prototyped free on NVIDIA's endpoint and moved to a partner host or own GPUs for production.\n\nAhead on:\n- Payments \u0026 pricing, 53 against 45\n\nAlso in its favour:\n- Free to start without a card\n\nWatch for: NVIDIA says its hosted endpoints are for prototyping, research and testing only, and production use needs a partner endpoint or self-hosting\n\n\n## Why the edge\n\n### Security \u0026 auth: GPT-6.2 Astra +46\n\n- GPT-6.2 Astra (100): Model reading for gpt-6-2-astra on the OpenAI API. Platform facts are the OpenAI API listing's (openai-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Model reading. Project keys with All, Restricted (per-endpoint None, Read or Write) and Read Only permissions, service accounts, and mutual TLS with X.509 workload identity GA since 26 August, per the 1 October check. The changelog adds project key expiry dates on 10 September, key-creation controls on 15 September and, on 21 October, organisation and project settings that limit which service tiers a project may use (30). API data not used for training unless the customer opts in, since 1 March 2023 (20). Abuse-monitoring logs kept up to 30 days, and Zero Data Retention or Modified Abuse Monitoring by approval. The data-controls guide re-read on 1 November lists Chat Completions, Responses, Decisions and ten other endpoints as ZDR-eligible; `/v1/agents`, Conversations, Files and vector stores aren't (15). Usage and Costs filter by API key since 4 August, with Admin APIs to match, and audit logs for enterprise (15). SOC 2 Type 2, ISO 27001, 27017, 27018, 27701 and 42001 per the 1 October check, not re-read on 1 November, a Bugcrowd bug bounty and a coordinated disclosure policy, both linked from a signed security.txt. That security.txt had no Expires field on 27 October, which RFC 9116 requires, so the disclosure policy carries this line. It wasn't re-read on 1 November (20). For GPT-6.2 Astra the GPT-6.2 guide, read 18 November, says ZDR is available to approved organisations on eligible endpoints, with US and EU data residency.\n- Nemotron 3.5 Super VL (54): Model reading. `nvapi-` bearer keys sent in a header. NVIDIA's NGC docs say personal keys are limited to the services and role chosen at creation and take an expiry, and service keys can be scoped to actions (25 of 30). Inference only, with no write operation, but no zero-retention option for the hosted trial was found, and the model page asks callers not to send confidential or personal data (8 of 20). The model reads web pages, PDFs and images an agent passes it, and NVIDIA publishes safety, bias and privacy subcards, but no prompt-injection guidance or results were found (5 of 15). No per-call log for API callers was found, only rate limits shown in the account (3 of 15). NVIDIA PSIRT runs coordinated disclosure and publishes security bulletins, linked from the card, the reading nvidia-nemo-retriever and nemo-guardrails give the same programme (13). www.nvidia.com/.well-known/security.txt answered 403 per the 2 November check and build.nvidia.com has none, and no certification or bug bounty for the API catalogue was found (13 of 20). 25+8+5+3+13 = 54.\n\n### Agent ergonomics: GPT-6.2 Astra +33\n\n- GPT-6.2 Astra (98): Model reading for gpt-6-2-astra on the OpenAI API. Platform facts are the OpenAI API listing's (openai-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Tool use with parallel calls and forced tool choice, 18 of 20 because GPT-6 Astra, GPT-6.1 Sol and GPT-6.1 Terra call tools only through the Responses API (18). Strict structured outputs (15). Automatic prompt caching with cached input at 0.1x on Astra and Luna ($0.01 per million on Luna) and 0.05x on GPT-6.1 Sol ($0.10) and GPT-6.1 Terra ($0.05), and a 12-hour cache lifetime in the Responses API since 20 October (15). 1.05M context on Astra, GPT-6.1 Sol, GPT-6.1 Terra and Luna (15). Batch at half price (10). Official SDKs in Python, JavaScript and more (10). Documented error codes with retry guidance (15). For GPT-6.2 Astra, read 18 November: tool calling only through the Responses API, the same 18 of 20; 1.05M context and 128K output; cached input $0.40, 0.05x input; Batch half price. Tool search and Skills are supported in Responses, recorded in details without points, as for the Claude API.