{
  "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 Novita AI's 56.1 (C), and leads in 6 of 7 scored categories. Novita AI leads on payments \u0026 pricing.",
    "b": {
      "slug": "novita-ai",
      "name": "Novita AI",
      "vendor": "Novita AI",
      "vendorUrl": "https://novita.ai",
      "company": "novita.ai",
      "kind": "model",
      "category": "inference",
      "summary": "Novita AI is a hosted inference API for open-weight language models, with embeddings, reranking, image, video and speech models on the same key. It answers OpenAI-style calls at api.novita.ai with a Bearer key.",
      "url": "https://www.anchorterminal.com/tools/novita-ai",
      "markdownUrl": "https://www.anchorterminal.com/tools/novita-ai.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/novita-ai.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/novita-ai.json",
      "dns": "novita-ai.grade.anchorterminal.com",
      "repo": "https://github.com/novitalabs/novita-skills",
      "license": "Proprietary service under the Novita AI Terms of Service. The agent skill and the MCP server are MIT",
      "transports": [
        "http"
      ],
      "remoteUrl": "https://api.novita.ai/openai",
      "packages": [
        {
          "registry": "npm",
          "name": "novita-sdk"
        },
        {
          "registry": "pypi",
          "name": "novita-client"
        },
        {
          "registry": "npm",
          "name": "@novitalabs/novita-mcp-server"
        }
      ],
      "auth": "api-key",
      "authNotes": "Self-serve Bearer key from Key Management in the console after a browser sign-up. Keys start with `sk_`, are shown once, number up to 10 an account and take an expiry of 24 hours, 30 days, 90 days or none. A per-key model access policy and source IP allowlist can be set by API. `auth.md` also describes OAuth with PKCE after the user signs in and approves (https://docs.novita.ai/guides/llm-api-keys, https://novita.ai/auth.md).",
      "pricing": "usage",
      "pricingNotes": "Pay per token from prepaid credit. `deepseek/deepseek-v4.1-flash` costs $0.30 in and $1.20 out per 1M tokens, batch is 50 per cent off as an introductory price, and two models are listed as free. A voucher for new users is described without an amount, and whether a card is needed was not found (https://novita.ai/pricing, checked 2026-10-09).",
      "priceSummary": "from $0.05 / 1M in",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the docs index, the docs site map, the pricing page or the skill repository (checked 2026-10-09).",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": 6,
        "npmWeekly": 1363,
        "pypiWeekly": null,
        "asOf": "2026-10-09"
      },
      "docsUrl": "https://docs.novita.ai/guides/introduction",
      "rateLimitsUrl": "https://docs.novita.ai/guides/llm-rate-limits",
      "llmsTxt": "https://docs.novita.ai/llms.txt",
      "openapi": "https://novita.ai/.well-known/openapi.json",
      "capabilities": [
        "inference.llm",
        "inference.open-weights",
        "embed.text",
        "rerank",
        "image.generate",
        "video.generate",
        "speech.tts",
        "compute.batch"
      ],
      "tags": [
        "hosted",
        "model",
        "open-weights",
        "usage-based",
        "llms-txt",
        "openai-compatible",
        "batch",
        "prompt-caching",
        "changelog"
      ],
      "lastRelease": "2026-10-22",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 56.1,
        "grade": "C",
        "agentReady": false,
        "rank": 956,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 36,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 72,
          "maintenance": 66,
          "payments": 53,
          "reliability": 28,
          "schema": 62,
          "security": 65,
          "transparency": 57
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-04"
        },
        "negative": 0,
        "verdict": "Per-token prices for about 140 language models are public, and each key can carry an expiry, a model allowlist and a source IP allowlist. No status page, SLA or security.txt was found, the per-model rate limit figures are drawn by script, and both vendor SDK repositories are archived while the docs still point to them.",
        "bestFor": "Agents that want many open-weight models at per-token prices behind one OpenAI-style key, with keys that can be limited by model, IP and expiry.",
        "strengths": [
          "API keys take an expiry of 24 hours, 30 days or 90 days, a per-key model access policy and a per-key source IP allowlist, the last two settable by API",
          "The pricing page lists input, output and cache-read prices per 1M tokens with context size for each language model, readable without a login",
          "The terms commit to zero data retention and say content is not used to train Novita's models by default, with stated exceptions",
          "A billing page states which HTTP statuses are charged. 400, 401, 403, 429, 500, 503 and 504 are not, and 200 and 499 are",
          "A dated changelog with nine entries between 1 September and 22 October 2026, each retirement naming a UTC time and a replacement"
        ],
        "weaknesses": [
          "No status page or SLA was found on the home page, the docs index or the docs site map. The home page states 99.5% uptime with no supporting document",
          "The rate limit page explains five tiers by monthly top-up, and the RPM and TPM figures per model are drawn by script and were not readable",
          "`xiaomimimo/mimo-v2.5` and `-pro` were retired at 00:00 UTC on 23 October 2026 on a notice dated 22 October",
          "The Python and JavaScript SDK repositories are archived, last changed in November 2024 and March 2025, and the SDK docs page still tells users to install them",
          "The terms name the contracting party only as Novita AI, with no corporate form or address, and no DPA or sub-processor list was found",
          "The terms bar automated or non-human access that extracts data from the site and its linked channels, docs included"
        ],
        "agentNotes": [
          "Set the OpenAI client base URL to `https://api.novita.ai/openai` and send the key as `Authorization: Bearer`. Keys start with `sk_`",
          "Do not close a connection to stop generation. A request that reached the model is billed in full under status 499, so cap output with `max_tokens`",
          "On 429, check whether the code is `RATE_LIMIT_EXCEEDED` or `TOKEN_LIMIT_EXCEEDED` and back off exponentially. No `Retry-After` header is documented",
          "Read the changelog for retirement notices before pinning a model id. One retirement in October 2026 came with 11 days' notice",
          "Ask the account owner for a key with an expiry, a model access policy and an IP allowlist. Keys are created and deleted only in the console"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "C",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 56.1
          }
        ],
        "editorialScores": {
          "ergonomics": 72,
          "maintenance": 66,
          "payments": 53,
          "reliability": 28,
          "schema": 62,
          "security": 65,
          "transparency": 42
        },
        "provenanceScore": 71,
        "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": {
        "install": "pip install openai   # or: npm install openai",
        "http": "curl \"https://api.novita.ai/openai/v1/chat/completions\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $NOVITA_API_KEY\" \\\n  -d '{\"model\":\"deepseek/deepseek-v4.1-flash\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello\"}]}'"
      },
      "letme": {
        "capability": "https://letme.dev/inference.llm",
        "tool": "https://letme.dev/novita-ai"
      },
      "area": "models",
      "provenance": {
        "legalEntity": "Novita AI",
        "domain": "novita.ai",
        "domainRegistered": "2023-09-18",
        "endpointOnVendorDomain": true,
        "terms": "https://novita.ai/legal/terms-of-service",
        "privacy": "https://novita.ai/legal/privacy-policy",
        "statusPage": "",
        "changelog": "https://docs.novita.ai/changelog",
        "securityTxt": "none",
        "checked": "2026-10-09",
        "notes": [
          "The Terms of Service, updated 5 August 2026, name the party only as Novita AI, with no corporate form or address. They cover the site and the services sold through it, the inference APIs included, under Delaware law with arbitration.",
          "The Privacy Policy, effective 13 May 2026, covers the website and services and says it does not apply to content processed on behalf of customers, which it leaves to customer agreements.",
          "The Acceptable Use Policy, effective 5 August 2026, is part of the terms.",
          "No status page was found on the home page, the pricing page, the docs index or the docs site map.",
          "https://novita.ai/.well-known/security.txt returns 404.",
          "RDAP for novita.ai gives a registration date of 2023-09-18.",
          "The API answers at api.novita.ai and the docs at docs.novita.ai. `auth.md` names a token endpoint at api-server.novita.ai.",
          "No SLA, DPA or sub-processor list was found. The trust centre at trust.novita.ai is drawn by script and was not read."
