{ "data": { "a": { "slug": "novita-ai", "name": "Novita AI", "vendor": "Novita AI", "vendorUrl": "https://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": 53.9, "grade": "D", "agentReady": false, "rank": 831, "ranked": true, "rankOf": 1350, "categoryRank": 22, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 72, "maintenance": 66, "payments": 35, "reliability": 28, "schema": 62, "security": 65, "transparency": 57 }, "pending": [ "performance", "tasks" ], "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": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 53.9 } ], "editorialScores": { "ergonomics": 72, "maintenance": 66, "payments": 35, "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": "2026-11-04", "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": "2026-11-05T01:29:10.647551109Z", "lastOk": true, "lastStatus": 404, "lastMs": 191, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 202, "p95ms24h": 296, "samples24h": 247, "samples30d": 6608, "days": [ { "date": "2026-10-09", "probes": 85, "ok": 85 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "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": 16, "ok": 16 } ] }, "versions": [ { "registry": "npm", "name": "@novitalabs/novita-mcp-server", "version": "1.0.2", "seenAt": "2026-11-04T20:40:15.45017663Z" }, { "registry": "npm", "name": "novita-sdk", "version": "3.1.3", "seenAt": "2026-11-04T20:40:14.270179758Z" }, { "registry": "pypi", "name": "novita-client", "version": "0.7.1", "released": "2024-11-08", "seenAt": "2026-11-04T20:40:15.103798158Z" } ], "githubStars": 6, "npmWeekly": 987, "pypiWeekly": 654, "securityTxt": { "url": "https://novita.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-04T15:53:21.922145119Z" }, "llmsTxt": { "url": "https://docs.novita.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-04T15:23:40.540019745Z" }, "domain": { "domain": "novita.ai", "registered": "2023-09-18", "source": "https://rdap.identitydigital.services/rdap/domain/novita.ai", "checkedAt": "2026-11-01T14:09:52.11894532Z" }, "pages": [ { "url": "https://docs.novita.ai/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-11-04T08:21:45.179013023Z", "changedAt": "2026-11-04T08:21:45.179013023Z", "fingerprint": "f827ac728b7d" }, { "url": "https://docs.novita.ai/changelog/01-09-26", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-04T08:21:47.49769274Z", "changedAt": "2026-11-04T08:21:47.49769274Z", "fingerprint": "3730f7bba944" }, { "url": "https://docs.novita.ai/changelog/15-10-26", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-04T08:21:49.491839435Z", "changedAt": "2026-11-04T08:21:49.491839435Z", "fingerprint": "a7425e10aff7" }, { "url": "https://docs.novita.ai/changelog/19-10-26", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-04T08:21:53.376170473Z", "changedAt": "2026-11-04T08:21:53.376170473Z", "fingerprint": "8b3250a4a370" }, { "url": "https://docs.novita.ai/changelog/20-09-26", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-04T08:21:53.597737286Z", "changedAt": "2026-11-04T08:21:53.597737286Z", "fingerprint": "f7e39de96a7d" }, { "url": "https://docs.novita.ai/changelog/22-10-26", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-04T08:21:55.606302628Z", "changedAt": "2026-11-04T08:21:55.606302628Z", "fingerprint": "87c421ed45cd" }, { "url": "https://docs.novita.ai/changelog/28-09-26", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-04T08:21:57.7360385Z", "changedAt": "2026-11-04T08:21:57.7360385Z", "fingerprint": "b9ec679ba600" }, { "url": "https://novita.ai/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-04T08:28:38.056960886Z", "changedAt": "2026-11-04T08:28:38.056960886Z", "fingerprint": "d3e695c49bb9" }, { "url": "https://novita.ai/legal/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-04T08:28:33.670672286Z", "changedAt": "2026-10-28T04:39:20.568611227Z", "fingerprint": "d50a56d160b7" }, { "url": "https://novita.ai/legal/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-11-04T08:28:36.163234923Z", "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": "2026-11-04T23:49:21.961528872Z" }, "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": "2026-11-04T23:49:21.961528872Z" }, "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": "2026-11-04T23:49:21.961528872Z" } }, "github": { "repo": "novitalabs/novita-skills", "checkedAt": "2026-11-02T09:11:04.159600432Z", "stars": 