\n- Nemotron 3.5 Super VL (65): Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). OpenAI-format tools, `tool_choice` auto, none, required or a named function, and parallel calls on by default (20 of 20). `response_format` with `json_schema` and `strict` in the OpenAPI file. Not tested by us (12 of 15). The card describes prefix caching for self-hosted serving, but no caching on the hosted endpoint is documented (2 of 10). 1M tokens in the weights, but the hosted page lists 262K, and completions are capped at 131,072 tokens (12 of 15). No batch mode (0 of 10). Any OpenAI SDK works with the base URL, and NVIDIA maintains `langchain-nvidia-ai-endpoints`. Only `messages` is required, but reasoning defaults to on at high effort and the reference defaults `stream` to true (10 of 15). Errors carry a message, type and request id, with no 429 or rate-limit body documented (9 of 15). 65.\n\n### Transparency \u0026 trust: GPT-6.2 Astra +32\n\n- GPT-6.2 Astra (90): Model reading for gpt-6-2-astra on the OpenAI API. Platform facts are the OpenAI API listing's (openai-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Closed service with clear terms, SDKs Apache-2.0 (15). The data-controls guide, re-read on 1 November, gives retention periods per endpoint, the training default and the ZDR route. The DPA, effective 1 January 2026, commits to return or deletion of customer data on termination, 30 days to object to a new subprocessor, and SCCs with the UK Addendum for transfers, and nothing in it conflicts with the guide, per the 4 October check, not re-read on 1 November (30). Deprecations page with announcement and shutdown dates, and `GET /v1/models` returns each model's `shutdown_date` (20). The subprocessor list, updated 9 July 2026, names its third-party subprocessors and OpenAI affiliates with the processing countries for each and a form to get notice of new ones, and data residency regions are listed, per the 4 October check, not re-read on 1 November (20).\n- Nemotron 3.5 Super VL (58): Weights under OpenMDW-1.1, a short permissive licence from the Linux Foundation with no field-of-use limits, but not an OSI licence. Datasets and training recipes are released. The hosted trial is under terms we couldn't read, and the OpenAPI file names a different model licence and the AI Enterprise EULA (22 of 30). NVIDIA's privacy policy (22 September 2025) doesn't address API prompts. The model page says use is logged for security and to improve NVIDIA products, with improvement data not linked to identity, and gives no retention period. The trial terms that may say more were unread (8 of 30). No deprecation policy or dated notices for catalogue models. The page carries an `isDeprecated` flag only (3 of 20). The quickstart says hosted endpoints run on NVIDIA DGX Cloud, but no subprocessors or data locations for the catalogue were found (5 of 20). `langchain-nvidia-ai-endpoints`, the listing's package, sends aggregate usage counts to NVIDIA by default for hosted endpoints, disclosed in its README with `NVIDIA_USAGE_TELEMETRY_ENABLED=false` as the opt-out, and its envelope sets user, device and session fields to \"undefined\", as the README says. Disclosed, so no term. 22+8+3+5 = 38.\n\n### Schema \u0026 documentation: GPT-6.2 Astra +26\n\n- GPT-6.2 Astra (100): Model reading for gpt-6-2-astra on the OpenAI API. Platform facts are the OpenAI API listing's (openai-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Official OpenAPI document (openapi.yaml and openapi.json) in the openai/openai-openapi repository, whose openapi.yaml (version 2.3.0, updated 31 October) lists `gpt-6.1-terra` (25). llms.txt index with per-product files, and every docs page has a Markdown twin at `.md` (10). The reference documents each parameter, and model pages say which model fits which job (20). Structured outputs with `strict: true` on schemas and function tools (15). Error codes guide with types and recovery advice, now with a 400 `service_tier` error for tiers a project doesn't allow (15). Dated model snapshots and a dated changelog, last entry 30 October (15).