        ],
        "score": 71
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/novita-ai.json",
      "live": {
        "slug": "novita-ai",
        "probe": {
          "target": "https://api.novita.ai/openai",
          "method": "get",
          "lastAt": "2026-11-18T23:01:43.415710948Z",
          "lastOk": true,
          "lastStatus": 404,
          "lastMs": 248,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 193,
          "p95ms24h": 343,
          "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": "2026-10-09T00:00:00Z"
        },
        "versions": [
          {
            "registry": "npm",
            "name": "@novitalabs/novita-mcp-server",
            "version": "1.0.2",
            "seenAt": "2026-11-18T18:12:20.248249424Z"
          },
          {
            "registry": "npm",
            "name": "novita-sdk",
            "version": "3.1.3",
            "seenAt": "2026-11-18T18:12:19.103340628Z"
          },
          {
            "registry": "pypi",
            "name": "novita-client",
            "version": "0.7.1",
            "released": "2024-11-08",
            "seenAt": "2026-11-18T18:12:20.063878665Z"
          }
        ],
        "githubStars": 6,
        "npmWeekly": 855,
        "pypiWeekly": 756,
        "securityTxt": {
          "url": "https://novita.ai/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-11-18T16:31:08.895935635Z"
        },
        "llmsTxt": {
          "url": "https://docs.novita.ai/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-11-18T16:15:24.715276068Z"
        },
        "domain": {
          "domain": "novita.ai",
          "registered": "2023-09-18",
          "source": "https://rdap.identitydigital.services/rdap/domain/novita.ai",
          "checkedAt": "2026-11-15T15:16:34.595794918Z"
        },
        "pages": [
          {
            "url": "https://docs.novita.ai/changelog",
            "kind": "changelog",
            "status": 200,
            "checkedAt": "2026-11-18T21:41:02.317493872Z",
            "changedAt": "2026-11-17T20:59:52.276184244Z",
            "fingerprint": "1a5305851f4c"
          },
          {
            "url": "https://docs.novita.ai/changelog/01-09-26",
            "kind": "deprecations",
            "status": 200,
            "checkedAt": "2026-11-18T21:41:04.47374454Z",
            "changedAt": "2026-11-17T20:59:54.439820671Z",
            "fingerprint": "14eb3a49dc06"
          },
          {
            "url": "https://docs.novita.ai/changelog/15-10-26",
            "kind": "deprecations",
            "status": 200,
            "checkedAt": "2026-11-18T21:41:06.527579447Z",
            "changedAt": "2026-11-17T20:59:56.464745021Z",
            "fingerprint": "505efed0970e"
          },
          {
            "url": "https://docs.novita.ai/changelog/19-10-26",
            "kind": "deprecations",
            "status": 200,
            "checkedAt": "2026-11-18T21:41:08.479520985Z",
            "changedAt": "2026-11-17T20:59:58.505022961Z",
            "fingerprint": "b4e59903f762"
          },
          {
            "url": "https://docs.novita.ai/changelog/20-09-26",
            "kind": "deprecations",
            "status": 200,
            "checkedAt": "2026-11-18T21:41:10.522924091Z",
            "changedAt": "2026-11-17T21:00:00.503787309Z",
            "fingerprint": "3317ef2cee8e"
          },
          {
            "url": "https://docs.novita.ai/changelog/22-10-26",
            "kind": "deprecations",
            "status": 200,
            "checkedAt": "2026-11-18T21:41:12.668877234Z",
            "changedAt": "2026-11-17T21:00:02.53508816Z",
            "fingerprint": "7288af7cd12d"
          },
          {
            "url": "https://docs.novita.ai/changelog/28-09-26",
            "kind": "deprecations",
            "status": 200,
            "checkedAt": "2026-11-18T21:41:14.509428185Z",
            "changedAt": "2026-11-17T21:00:04.608955679Z",
            "fingerprint": "12304e471933"
          },
          {
            "url": "https://novita.ai/pricing",
            "kind": "pricing",
            "status": 200,
            "checkedAt": "2026-11-18T21:49:22.332089736Z",
            "changedAt": "2026-11-18T21:49:22.332089736Z",
            "fingerprint": "a7966bb3f97c"
          },
          {
            "url": "https://novita.ai/legal/privacy-policy",
            "kind": "privacy",
            "status": 200,
            "checkedAt": "2026-11-18T21:49:17.95639458Z",
            "changedAt": "2026-10-28T04:39:20.568611227Z",
            "fingerprint": "d50a56d160b7"
          },
          {
            "url": "https://novita.ai/legal/terms-of-service",
            "kind": "terms",
            "status": 200,
            "checkedAt": "2026-11-18T21:49:20.433911892Z",
            "changedAt": "2026-10-28T04:39:23.076821771Z",
            "fingerprint": "cacda80faa75"
          }
        ],
        "models": {
          "deepseek/deepseek-v4.1-flash": {
            "openrouterId": "deepseek/deepseek-v4.1-flash",
            "tools": true,
            "structuredOutputs": true,
            "jsonMode": true,
            "reasoning": true,
            "input": [
              "image",
              "text"
            ],
            "promptCaching": true,
            "contextTokens": 1048576,
            "maxOutput": 943718,
            "checkedAt": "2026-11-17T23:49:36.802198339Z"
          },
          "openai/gpt-oss-120b": {
            "openrouterId": "openai/gpt-oss-120b",
            "tools": true,
            "structuredOutputs": true,
            "jsonMode": true,
            "reasoning": true,
            "input": [
              "text"
            ],
            "promptCaching": true,
            "contextTokens": 131072,
            "maxOutput": 65536,
            "checkedAt": "2026-11-17T23:49:36.802198339Z"
          },
          "qwen/qwen3.8-flash": {
            "openrouterId": "qwen/qwen3.8-flash",