6, "archived": false, "issuesEnabled": true, "pushedAt": "2026-09-24T05:32:53Z", "openIssues": 0, "openPRs": 0, "issuesOpened90d": 0, "issuesClosed90d": 0, "prsMerged90d": 1 }, "updatedAt": "2026-11-05T01:29:10.647551109Z" } }, "answer": "Novita AI scores 53.9 (D) on agent readiness against SWE-2 Flash's 36.4 (F), and leads in 5 of 7 scored categories. SWE-2 Flash leads on reliability and transparency \u0026 trust.", "b": { "slug": "swe-2-flash", "name": "SWE-2 Flash", "vendor": "Cognition AI, Inc.", "vendorUrl": "https://cognition.com/blog/swe-2-flash", "kind": "model", "category": "inference", "summary": "SWE-2 Flash is Cognition's small, fast coding model, mid-trained and reinforcement-trained from Thinking Machines' Inkling-Small (276B total, 12B active parameters). It runs inside Devin Desktop and Devin CLI, with no model API of its own and no public weights.", "url": "https://www.anchorterminal.com/tools/swe-2-flash", "markdownUrl": "https://www.anchorterminal.com/tools/swe-2-flash.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/swe-2-flash.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/swe-2-flash.json", "dns": "swe-2-flash.grade.anchorterminal.com", "license": "Proprietary model, used through Devin Desktop and Devin CLI under Cognition's Platform Terms of Service. The weights are not public; Cognition says it is building a programme to share them with industry partners and researchers", "transports": [], "packages": [], "auth": "mixed", "authNotes": "No model API or key of its own. A person signs in to Devin Desktop, or runs `devin auth login` for Devin CLI, through a browser (enterprise users through their identity provider). The CLI then keeps an API token in credentials.toml that by default is persistent and does not expire, and the docs warn that anyone with the file can authenticate as that user. Enterprise admins choose which models a team may use with a model allowlist.", "pricing": "freemium", "pricingNotes": "Free in Devin Desktop and Devin CLI through 30 November 2026, per the launch post. Afterwards it is billed against the plan's daily and weekly quota, then extra usage at API pricing. The post says one-fifth the price of SWE-2, whose list price is $3.00 input, $0.30 cached input and $15.00 output per million tokens, but no SWE-2 Flash figure is published: the docs' cost table loads in the browser and the models pages don't list it yet (checked 2026-11-04). Plans are Free $0, Pro $20 a month, Max $200 a month and Teams $80 a month plus $40 per full seat. The docs say Free tier users only have SWE-1.6, so whether Free reaches SWE-2 Flash is unconfirmed.", "priceSummary": "Freemium", "where": "local", "x402": { "level": "no", "evidence": "No model endpoint to pay. No x402, MPP or L402 on the Devin pricing page, the Devin Desktop models page or the launch post (checked 2026-11-04).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-04" }, "docsUrl": "https://docs.devin.ai/desktop/models", "llmsTxt": "https://docs.devin.ai/llms.txt", "capabilities": [ "inference.llm" ], "tags": [ "official", "hosted", "model", "closed-source", "coding", "moe", "cli", "desktop-app", "llms-txt", "status-page", "soc2", "iso27001", "sla", "freemium", "new" ], "lastRelease": "2026-11-04", "graded": true, "anchor": { "graded": true, "score": 36.4, "grade": "F", "agentReady": false, "rank": 1243, "ranked": true, "rankOf": 1350, "categoryRank": 33, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 10, "maintenance": 53, "payments": 20, "reliability": 50, "schema": 29, "security": 53, "transparency": 64 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-04" }, "negative": -2, "negativeNotes": [ "The launch post says 'On leading evals, SWE-2 Flash outperforms all American open-weight models'. The post's own table, a first-hand source, gives Meta's Muse Spark Open (American, open weights, released 15 October 2026) 54.0 on SWE-Atlas QA against SWE-2 Flash's 50.0, and Meta's own figure for Muse Spark Open is 58. A 'surpasses' claim a first-hand source shows false is a deduction of 2 (research/new-2026-11-04-ripple-swe2/NEWLIST.md, rule 4). The case against: SWE-2 Flash leads every other row it shares with the American open-weight models in the table, and DeepSWE 1.1 is 60.1 to 60.0, so 'on leading evals' can be read as overall. Proposed for the founder to confirm at landing, as xiaomi-ocr-0's was" ], "verdict": "A new small coding model from Cognition that anyone can try free in Devin