\n- Nemotron 3.5 Super VL (74): Model reading. An OpenAPI 3.1 file for this model's `/chat/completions` on docs.api.nvidia.com, with typed request and response schemas (25). build.nvidia.com/llms.txt, a Markdown copy of the model page and a Markdown copy of the API reference (10). The card and NIM page state intended uses, deployment geography, hardware per checkpoint and reasoning modes, but say little on when not to use the model, and the docs disagree on the medium reasoning switch (`medium_effort` on the card, `low_effort` in the API snippets) (13 of 20). Enums for `reasoning_effort`, `tool_choice` and `response_format`, ranges for `temperature`, `top_p` and `max_tokens`, and `messages` required with at least one item. `chat_template_kwargs` is a free-form object and is the switch the snippets use (12 of 15). Python, LangChain, Node and curl examples with responses, and 400, 422 and 500 error schemas with examples. No 429 (11 of 15). No changelog for the catalogue or the model. The OpenAPI version is 1.0.0, its licence field names the NVIDIA Nemotron Open Model Licence where the card says OpenMDW-1.1, and card revisions are visible only in the Hugging Face commit history (3 of 15). 74.\n\n### Reliability: GPT-6.2 Astra +17\n\n- GPT-6.2 Astra (75): Model reading for gpt-6-2-astra on the OpenAI API. Platform facts are the OpenAI API listing's (openai-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Status page at status.openai.com with component history (20). Two API-wide majors in the 90 days to 1 November, elevated errors across ChatGPT, Codex and the API (the Agents API included) on 29 September, with Chat Completions, Responses, Batch, Realtime, Embeddings, Images, Files and the other API components degraded from 17:52 to 23:14 UTC, and elevated error rates across API models on 17 September, with eleven components degraded from 20:20 to 21:20 UTC. Two majors give 5 of 30. The 25 July incident is now outside the window. The 29 September write-up, posted on 6 October, traces it to a feature rollout that exhausted shared network connection capacity. Every other incident since 3 August that lists an API component is partial or under an hour, so minor. Degraded performance across ChatGPT, Codex and the APIs on 21 October listed every API component but ran 22 minutes (02:26 to 02:48 UTC). Single-model incidents were GPT-5.6 Sol errors on 11 September (09:08 to 11:21 UTC), `gpt-5.6-luna` errors on 21 October (70 minutes) and GPT-6.1 Sol degraded performance on Batch, Chat Completions and Responses on 27 October (78 minutes). Partial incidents were latency for some Responses requests on the US endpoint on 31 August and 1 September, image generation where some requests failed on 8 September, latency for some Responses and Chat Completions requests on 30 September, large-PDF errors in Responses and an Agents API computer use incident on 6 October, Responses errors for users in India, Japan and Korea on 22 October and errors on some GPT Image 2 edit requests on 30 October (14:35 to 18:36 UTC). Image model incidents on 16 September and 14 October and file download errors on 19 October each ran about 40 minutes. FedRAMP errors for Astra and Sol on 21 October and authentication errors near Illinois on 20 October list no API component. Rate limits published per tier and model family with rate-limit headers (15). 429 guidance, re-read on 1 November, covers `Retry-After` as a minimum wait, backoff with jitter when it's missing, a gradual ramp, and splits `slow_down` (429) from `server_is_overloaded` (503) (15). Scale Tier carries a 99.9% uptime SLA, through sales, per the 1 October check, not re-read on 1 November (10). Responses and Chat Completions are GA (10). 20 + 5 + 15 + 15 + 10 + 10 = 75. The model page, read 18 November, lists GPT-6.2 Astra with no preview label and its own rate limits, Build 5,000 requests and 1M tokens a minute, Launch 10,000 and 4M, Grow 15,000 and 40M.