            "tools": true,
            "structuredOutputs": true,
            "jsonMode": true,
            "reasoning": true,
            "input": [
              "image",
              "text",
              "video"
            ],
            "promptCaching": true,
            "contextTokens": 1000000,
            "maxOutput": 131072,
            "checkedAt": "2026-11-17T23:49:36.802198339Z"
          }
        },
        "github": {
          "repo": "novitalabs/novita-skills",
          "checkedAt": "2026-11-16T12:35:42.544409753Z",
          "stars": 6,
          "archived": false,
          "issuesEnabled": true,
          "pushedAt": "2026-11-05T08:40:25Z",
          "openIssues": 0,
          "openPRs": 0,
          "issuesOpened90d": 0,
          "issuesClosed90d": 0,
          "prsMerged90d": 2
        },
        "updatedAt": "2026-11-18T23:01:43.415710948Z"
      },
      "streak": {
        "days": 20,
        "from": "2026-10-29",
        "last": {
          "kind": "shutdown",
          "date": "2026-10-29",
          "what": "`baidu/ernie-4.5-21B-a3b` goes offline. Move to `deepseek/deepseek-v4.1-flash`",
          "source": "https://docs.novita.ai/changelog/15-10-26"
        },
        "best": 20
      }
    },
    "edges": [
      {
        "by": 47,
        "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. No status page was found. None is linked from the home page, the pricing page, the docs introduction, either `llms.txt` or the docs site map (0), so there is no incident record to read (0). The rate limit page documents five account tiers set by monthly top-ups, from under $50 to $10,000 and over, and limits counted in RPM and TPM per model. The figures per model are drawn by script and were not readable, so this line takes part marks (8 of 15). 429 with `RATE_LIMIT_EXCEEDED` or `TOKEN_LIMIT_EXCEEDED`, advice to throttle and use exponential backoff, and a billing page that says 429, 500, 503 and 504 are not charged. No `Retry-After` header was found (10 of 15). No SLA was found. The home page states 99.5% uptime, and the terms say availability is not guaranteed (0). Generally available (10). Per the 9 October check, not re-read on 4 November, as the terms bar automated access to the site and docs."
        },
        "scores": {
          "a": 75,
          "b": 28
        }
      },
      {
        "by": 38,
        "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. The OpenAPI 3.1.0 document at `/.well-known/openapi.json` is a 964-byte discovery file with four paths and no schemas, and the API reference is written by hand (6 of 25). `llms.txt` on both hosts, a Markdown copy of every docs page and an `llms-full.txt` (10). Guides for function calling, structured output, prompt caching, batch and reasoning say what each is for, and the chat reference describes 136 request and response fields (14 of 20). Fields are typed with required flags and defaults. Enums and ranges are stated in prose only (10 of 15). Curl and Python examples on each guide, error tables by product, a common errors guide and a table of which statuses are billed. The FAQ says `json_schema` and `top_logprobs` are unsupported while the reference and a guide document both (10 of 15). A dated changelog with 84 entries since February 2024. The API has no version scheme beyond `/v1` (12 of 15). Per the 9 October check, not re-read on 4 November, as the terms bar automated access to the site and docs."
        },
        "scores": {
          "a": 100,
          "b": 62
        }
      },
      {
        "by": 35,
        "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. Bearer keys with the `sk_` prefix, shown once, up to 10 an account, with an expiry of 24 hours, 30 days, 90 days or none fixed at creation, deletable in the console, and a per-key model access policy and source IP allowlist that can be set by API. OAuth with PKCE and the scopes `api` and `balance:read` is described in `auth.md`, with no token revocation endpoint. No documented way to send a key in a URL was found (26 of 30). The terms, re-read on 4 November and still updated 5 August 2026, say content is not used to train Novita's models or improve the services by default (17 of 20). The terms state zero data retention, with exceptions for law and for what is necessary to run or support the service, and allow automated safety screening. Batch input files are kept for 15 days (11 of 15). Billing can be queried per key, and budget, monitoring and metrics pages are listed in the docs index and were not read (7 of 15). The trust centre at trust.novita.ai is drawn by script and was not read. `/.well-known/security.txt` returns 404, and no disclosure policy or bug bounty was found (4 of 20). The key, retention and trust-centre readings are per the 9 October check, not re-read on 4 November."
        },
        "scores": {
          "a": 100,
          "b": 65
        }
      },
      {
        "by": 33,
        "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": "Closed service. The terms set Delaware law and arbitration but name the party only as Novita AI, with no corporate form or address. The skill and the MCP server are MIT (10 of 30). The terms state zero data retention and no training by default, and the privacy policy lists retention periods (account data for the life of the account plus 7 years, technical data 2 years). The privacy policy says it does not cover content processed for customers and points to customer agreements. No DPA was found (16 of 30). Retirement notices in the changelog carry a UTC time and a replacement. The terms reserve the right to discontinue any service without notice (12 of 20). The privacy policy names categories of recipients only and transfers that include the United States. No sub-processor list was found (4 of 20). Per the 9 October check, not re-read on 4 November, as the terms bar automated access to the site and docs."