Desktop and Devin CLI until 30 November 2026, with strong vendor-reported coding scores. It has no model API, no published per-token price, context length or model card, and no public weights, so an agent can reach it only by driving Devin's own CLI.", "bestFor": "People already using Devin Desktop or Devin CLI who want a cheaper, faster model for routine coding work such as automations, reviews and small changes, while it is free in November 2026.", "strengths": [ "Free in Devin Desktop and Devin CLI through 30 November 2026, and selectable per run with `devin --model` or `/model`", "Cognition reports large gains over its base model, Terminal-Bench 4.0 from 0.9 to 20.0 and FrontierCode 2.0 from 3.2 to 24.0, with the full benchmark table in the post", "Runs inside Devin CLI's sandbox, permissions and hooks, and enterprise admins can allow or block it per team", "Cognition holds SOC 2 Type II and ISO/IEC 27001:2022 and publishes an SLA for contracts that include one", "Status page with a Desktop Agent component, and in the 90 days to 4 November no incident names Desktop or the CLI, only a scheduled extension marketplace maintenance on 7 August" ], "weaknesses": [ "No model API, OpenAPI entry or model card. The Devin API's session agents list SWE-2 but not SWE-2 Flash", "No per-token price, context length, output limit or reasoning settings published for it, and the docs' models pages don't list it yet", "The weights are withheld for now, with a partner and researcher programme promised but not yet described", "Customer data may be used for model training by default on self-serve plans, with the opt-out on paid plans only", "The CLI's login token is persistent and doesn't expire by default, and no rate limit figures or retry guidance are published" ], "agentNotes": [ "There is no endpoint to call. Run Devin CLI single-turn with `devin -p` and pick the model with `--model`; the SWE-2 Flash model ID isn't documented yet, so check `/model` in the CLI first", "Don't rely on the short name `swe`. The docs say it resolves to the latest model in the family, which may be SWE-2 rather than SWE-2 Flash", "Plan for billing to start on 1 December 2026. The free period covers Devin Desktop and CLI only, not Devin cloud sessions", "Treat Cognition's benchmark figures as the vendor's. No independent result for SWE-2 Flash was found", "Keep `credentials.toml` private. The token in it doesn't expire by default and carries the signed-in user's access" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "F", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 36.4 } ], "editorialScores": { "ergonomics": 10, "maintenance": 53, "payments": 20, "reliability": 50, "schema": 29, "security": 53, "transparency": 56 }, "provenanceScore": 72, "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", "oldest": "2026-11-04", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "Install Devin CLI or Devin Desktop from https://devin.ai/download, sign in with `devin auth login`, then choose SWE-2 Flash with `/model`" }, "letme": { "capability": "https://letme.dev/inference.llm", "tool": "https://letme.dev/swe-2-flash" }, "area": "models", "provenance": { "legalEntity": "Cognition AI, Inc.", "domain": "cognition.com", "domainRegistered": "", "domainNote": "Not looked up: RDAP isn't requested under the 1 November 2026 rules. The product runs on devin.ai, registered 2022-12-06 per the devin listing's RDAP check of 8 October 2026.", "endpointOnVendorDomain": true, "terms": "https://cognition.com/legal/platform-terms-of-service", "privacy": "https://cognition.com/legal/privacy-policy", "statusPage": "https://www.devinstatus.com", "changelog": "https://docs.devin.ai/release-notes/overview", "securityTxt": "none", "checked": "2026-11-04", "notes": [ "The launch post is on cognition.com, signed by the Cognition Team, and the Devin docs, pricing page and status page link the same company. The platform terms (30 June 2026) name Cognition AI, Inc.", "The website terms of use (13 May 2024) and platform terms were read for automated-access limits and have none. cognition.com's robots.txt disallows only /downloads/, devin.ai's only /top-secret and /assets/downloads/, docs.devin.ai's /cdn-cgi/ and /_next/ (with Content-Signal ai-input=yes), and www.devinstatus.com's /api/ and /embed/.", "security.txt is none per the devin listing's 8 October check, not re-read. The docs give a security address for vulnerability reports.", "No SWE-2 Flash entry in the Devin release notes, whose newest is 2 November 2026." ], "score": 72 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/swe-2-flash.json", "live": { "slug": "swe-2-flash", "vendorStatus": { "page": "https://www.devinstatus.