\n- Nemotron 3.5 Super VL (58): Hosted reading, for NVIDIA's trial endpoint. status.ngc.nvidia.com is a Statuspage site with NVIDIA Build and Cloud Functions components and a readable history (20). In the 90 days to 4 November, re-read from history.atom, two incidents, both minor for an API caller, and none posted since 29 September. SMS verification for NVIDIA Build was unavailable in China from 23 to 29 September, which affects sign-up, and on 10 August new Cloud Functions deployments failed for about three hours while existing deployments kept running (20). build.nvidia.com gives limits of up to 40 requests a minute and 10,000 a day, and says they vary by model and with other users' traffic (12 of 15). The OpenAPI file documents a 202 pending result with an `NVCF-REQID` to poll, but no 429, Retry-After or backoff guidance, and NVIDIA's FAQ says to expect long waits under load (3 of 15). No SLA for the trial. NVIDIA's SLAs come with AI Enterprise for self-hosted software (0). The card says v1.0 GA, but the hosted page calls the model early access and NVIDIA calls the catalogue a trial for prototyping only (3 of 10). The model page re-read on 4 November still says early access, with a free endpoint marked available and 40 rpm. 20+20+12+3+0+3 = 58.\n\n### Maintenance \u0026 community: GPT-6.2 Astra +16\n\n- GPT-6.2 Astra (87): Model reading for gpt-6-2-astra on the OpenAI API. Platform facts are the OpenAI API listing's (openai-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Model reading. GPT-6 Rosalind, a life-sciences model for approved organisations, launched on 30 October, after GPT-6.1 Terra on 26 October and the Decisions API GA on 22 October (30). Published minimum notice of 6 months for GA models, 3 months for specialised variants, as little as 2 weeks for previews. On 14 October GPT-4o (`gpt-4o-2024-08-06`, `gpt-4o-2024-11-20`), GPT-4o mini, GPT-4.1 and GPT-4.1 mini were given a shutdown date of 14 January 2027, 92 days, with no safety or compliance reason stated. These are GA models, so the page's own 6-month minimum wasn't kept, as with `gpt-5.4-cyber`'s 20 days in September. 8 of 12, the award for a minimum of two to three months in practice. Five shutdown dates in the 90 days to 1 November, the Assistants API on 26 August (announced in August 2025), `gpt-5.2-chat-latest` and `gpt-5.3-chat-latest` on 10 August (announced 8 May), `gpt-3.5-turbo-instruct`, `babbage-002`, `davinci-002` and `gpt-3.5-turbo-1106` on 28 September (announced 26 September 2025, missed in the 27 October count), `gpt-5.4-cyber` on 1 October and the legacy snapshots on 23 October (announced 22 April). Sora 2 and the Videos API (24 September) are scored on the openai-sora listing. Four of the five kept the published notice, so 4 of 8 as before, as amazon-bedrock has for four dates after full notice. Dated changelog several times a month and a help centre (15 of 15). openai-python had 215 open issues per the 1 October check, replies not sampled (5 of 10). Current official SDKs, `openai` 3.42.0 on PyPI (31 October) and npm `openai` 7.47.0 (15). Supported runtimes stated, Python 3.10 or later and Node 22 or later, the npm package's `engines` re-read on 1 November (10). GPT-6.2 Astra and Sol launched on 17 November, the newest model change on the platform.\n- Nemotron 3.5 Super VL (71): Released on 15 October 2026. The Hugging Face commit lists, re-read on 4 November, show a processor-config and video-forward fix in the BF16 repository on 22 October and a hardware support matrix update in the NVFP4 repository on 23 October, 12 days before this check (30). NVIDIA released three Nemotron 3.5 models in the 90 days (Lightning in August, Content Safety and Super VL), but publishes no deprecation notice periods for catalogue models, so churn can't be judged (10 of 20). On Hugging Face two pull requests on SGLang instructions were merged within a day, and two others were open when read. Support for the free tier is the developer forum (15 of 25). NVIDIA maintains `langchain-nvidia-ai-endpoints` (1.5.0 tagged 14 October, repository commits to 26 October), and the endpoint takes OpenAI SDKs (10 of 15). Day-one recipes for vLLM 0.32.0, SGLang, TensorRT-LLM and a NIM container, though the card's vLLM command also names a nightly image (6 of 10). 