        },
        "scores": {
          "a": 90,
          "b": 57
        }
      },
      {
        "by": 26,
        "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). `tools` with a `strict` flag and a worked example. The list of models that support it is drawn by script, and `tool_choice` is absent from the chat reference (13 of 20). `response_format` takes `json_object` and `json_schema` with `strict` in the reference, while the FAQ says only `json_object` works (9 of 15). Prompt caching is automatic on supported models, cache-read prices are on the pricing page and `cached_tokens` is returned in usage (12 of 15). Context of 1M tokens on DeepSeek V4, GLM 5.3 and Kimi K3 per the pricing page. Output caps were not read (12 of 15). OpenAI-style files and batches with a 24-hour window, one model per file and an introductory 50 per cent discount (10). The OpenAI client works with a changed base URL. Both vendor SDK repositories are archived (5 of 10). Named error codes, a 429 that separates request and token limits, and a `trace_id` for support (11 of 15). Per the 9 October check, not re-read on 4 November, as the terms bar automated access to the site and docs."
        },
        "scores": {
          "a": 98,
          "b": 72
        }
      },
      {
        "by": 21,
        "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": "Model reading. Changelog entries per the 27 October reading of each entry page, not re-read on 4 November because Novita's terms bar automated access to the site and its linked channels. The newest entry is dated 22 October 2026 (30). Retirement notices carry a UTC time and a replacement, with notice of 1 day (22 October for `xiaomimimo/mimo-v2.5` at 00:00 UTC on 23 October) to 29 days (1 September for multimodal models on 30 September). No written notice period was found (6 of 12). Nine dated entries in the 90 days from 6 August (1, 8, 18, 20, 23 and 28 September, 15, 19 and 22 October), each read on its own page (8 of 8). A dated changelog, a Discord server and a support address per the 9 October check (12 of 15). `novitalabs/python-sdk` and `novitalabs/javascript-sdk` are archived, unchanged since 8 November 2024 and 4 March 2025, and issue replies were not examined (2 of 10). The docs rely on the OpenAI client, the SDK page still named the two archived packages on 9 October, and the skill repository is unchanged since 24 September 2026 (5 of 15). The JavaScript SDK repository has a publish workflow only and the Python one has none (3 of 10). 30 + 6 + 8 + 12 + 2 + 5 + 3 = 66."
        },
        "scores": {
          "a": 87,
          "b": 66
        }
      }
    ],
    "facts": [
      {
        "a": "Model API",
        "b": "Model API",
        "name": "Kind"
      },
      {
        "a": "OpenAI",
        "b": "Novita AI",
        "name": "Vendor"
      },
      {
        "a": "https://api.openai.com/v1",
        "b": "https://api.novita.ai/openai",
        "name": "Hosted endpoint"
      },
      {
        "a": "",
        "b": "HTTP",
        "name": "Transports"
      },
      {
        "a": "API key",
        "b": "API key",
        "name": "Auth"
      },
      {
        "a": "Pay per use",
        "b": "Pay per use",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "Closed model, used through the OpenAI API under OpenAI's Services Agreement",
        "b": "Proprietary service under the Novita AI Terms of Service. The agent skill and the MCP server are MIT",
        "name": "Licence"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "llms.txt"
      },
      {
        "a": "2026-11-17",
        "b": "2026-10-22",
        "name": "Last release"
      },
      {
        "a": "couldn't be read",
        "b": "2026-08-05",
        "name": "Terms last updated"
      },
      {
        "a": "couldn't be read",
        "b": "2026-05-13",
        "name": "Privacy policy last updated"
      },
      {
        "a": "couldn't be read",
        "b": "not found in the text",
        "name": "Customer content may train models"
      },
      {
        "a": "couldn't be read",
        "b": "not found in the text",
        "name": "Terms restrict automated access"
      },
      {
        "a": "couldn't be read",
        "b": "not found in the text",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "couldn't be read",
        "b": "yes",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "couldn't be read",
        "b": "yes",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "none",
        "b": "6 stars, 1.4k npm/wk",
        "name": "Popularity"
      }
    ],
    "faq": [
      {
        "answer": "GPT-6.2 Astra scores 85.8 (AA) on agent readiness against Novita AI's 56.1 (C), and leads in 6 of 7 scored categories. Novita AI leads on payments \u0026 pricing.",
        "question": "Which is better for AI agents, GPT-6.2 Astra or Novita AI?"
      },
      {
        "answer": "Both need an API key.",
        "question": "Do GPT-6.2 Astra and Novita AI need an API key?"
      },
      {
        "answer": "Yes. GPT-6.2 Astra has a hosted endpoint at https://api.openai.com/v1 and Novita AI at https://api.novita.ai/openai.",
        "question": "Can an agent call GPT-6.2 Astra and Novita AI without installing anything?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 75 against 28",
          "Schema \u0026 documentation, 100 against 62",
          "Agent ergonomics, 98 against 72",
          "Security \u0026 auth, 100 against 65",
          "Maintenance \u0026 community, 87 against 66",
          "Transparency \u0026 trust, 90 against 57"
        ],
        "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": null,
        "goodFor": "Agents that want many open-weight models at per-token prices behind one OpenAI-style key, with keys that can be limited by model, IP and expiry.",
        "slug": "novita-ai",
        "watchFor": "No status page or SLA was found on the home page, the docs index or the docs site map. The home page states 99.5% uptime with no supporting document"
      }
    ],
    "history": {
      "gpt-6-2-astra": null,
      "novita-ai": [
        {
          "causes": [
            "method"
          ],
          "date": "2026-11-13",
          "delta": 2.2,
          "from": 53.9,
          "fromGrade": "D",
          "to": 56.1,
          "toGrade": "C"
        },
        {
          "causes": [
            "evidence"
          ],
          "date": "2026-11-04",
          "delta": 0.4,
          "from": 53.5,
          "fromGrade": "D",
          "to": 53.9,
          "toGrade": "D"
        },
        {
          "causes": [
            "method"
          ],
          "date": "2026-10-27",
          "delta": 0,
          "from": 53.5,
          "fromGrade": "D",
          "to": 53.5,
          "toGrade": "D"
        }
      ]
    },
    "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-novita-ai.json",
        "title": "Amazon Bedrock vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-novita-ai"
      },
      {
        "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-novita-ai.json",
        "title": "Claude API vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-novita-ai"
      },
      {
        "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-novita-ai.json",
        "title": "Antseed vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/antseed-vs-novita-ai"