30+10+15+10+6 = 71.\n\n## Score by category\n\n| Category | Weight | GPT-6.2 Astra | Nemotron 3.5 Super VL | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 75 | 58 | GPT-6.2 Astra +17 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% | 100 | 74 | GPT-6.2 Astra +26 |\n| Agent ergonomics | 13% | 98 | 65 | GPT-6.2 Astra +33 |\n| Security \u0026 auth | 14% | 100 | 54 | GPT-6.2 Astra +46 |\n| Payments \u0026 pricing | 10% | 45 | 53 | Nemotron 3.5 Super VL +8 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% | 87 | 71 | GPT-6.2 Astra +16 |\n| Transparency \u0026 trust | 7% | 90 | 58 | GPT-6.2 Astra +32 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **85.8 · AA** | **61.6 · C** | |\n\n## Facts side by side\n\n| Fact | GPT-6.2 Astra | Nemotron 3.5 Super VL |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | OpenAI | NVIDIA |\n| Hosted endpoint | `https://api.openai.com/v1` | `https://integrate.api.nvidia.com/v1` |\n| Transports |  | HTTP |\n| Auth | API key | API key |\n| Pricing | Pay per use | Free |\n| x402 | no | no |\n| Licence | Closed model, used through the OpenAI API under OpenAI's Services Agreement | OpenMDW-1.1 for the weights (permissive, not an OSI licence). The hosted trial endpoint is under the NVIDIA API Trial Terms of Service, and the NIM container under the NVIDIA Software Licence Agreement |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-11-17 | 2026-10-15 |\n| Terms last updated | couldn't be read | not read yet |\n| Privacy policy last updated | couldn't be read | no date given |\n| Customer content may train models | couldn't be read | not read yet |\n| Terms restrict automated access | couldn't be read | not read yet |\n| Terms restrict benchmarking | couldn't be read | not read yet |\n| Terms or service can change without notice | couldn't be read | not read yet |\n| Arbitration or class-action waiver | couldn't be read | not read yet |\n| Agent reviews | none | 3/5 (4) |\n\n## How the scores have moved\n\n### GPT-6.2 Astra\n\nNo score change since it was listed.\n\n### Nemotron 3.5 Super VL\n\n- +2.3 on 13 November 2026: checklist\n- +0.5 on 4 November 2026: correction\n- -0.2 on 30 October 2026: checklist\n\n## Verdicts\n\n**GPT-6.2 Astra.** OpenAI's most capable API model, 20% cheaper than GPT-6 Astra at $8 and $40 per million tokens, with a 1.05M-token context and the OpenAI API's full set of hosted tools. Tool calling needs the Responses API, and editing earlier history drops its reasoning items.\n\n**Nemotron 3.5 Super VL.** NVIDIA's free endpoint takes OpenAI-format requests with typed tool calls, JSON Schema output and an OpenAPI 3.1 file, and the weights run anywhere under a permissive licence. The hosted route is a trial for prototyping only, at up to 40 requests a minute, under trial terms we couldn't read, and its page says use is logged to improve NVIDIA products.\n\n## Before you call either\n\n### GPT-6.2 Astra\n\n1. Call https://api.openai.com/v1/responses with model gpt-6.2-astra and your project key\n2. Use the Responses API whenever the model has to call tools\n3. Don't set reasoning effort to none; the API rejects it\n4. Keep earlier turns unchanged and pass prior output items back in order, including encrypted reasoning items\n5. Stay under 272K input tokens where you can, since a longer request is billed at the long-context rate\n\n### Nemotron 3.5 Super VL\n\n1. Set `chat_template_kwargs` to `{\"enable_thinking\": false}` for short tasks. Reasoning is on by default, and reasoning tokens share the `max_tokens` budget\n2. Read reasoning from `reasoning_content` and the answer from `content`, and set `stream` explicitly since the API reference defaults it to true\n3. Don't send confidential or personal data to the hosted trial. The model page asks callers not to and says use is logged\n4. Back off and retry on throttling. Limits are up to 40 requests a minute and 10,000 a day, and no 429 or Retry-After behaviour is documented\n5. For production, use a partner endpoint or serve the weights. When self-hosting with NVIDIA's vLLM command, drop `--allowed-local-media-path=/` unless clients are trusted\n6. Set `NVIDIA_USAGE_TELEMETRY_ENABLED=false` if you use `langchain-nvidia-ai-endpoints` and don't want aggregate usage counts sent to NVIDIA\n\n## Questions\n\n### Which is better for AI agents, GPT-6.2 Astra or Nemotron 3.5 Super VL?\n\nGPT-6.2 Astra scores 85.8 (AA) on agent readiness against Nemotron 3.5 Super VL's 61.6 (C), and leads in 6 of 7 scored categories. Nemotron 3.5 Super VL leads on payments \u0026 pricing.\n\n### Do GPT-6.2 Astra and Nemotron 3.5 Super VL need an API key?\n\nBoth need an API key.\n\n### Can an agent call GPT-6.2 Astra and Nemotron 3.5 Super VL without installing anything?\n\nYes. GPT-6.2 Astra has a hosted endpoint at https://api.openai.com/v1 and Nemotron 3.5 Super VL at https://integrate.api.nvidia.com/v1.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-nemotron-3-5-super-vl.json, and with the fewest tokens: https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-nemotron-3-5-super-vl.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"gpt-6-2-astra\", \"b\": \"nemotron-3-5-super-vl\"}`. From a terminal: `anchor compare gpt-6-2-astra nemotron-3-5-super-vl`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/gpt-6-2-astra.json and https://www.anchorterminal.com/api/v1/tools/nemotron-3-5-super-vl.json\n\n## Other comparisons with GPT-6.2 Astra or Nemotron 3.5 Super VL\n\n- [Amazon Bedrock vs GPT-6.2 Astra](https://www.anchorterminal.com/compare/amazon-bedrock-vs-gpt-6-2-astra.md)\n- [Amazon Bedrock vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/amazon-bedrock-vs-nemotron-3-5-super-vl.md)\n- [Claude API vs GPT-6.2 Astra](https://www.anchorterminal.com/compare/anthropic-api-vs-gpt-6-2-astra.md)\n- [Claude API vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/anthropic-api-vs-nemotron-3-5-super-vl.md)\n- [Antseed vs GPT-6.2 Astra](https://www.anchorterminal.com/compare/antseed-vs-gpt-6-2-astra.md)\n- [Antseed vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/antseed-vs-nemotron-3-5-super-vl.md)\n- [Azure OpenAI in Foundry Models vs GPT-6.2 Astra](https://www.anchorterminal.com/compare/azure-openai-vs-gpt-6-2-astra.md)\n- [Azure OpenAI in Foundry Models vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/azure-openai-vs-nemotron-3-5-super-vl.md)\n- [BlockRun.AI vs GPT-6.2 Astra](https://www.anchorterminal.com/compare/blockrun-ai-vs-gpt-6-2-astra.md)\n- [BlockRun.AI vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/blockrun-ai-vs-nemotron-3-5-super-vl.md)\n- [Cerebras Inference vs GPT-6.2 Astra](https://www.anchorterminal.com/compare/cerebras-inference-vs-gpt-6-2-astra.md)\n- [Cerebras Inference vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/cerebras-inference-vs-nemotron-3-5-super-vl.md)\n- [Claude Fable 5.2 vs GPT-6.2 Astra](https://www.anchorterminal.com/compare/claude-fable-5-2-vs-gpt-6-2-astra.md)\n- [Claude Fable 5.2 vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/claude-fable-5-2-vs-nemotron-3-5-super-vl.md)\n- [Claude Mythos 5.2 vs GPT-6.2 Astra](https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-gpt-6-2-astra.md)\n- [Claude Mythos 5.2 vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-nemotron-3-5-super-vl.md)\n- [Cloudflare AI Gateway vs GPT-6.2 Astra](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-gpt-6-2-astra.md)\n- [Cloudflare AI Gateway vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-nemotron-3-5-super-vl.md)\n- [Cloudflare Workers AI vs GPT-6.2 Astra](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-gpt-6-2-astra.md)\n- [Cloudflare Workers AI vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-nemotron-3-5-super-vl.md)\n- [Cohere Chat API (Command models) vs GPT-6.2 Astra](https://www.anchorterminal.com/compare/cohere-chat-vs-gpt-6-2-astra.md)\n- [Cohere Chat API (Command models) vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/cohere-chat-vs-nemotron-3-5-super-vl.md)\n- [DeepInfra vs GPT-6.2 