      },
      {
        "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-novita-ai.json",
        "title": "Azure OpenAI in Foundry Models vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/azure-openai-vs-novita-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/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-novita-ai.json",
        "title": "BlockRun.AI vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-novita-ai"
      },
      {
        "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-novita-ai.json",
        "title": "Cerebras Inference vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-novita-ai"
      },
      {
        "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-novita-ai.json",
        "title": "Claude Fable 5.2 vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/claude-fable-5-2-vs-novita-ai"
      },
      {
        "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-novita-ai.json",
        "title": "Claude Mythos 5.2 vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-novita-ai"
      },
      {
        "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-novita-ai.json",
        "title": "Cloudflare AI Gateway vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-novita-ai"
      },
      {
        "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-novita-ai.json",
        "title": "Cloudflare Workers AI vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-novita-ai"
      },
      {
        "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-novita-ai.json",
        "title": "Cohere Chat API (Command models) vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-novita-ai"
      },
      {
        "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-novita-ai.json",
        "title": "DeepInfra vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/deepinfra-vs-novita-ai"
      },
      {
        "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-novita-ai.json",
        "title": "DeepSeek API vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-novita-ai"
      },
      {
        "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-novita-ai.json",
        "title": "Eden AI vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/eden-ai-vs-novita-ai"
      },
      {
        "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-novita-ai.json",
        "title": "Glimpse vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-novita-ai"
      },
      {
        "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-novita-ai.json",
        "title": "Fireworks AI Inference vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-novita-ai"
      },
      {
        "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-novita-ai.json",
        "title": "Gemini 4 Carbon vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-novita-ai"
      },
      {
        "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-novita-ai.json",
        "title": "Gemini 4 Hydrogen vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-novita-ai"
      },
      {
        "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-novita-ai.json",
        "title": "Gemini Developer API vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/gemini-api-vs-novita-ai"
      },
      {
        "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-nemotron-3-5-super-vl.json",
        "title": "GPT-6.2 Astra vs Nemotron 3.5 Super VL",
        "url": "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-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-novita-ai.json",
        "title": "GroqCloud vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/groq-vs-novita-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-novita-ai.json",
        "title": "Hugging Face Inference Providers vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-novita-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hy4-vs-novita-ai.json",
        "title": "Tencent Hy4 vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/hy4-vs-novita-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/jais-3-vs-novita-ai.json",
        "title": "Jais 3 vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/jais-3-vs-novita-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-novita-ai.json",
        "title": "Meta Model API vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-novita-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/minimax-api-vs-novita-ai.json",
        "title": "MiniMax API vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/minimax-api-vs-novita-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/mistral-api-vs-novita-ai.json",
        "title": "Mistral AI API vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/mistral-api-vs-novita-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/muse-ember-vs-novita-ai.json",
        "title": "Muse Ember vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/muse-ember-vs-novita-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-novita-ai.json",
        "title": "Muse Spark Open vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-novita-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/novita-ai-vs-openai-api.json",
        "title": "Novita AI vs OpenAI API",
        "url": "https://www.anchorterminal.com/compare/novita-ai-vs-openai-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/novita-ai-vs-openrouter.json",
        "title": "Novita AI vs OpenRouter",
        "url": "https://www.anchorterminal.com/compare/novita-ai-vs-openrouter"
      },
      {
        "json": "https://www.anchorterminal.com/compare/novita-ai-vs-prism-inference.json",
        "title": "Novita AI vs Prism Inference",
        "url": "https://www.anchorterminal.com/compare/novita-ai-vs-prism-inference"
      },
      {
        "json": "https://www.anchorterminal.com/compare/novita-ai-vs-ramp-router.json",
        "title": "Novita AI vs Router.com (Ramp Router)",
        "url": "https://www.anchorterminal.com/compare/novita-ai-vs-ramp-router"
      },
      {
        "json": "https://www.anchorterminal.com/compare/novita-ai-vs-reflection-beam.json",
        "title": "Novita AI vs Beam 1.0",
        "url": "https://www.anchorterminal.com/compare/novita-ai-vs-reflection-beam"
      },
      {
        "json": "https://www.anchorterminal.com/compare/novita-ai-vs-routerplus.json",
        "title": "Novita AI vs RouterPlus",
        "url": "https://www.anchorterminal.com/compare/novita-ai-vs-routerplus"
      },
      {
        "json": "https://www.anchorterminal.com/compare/novita-ai-vs-sambanova.json",
        "title": "Novita AI vs SambaCloud",
        "url": "https://www.anchorterminal.com/compare/novita-ai-vs-sambanova"
      },
      {
        "json": "https://www.anchorterminal.com/compare/novita-ai-vs-siliconflow.json",
        "title": "Novita AI vs SiliconFlow",
        "url": "https://www.anchorterminal.com/compare/novita-ai-vs-siliconflow"
      },
      {
        "json": "https://www.anchorterminal.com/compare/novita-ai-vs-simplismart.json",
        "title": "Novita AI vs Simplismart",
        "url": "https://www.anchorterminal.com/compare/novita-ai-vs-simplismart"
      },
      {
        "json": "https://www.anchorterminal.com/compare/novita-ai-vs-stepfun-api.json",
        "title": "Novita AI vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/novita-ai-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/novita-ai-vs-swe-2-flash.json",