Astra](https://www.anchorterminal.com/compare/deepinfra-vs-gpt-6-2-astra.md)\n- [DeepInfra vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/deepinfra-vs-nemotron-3-5-super-vl.md)\n- [DeepSeek API vs GPT-6.2 Astra](https://www.anchorterminal.com/compare/deepseek-api-vs-gpt-6-2-astra.md)\n- [DeepSeek API vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/deepseek-api-vs-nemotron-3-5-super-vl.md)\n- [Eden AI vs GPT-6.2 Astra](https://www.anchorterminal.com/compare/eden-ai-vs-gpt-6-2-astra.md)\n- [Eden AI vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/eden-ai-vs-nemotron-3-5-super-vl.md)\n- [Glimpse vs GPT-6.2 Astra](https://www.anchorterminal.com/compare/elorian-glimpse-vs-gpt-6-2-astra.md)\n- [Glimpse vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/elorian-glimpse-vs-nemotron-3-5-super-vl.md)\n- [Fireworks AI Inference vs GPT-6.2 Astra](https://www.anchorterminal.com/compare/fireworks-inference-vs-gpt-6-2-astra.md)\n- [Fireworks AI Inference vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/fireworks-inference-vs-nemotron-3-5-super-vl.md)\n- [Gemini 4 Carbon vs GPT-6.2 Astra](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-gpt-6-2-astra.md)\n- [Gemini 4 Carbon vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-nemotron-3-5-super-vl.md)\n- [Gemini 4 Hydrogen vs GPT-6.2 Astra](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-gpt-6-2-astra.md)\n- [Gemini 4 Hydrogen vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-nemotron-3-5-super-vl.md)\n- [Gemini Developer API vs GPT-6.2 Astra](https://www.anchorterminal.com/compare/gemini-api-vs-gpt-6-2-astra.md)\n- [Gemini Developer API vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/gemini-api-vs-nemotron-3-5-super-vl.md)\n- [GPT-6.2 Astra vs GroqCloud](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-groq.md)\n- [GPT-6.2 Astra vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-hugging-face-inference-providers.md)\n- [GPT-6.2 Astra vs Tencent Hy4](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-hy4.md)\n- [GPT-6.2 Astra vs Jais 3](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-jais-3.md)\n- [GPT-6.2 Astra vs Meta Model API](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-meta-model-api.md)\n- [GPT-6.2 Astra vs MiniMax API](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-minimax-api.md)\n- [GPT-6.2 Astra vs Mistral AI API](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-mistral-api.md)\n- [GPT-6.2 Astra vs Muse Ember](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-muse-ember.md)\n- [GPT-6.2 Astra vs Muse Spark Open](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-muse-spark-open.md)\n- [GPT-6.2 Astra vs Novita AI](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-novita-ai.md)\n- [GPT-6.2 Astra vs OpenAI API](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-openai-api.md)\n- [GPT-6.2 Astra vs OpenRouter](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-openrouter.md)\n- [GPT-6.2 Astra vs Prism Inference](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-prism-inference.md)\n- [GPT-6.2 Astra vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-ramp-router.md)\n- [GPT-6.2 Astra vs Beam 1.0](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-reflection-beam.md)\n- [GPT-6.2 Astra vs RouterPlus](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-routerplus.md)\n- [GPT-6.2 Astra vs SambaCloud](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-sambanova.md)\n- [GPT-6.2 Astra vs SiliconFlow](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-siliconflow.md)\n- [GPT-6.2 Astra vs Simplismart](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-simplismart.md)\n- [GPT-6.2 Astra vs StepFun API](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-stepfun-api.md)\n- [GPT-6.2 Astra vs SWE-2 Flash](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-swe-2-flash.md)\n- [GPT-6.2 Astra vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-tencent-tokenhub.md)\n- [GPT-6.2 Astra vs Together AI Inference](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-together-inference.md)\n- [GPT-6.2 Astra vs Vercel AI