        "title": "Novita AI vs SWE-2 Flash",
        "url": "https://www.anchorterminal.com/compare/novita-ai-vs-swe-2-flash"
      },
      {
        "json": "https://www.anchorterminal.com/compare/novita-ai-vs-tencent-tokenhub.json",
        "title": "Novita AI vs Tencent Cloud TokenHub",
        "url": "https://www.anchorterminal.com/compare/novita-ai-vs-tencent-tokenhub"
      },
      {
        "json": "https://www.anchorterminal.com/compare/novita-ai-vs-together-inference.json",
        "title": "Novita AI vs Together AI Inference",
        "url": "https://www.anchorterminal.com/compare/novita-ai-vs-together-inference"
      },
      {
        "json": "https://www.anchorterminal.com/compare/novita-ai-vs-vercel-ai-gateway.json",
        "title": "Novita AI vs Vercel AI Gateway",
        "url": "https://www.anchorterminal.com/compare/novita-ai-vs-vercel-ai-gateway"
      },
      {
        "json": "https://www.anchorterminal.com/compare/novita-ai-vs-vertex-ai.json",
        "title": "Novita AI vs Vertex AI (Gemini Enterprise Agent Platform)",
        "url": "https://www.anchorterminal.com/compare/novita-ai-vs-vertex-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/novita-ai-vs-xai-api.json",
        "title": "Novita AI vs xAI API (Grok)",
        "url": "https://www.anchorterminal.com/compare/novita-ai-vs-xai-api"
      },
      {
        "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"
      }
    ],
    "panel": null,
    "scores": [
      {
        "by": 47,
        "edge": "gpt-6-2-astra",
        "gpt-6-2-astra": 75,
        "key": "reliability",
        "name": "Reliability",
        "novita-ai": 28,
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "by": 38,
        "edge": "gpt-6-2-astra",
        "gpt-6-2-astra": 100,
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "novita-ai": 62,
        "weight": 13
      },
      {
        "by": 26,
        "edge": "gpt-6-2-astra",
        "gpt-6-2-astra": 98,
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "novita-ai": 72,
        "weight": 13
      },
      {
        "by": 35,
        "edge": "gpt-6-2-astra",
        "gpt-6-2-astra": 100,
        "key": "security",
        "name": "Security \u0026 auth",
        "novita-ai": 65,
        "weight": 14
      },
      {
        "by": 8,
        "edge": "novita-ai",
        "gpt-6-2-astra": 45,
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "novita-ai": 53,
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "by": 21,
        "edge": "gpt-6-2-astra",
        "gpt-6-2-astra": 87,
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "novita-ai": 66,
        "weight": 7
      },
      {
        "by": 33,
        "edge": "gpt-6-2-astra",
        "gpt-6-2-astra": 90,
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "novita-ai": 57,
        "weight": 7
      }
    ],
    "summary": "GPT-6.2 Astra scores 85.8 (AA) on agent readiness against Novita AI's 56.1 (C), and leads in 6 of 7 scored categories. Novita AI 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.",
      "novita-ai": "Per-token prices for about 140 language models are public, and each key can carry an expiry, a model allowlist and a source IP allowlist. No status page, SLA or security.txt was found, the per-model rate limit figures are drawn by script, and both vendor SDK repositories are archived while the docs still point to them."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-novita-ai",
    "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-novita-ai.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-novita-ai.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-novita-ai.min.md"
  },
  "markdown": "GPT-6.2 Astra scores 85.8 (AA) on agent readiness against Novita AI's 56.1 (C), and leads in 6 of 7 scored categories. Novita AI 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- Novita AI: grade C, 56.1/100, rank #956 of 1557. Markdown https://www.anchorterminal.com/tools/novita-ai.md · JSON https://www.anchorterminal.com/api/v1/tools/novita-ai.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 28\n- Schema \u0026 documentation, 100 against 62\n- Agent ergonomics, 98 against 72\n- Security \u0026 auth, 100 against 65\n- Maintenance \u0026 community, 87 against 66\n- Transparency \u0026 trust, 90 against 57\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### Novita AI (C)\n\nGood for: Agents that want many open-weight models at per-token prices behind one OpenAI-style key, with keys that can be limited by model, IP and expiry.\n\nAhead on:\n- Payments \u0026 pricing, 53 against 45\n\nWatch for: No status page or SLA was found on the home page, the docs index or the docs site map. The home page states 99.5% uptime with no supporting document\n\n\n## Why the edge\n\n### Reliability: GPT-6.2 Astra +47\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- Novita AI (28): Hosted reading. No status page was found. None is linked from the home page, the pricing page, the docs introduction, either `llms.txt` or the docs site map (0), so there is no incident record to read (0). The rate limit page documents five account tiers set by monthly top-ups, from under $50 to $10,000 and over, and limits counted in RPM and TPM per model. The figures per model are drawn by script and were not readable, so this line takes part marks (8 of 15). 429 with `RATE_LIMIT_EXCEEDED` or `TOKEN_LIMIT_EXCEEDED`, advice to throttle and use exponential backoff, and a billing page that says 429, 500, 503 and 504 are not charged. No `Retry-After` header was found (10 of 15). No SLA was found. The home page states 99.5% uptime, and the terms say availability is not guaranteed (0). Generally available (10). Per the 9 October check, not re-read on 4 November, as the terms bar automated access to the site and docs.\n\n### Schema \u0026 documentation: GPT-6.2 Astra +38\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- Novita AI (62): Model reading. The OpenAPI 3.1.0 document at `/.well-known/openapi.json` is a 964-byte discovery file with four paths and no schemas, and the API reference is written by hand (6 of 25). `llms.txt` on both hosts, a Markdown copy of every docs page and an `llms-full.txt` (10). Guides for function calling, structured output, prompt caching, batch and reasoning say what each is for, and the chat reference describes 136 request and response fields (14 of 20). Fields are typed with required flags and defaults. Enums and ranges are stated in prose only (10 of 15). Curl and Python examples on each guide, error tables by product, a common errors guide and a table of which statuses are billed. The FAQ says `json_schema` and `top_logprobs` are unsupported while the reference and a guide document both (10 of 15). A dated changelog with 84 entries since February 2024. The API has no version scheme beyond `/v1` (12 of 15). Per the 9 October check, not re-read on 4 November, as the terms bar automated access to the site and docs.\n\n### Security \u0026 auth: GPT-6.2 Astra +35\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- Novita AI (65): Model reading. Bearer keys with the `sk_` prefix, shown once, up to 10 an account, with an expiry of 24 hours, 30 days, 90 days or none fixed at creation, deletable in the console, and a per-key model access policy and source IP allowlist that can be set by API. OAuth with PKCE and the scopes `api` and `balance:read` is described in `auth.md`, with no token revocation endpoint. No documented way to send a key in a URL was found (26 of 30). The terms, re-read on 4 November and still updated 5 August 2026, say content is not used to train Novita's models or improve the services by default (17 of 20). The terms state zero data retention, with exceptions for law and for what is necessary to run or support the service, and allow automated safety screening. Batch input files are kept for 15 days (11 of 15). Billing can be queried per key, and budget, monitoring and metrics pages are listed in the docs index and were not read (7 of 15). The trust centre at trust.novita.ai is drawn by script and was not read. `/.well-known/security.txt` returns 404, and no disclosure policy or bug bounty was found (4 of 20). The key, retention and trust-centre readings are per the 9 October check, not re-read on 4 November.\n\n### Transparency \u0026 trust: GPT-6.2 Astra +33\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- Novita AI (57): Closed service. The terms set Delaware law and arbitration but name the party only as Novita AI, with no corporate form or address. The skill and the MCP server are MIT (10 of 30). The terms state zero data retention and no training by default, and the privacy policy lists retention periods (account data for the life of the account plus 7 years, technical data 2 years). The privacy policy says it does not cover content processed for customers and points to customer agreements. No DPA was found (16 of 30). Retirement notices in the changelog carry a UTC time and a replacement. The terms reserve the right to discontinue any service without notice (12 of 20). The privacy policy names categories of recipients only and transfers that include the United States. No sub-processor list was found (4 of 20). Per the 9 October check, not re-read on 4 November, as the terms bar automated access to the site and docs.\n\n### Agent ergonomics: GPT-6.2 Astra +26\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- Novita AI (72): Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). `tools` with a `strict` flag and a worked example. The list of models that support it is drawn by script, and `tool_choice` is absent from the chat reference (13 of 20). `response_format` takes `json_object` and `json_schema` with `strict` in the reference, while the FAQ says only `json_object` works (9 of 15). Prompt caching is automatic on supported models, cache-read prices are on the pricing page and `cached_tokens` is returned in usage (12 of 15). Context of 1M tokens on DeepSeek V4, GLM 5.3 and Kimi K3 per the pricing page. Output caps were not read (12 of 15). OpenAI-style files and batches with a 24-hour window, one model per file and an introductory 50 per cent discount (10). The OpenAI client works with a changed base URL. Both vendor SDK repositories are archived (5 of 10). Named error codes, a 429 that separates request and token limits, and a `trace_id` for support (11 of 15). Per the 9 October check, not re-read on 4 November, as the terms bar automated access to the site and docs.\n\n### Maintenance \u0026 community: GPT-6.2 Astra +21\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- Novita AI (66): Model reading. Changelog entries per the 27 October reading of each entry page, not re-read on 4 November because Novita's terms bar automated access to the site and its linked channels. The newest entry is dated 22 October 2026 (30). Retirement notices carry a UTC time and a replacement, with notice of 1 day (22 October for `xiaomimimo/mimo-v2.5` at 00:00 UTC on 23 October) to 29 days (1 September for multimodal models on 30 September). No written notice period was found (6 of 12). Nine dated entries in the 90 days from 6 August (1, 8, 18, 20, 23 and 28 September, 15, 19 and 22 October), each read on its own page (8 of 8). A dated changelog, a Discord server and a support address per the 9 October check (12 of 15). `novitalabs/python-sdk` and `novitalabs/javascript-sdk` are archived, unchanged since 8 November 2024 and 4 March 2025, and issue replies were not examined (2 of 10). The docs rely on the OpenAI client, the SDK page still named the two archived packages on 9 October, and the skill repository is unchanged since 24 September 2026 (5 of 15). The JavaScript SDK repository has a publish workflow only and the Python one has none (3 of 10). 30 + 6 + 8 + 12 + 2 + 5 + 3 = 66.\n\n## Score by category\n\n| Category | Weight | GPT-6.2 Astra | Novita AI | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 75 | 28 | GPT-6.2 Astra +47 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% | 100 | 62 | GPT-6.2 Astra +38 |\n| Agent ergonomics | 13% | 98 | 72 | GPT-6.2 Astra +26 |\n| Security \u0026 auth | 14% | 100 | 65 | GPT-6.2 Astra +35 |\n| Payments \u0026 pricing | 10% | 45 | 53 | Novita AI +8 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% | 87 | 66 | GPT-6.2 Astra +21 |\n| Transparency \u0026 trust | 7% | 90 | 57 | GPT-6.2 Astra +33 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **85.8 · AA** | **56.1 · C** | |\n\n## Facts side by side\n\n| Fact | GPT-6.2 Astra | Novita AI |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | OpenAI | Novita AI |\n| Hosted endpoint | `https://api.openai.com/v1` | `https://api.novita.ai/openai` |\n| Transports |  | HTTP |\n| Auth | API key | API key |\n| Pricing | Pay per use | Pay per use |\n| x402 | no | no |\n| Licence | Closed model, used through the OpenAI API under OpenAI's Services Agreement | Proprietary service under the Novita AI Terms of Service. The agent skill and the MCP server are MIT |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-11-17 | 2026-10-22 |\n| Terms last updated | couldn't be read | 2026-08-05 |\n| Privacy policy last updated | couldn't be read | 2026-05-13 |\n| Customer content may train models | couldn't be read | not found in the text |\n| Terms restrict automated access | couldn't be read | not found in the text |\n| Terms restrict benchmarking | couldn't be read | not found in the text |\n| Terms or service can change without notice | couldn't be read | yes |\n| Arbitration or class-action waiver | couldn't be read | yes |\n| Popularity | none | 6 stars, 1.4k npm/wk |\n\n## How the scores have moved\n\n### GPT-6.2 Astra\n\nNo score change since it was listed.\n\n### Novita AI\n\n- +2.2 on 13 November 2026 (D to C): checklist\n- +0.4 on 4 November 2026: new evidence\n- no change on 27 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**Novita AI.** Per-token prices for about 140 language models are public, and each key can carry an expiry, a model allowlist and a source IP allowlist. No status page, SLA or security.txt was found, the per-model rate limit figures are drawn by script, and both vendor SDK repositories are archived while the docs still point to them.\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### Novita AI\n\n1. Set the OpenAI client base URL to `https://api.novita.ai/openai` and send the key as `Authorization: Bearer`. Keys start with `sk_`\n2. Do not close a connection to stop generation. A request that reached the model is billed in full under status 499, so cap output with `max_tokens`\n3. On 429, check whether the code is `RATE_LIMIT_EXCEEDED` or `TOKEN_LIMIT_EXCEEDED` and back off exponentially. No `Retry-After` header is documented\n4. Read the changelog for retirement notices before pinning a model id. One retirement in October 2026 came with 11 days' notice\n5. Ask the account owner for a key with an expiry, a model access policy and an IP allowlist. Keys are created and deleted only in the console\n\n## Questions\n\n### Which is better for AI agents, GPT-6.2 Astra or Novita AI?