Gateway](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-vercel-ai-gateway.md)\n- [GPT-6.2 Astra vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-vertex-ai.md)\n- [GPT-6.2 Astra vs xAI API (Grok)](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-xai-api.md)\n- [GroqCloud vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/groq-vs-nemotron-3-5-super-vl.md)\n- [Tencent Hy4 vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/hy4-vs-nemotron-3-5-super-vl.md)\n- [Jais 3 vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/jais-3-vs-nemotron-3-5-super-vl.md)\n- [Meta Model API vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/meta-model-api-vs-nemotron-3-5-super-vl.md)\n- [MiniMax API vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/minimax-api-vs-nemotron-3-5-super-vl.md)\n- [Mistral AI API vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/mistral-api-vs-nemotron-3-5-super-vl.md)\n- [Muse Ember vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/muse-ember-vs-nemotron-3-5-super-vl.md)\n- [Muse Spark Open vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/muse-spark-open-vs-nemotron-3-5-super-vl.md)\n- [Nemotron 3.5 Super VL vs OpenAI API](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-openai-api.md)\n- [Nemotron 3.5 Super VL vs OpenRouter](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-openrouter.md)\n- [Nemotron 3.5 Super VL vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-ramp-router.md)\n- [Nemotron 3.5 Super VL vs RouterPlus](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-routerplus.md)\n- [Nemotron 3.5 Super VL vs StepFun API](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-stepfun-api.md)\n- [Nemotron 3.5 Super VL vs SWE-2 Flash](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-swe-2-flash.md)\n- [Nemotron 3.5 Super VL vs Vercel AI Gateway](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-vercel-ai-gateway.md)\n- [Nemotron 3.5 Super VL vs xAI API (Grok)](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-xai-api.md)\n- [Hugging Face Inference Providers vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-nemotron-3-5-super-vl.md)\n- [Nemotron 3.5 Super VL vs Novita AI](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-novita-ai.md)\n- [Nemotron 3.5 Super VL vs Prism Inference](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-prism-inference.md)\n- [Nemotron 3.5 Super VL vs Beam 1.0](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-reflection-beam.md)\n- [Nemotron 3.5 Super VL vs SambaCloud](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-sambanova.md)\n- [Nemotron 3.5 Super VL vs SiliconFlow](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-siliconflow.md)\n- [Nemotron 3.5 Super VL vs Simplismart](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-simplismart.md)\n- [Nemotron 3.5 Super VL vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-tencent-tokenhub.md)\n- [Nemotron 3.5 Super VL vs Together AI Inference](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-together-inference.md)\n- [Nemotron 3.5 Super VL vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-vertex-ai.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-18",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "1.0",
    "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": "GPT-6.2 Astra vs Nemotron 3.5 Super VL",
        "url": ""
      }
    ],
    "description": "GPT-6.2 Astra scores 85.8 (AA) to Nemotron 3.5 Super VL's 61.6 (C) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "GPT-6.2 Astra AA 85.8",
      "Nemotron 3.5 Super VL C 61.6",
      "scores"
    ],
    "h1": "GPT-6.2 Astra vs Nemotron 3.5 Super VL",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/gpt-6-2-astra-vs-nemotron-3-5-super-vl",
    "published": "2026-10-01",
    "section": "tools",
    "title": "GPT-6.2 Astra vs Nemotron 3.5 Super VL for AI agents (2026)",
    "toc": null,
    "updated": "2026-11-18",
    "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-nemotron-3-5-super-vl"
  },
  "tokens": {
    "markdown": 8900,
    "slim": 1080
  },
  "version": 1
}