\n\nGPT-6.2 Astra scores 85.8 (AA) on agent readiness against Novita AI's 56.1 (C), and leads in 6 of 7 scored categories. Novita AI leads on payments \u0026 pricing.\n\n### Do GPT-6.2 Astra and Novita AI need an API key?\n\nBoth need an API key.\n\n### Can an agent call GPT-6.2 Astra and Novita AI without installing anything?\n\nYes. GPT-6.2 Astra has a hosted endpoint at https://api.openai.com/v1 and Novita AI at https://api.novita.ai/openai.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-novita-ai.json, and with the fewest tokens: https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-novita-ai.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"gpt-6-2-astra\", \"b\": \"novita-ai\"}`. From a terminal: `anchor compare gpt-6-2-astra novita-ai`\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/novita-ai.json\n\n## Other comparisons with GPT-6.2 Astra or Novita AI\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 Novita AI](https://www.anchorterminal.com/compare/amazon-bedrock-vs-novita-ai.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 Novita AI](https://www.anchorterminal.com/compare/anthropic-api-vs-novita-ai.md)\n- [Antseed vs GPT-6.2 Astra](https://www.anchorterminal.com/compare/antseed-vs-gpt-6-2-astra.md)\n- [Antseed vs Novita AI](https://www.anchorterminal.com/compare/antseed-vs-novita-ai.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 Novita AI](https://www.anchorterminal.com/compare/azure-openai-vs-novita-ai.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 Novita AI](https://www.anchorterminal.com/compare/blockrun-ai-vs-novita-ai.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 Novita AI](https://www.anchorterminal.com/compare/cerebras-inference-vs-novita-ai.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 Novita AI](https://www.anchorterminal.com/compare/claude-fable-5-2-vs-novita-ai.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 Novita AI](https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-novita-ai.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 Novita AI](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-novita-ai.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 Novita AI](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-novita-ai.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 Novita AI](https://www.anchorterminal.com/compare/cohere-chat-vs-novita-ai.md)\n- [DeepInfra vs GPT-6.2 Astra](https://www.anchorterminal.com/compare/deepinfra-vs-gpt-6-2-astra.md)\n- [DeepInfra vs Novita AI](https://www.anchorterminal.com/compare/deepinfra-vs-novita-ai.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 Novita AI](https://www.anchorterminal.com/compare/deepseek-api-vs-novita-ai.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 Novita AI](https://www.anchorterminal.com/compare/eden-ai-vs-novita-ai.md)\n- [Glimpse vs GPT-6.2 Astra](https://www.anchorterminal.com/compare/elorian-glimpse-vs-gpt-6-2-astra.md)\n- [Glimpse vs Novita AI](https://www.anchorterminal.com/compare/elorian-glimpse-vs-novita-ai.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 Novita AI](https://www.anchorterminal.com/compare/fireworks-inference-vs-novita-ai.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 Novita AI](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-novita-ai.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 Novita AI](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-novita-ai.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 Novita AI](https://www.anchorterminal.com/compare/gemini-api-vs-novita-ai.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 Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-nemotron-3-5-super-vl.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 Novita AI](https://www.anchorterminal.com/compare/groq-vs-novita-ai.md)\n- [Hugging Face Inference Providers vs Novita AI](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-novita-ai.md)\n- [Tencent Hy4 vs Novita AI](https://www.anchorterminal.com/compare/hy4-vs-novita-ai.md)\n- [Jais 3 vs Novita AI](https://www.anchorterminal.com/compare/jais-3-vs-novita-ai.md)\n- [Meta Model API vs Novita AI](https://www.anchorterminal.com/compare/meta-model-api-vs-novita-ai.md)\n- [MiniMax API vs Novita AI](https://www.anchorterminal.com/compare/minimax-api-vs-novita-ai.md)\n- [Mistral AI API vs Novita AI](https://www.anchorterminal.com/compare/mistral-api-vs-novita-ai.md)\n- [Muse Ember vs Novita AI](https://www.anchorterminal.com/compare/muse-ember-vs-novita-ai.md)\n- [Muse Spark Open vs Novita AI](https://www.anchorterminal.com/compare/muse-spark-open-vs-novita-ai.md)\n- [Novita AI vs OpenAI API](https://www.anchorterminal.com/compare/novita-ai-vs-openai-api.md)\n- [Novita AI vs OpenRouter](https://www.anchorterminal.com/compare/novita-ai-vs-openrouter.md)\n- [Novita AI vs Prism Inference](https://www.anchorterminal.com/compare/novita-ai-vs-prism-inference.md)\n- [Novita AI vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/novita-ai-vs-ramp-router.md)\n- [Novita AI vs Beam 1.0](https://www.anchorterminal.com/compare/novita-ai-vs-reflection-beam.md)\n- [Novita AI vs RouterPlus](https://www.anchorterminal.com/compare/novita-ai-vs-routerplus.md)\n- [Novita AI vs SambaCloud](https://www.anchorterminal.com/compare/novita-ai-vs-sambanova.md)\n- [Novita AI vs SiliconFlow](https://www.anchorterminal.com/compare/novita-ai-vs-siliconflow.md)\n- [Novita AI vs Simplismart](https://www.anchorterminal.com/compare/novita-ai-vs-simplismart.md)\n- [Novita AI vs StepFun API](https://www.anchorterminal.com/compare/novita-ai-vs-stepfun-api.md)\n- [Novita AI vs SWE-2 Flash](https://www.anchorterminal.com/compare/novita-ai-vs-swe-2-flash.md)\n- [Novita AI vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/novita-ai-vs-tencent-tokenhub.md)\n- [Novita AI vs Together AI Inference](https://www.anchorterminal.com/compare/novita-ai-vs-together-inference.md)\n- [Novita AI vs Vercel AI Gateway](https://www.anchorterminal.com/compare/novita-ai-vs-vercel-ai-gateway.md)\n- [Novita AI vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/novita-ai-vs-vertex-ai.md)\n- [Novita AI vs xAI API (Grok)](https://www.anchorterminal.com/compare/novita-ai-vs-xai-api.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",
  "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 Novita AI",
        "url": ""
      }
    ],
    "description": "GPT-6.2 Astra scores 85.8 (AA) to Novita AI's 56.1 (C) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "GPT-6.2 Astra AA 85.8",
      "Novita AI C 56.1",
      "scores"
    ],
    "h1": "GPT-6.2 Astra vs Novita AI",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/gpt-6-2-astra-vs-novita-ai",
    "published": "2026-10-01",
    "section": "tools",
    "title": "GPT-6.2 Astra vs Novita AI for AI agents in 2026: scores and prices",
    "toc": null,
    "updated": "2026-11-18",
    "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-novita-ai"
  },
  "tokens": {
    "markdown": 8400,
    "slim": 930
  },
  "version": 1
}