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-05T01:27:53.220664573Z" }, "updatedAt": "2026-11-05T01:27:53.220664573Z" } }, "edges": [ { "by": 62, "category": "ergonomics", "leads": "novita-ai", "name": "Agent ergonomics", "reasons": { "a": "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.", "b": "Model reading (tool use, structured output, caching, context, batch, SDKs). Tool use is Devin's harness, not something a caller configures; no context length, output limit or cache price is published for SWE-2 Flash (5 of 25). No documented output-size or reasoning controls for this model; SWE-2's effort levels aren't stated for Flash (0 of 20). No model-level error documentation (0 of 20). No idempotency or retry guidance (0 of 20). One flag or picker selects it and `devin -p` runs a single turn and prints to stdout, but there is no SDK or direct endpoint (5 of 15). 5 + 0 + 0 + 0 + 5 = 10." }, "scores": { "a": 72, "b": 10 } }, { "by": 33, "category": "schema", "leads": "novita-ai", "name": "Schema \u0026 documentation", "reasons": { "a": "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.", "b": "Model reading. No model API, so no OpenAPI entry; the Devin v3 OpenAPI file lists SWE-2 agents only, and no model card was found (0). docs.devin.ai serves llms.txt and Markdown copies of every page (10). The launch post says what it is for (automations, code review, feature development, documentation) and the CLI docs say when to pick a SWE model, but the models pages don't list SWE-2 Flash yet (6 of 20). No documented model ID, reasoning settings, context or output limits to type (0 of 15). The CLI pages show `--model` and `/model` examples, with no model-specific errors (3 of 15). Named, dated model versions on Cognition's blog and public release notes, but no release note for SWE-2 Flash yet; the newest is 2 November (10 of 15). 0 + 10 + 6 + 0 + 3 + 10 = 29." }, "scores": { "a": 62, "b": 29 } }, { "by": 22, "category": "reliability", "leads": "swe-2-flash", "name": "Reliability", "reasons": { "a": "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.", "b": "Model reading, for the surface it runs on, Devin Desktop and Devin CLI. Status page at www.devinstatus.com (Atlassian Statuspage) with Desktop Agent and Desktop Tab components besides the cloud ones, read on 4 November 2026 (20). The history feed for the 90 days from 6 August lists 'Devin unavailable' for 20 minutes on 13 August with no component named, read as across the board and a major as on the devin listing; Devin Cloud unavailable on 13 August and the web app down on 24 September name cloud surfaces this model doesn't use; the rest are degraded-performance incidents (new sessions on 3 September, 'multiple services' on 17 September, Ask Devin on 26 October, automation triggers on 4 November) and session queuing on 10 and 11 August, read as minor and a scheduled Devin Desktop extension marketplace upgrade on 7 August, read as maintenance. One major (10). No rate limit figures for the model or the CLI; usage is a daily and weekly quota with no numbers (0). No 429, backoff or retry guidance for this surface (0). Cognition publishes an SLA (25 February 2026) with uptime and response times that applies when included in an order form, read as a contractual SLA on Enterprise, as on other listings (10). The launch post makes it available today with no preview or beta label (10). 20 + 10 + 0 + 0 + 10 + 10 = 50." }, "scores": { "a": 28, "b": 50 } }, { "by": 15, "category": "payments", "leads": "novita-ai", "name": "Payments \u0026 pricing", "reasons": { "a": "No machine payment protocol was found in the docs index, the site map, the pricing page or the skill repository (0). Per-token prices for each model on the pricing page without a login, such as `deepseek/deepseek-v4.1-flash` at $0.30 in and $1.20 out per 1M tokens (20). Two language models are listed as free and the FAQ describes a voucher for new users. Whether a card is needed to use either was not stated in the pages read (15 of 20). A person signs up in a browser, keys are created only in the console, and the OAuth route needs the user to sign in and approve (0). Per the 9 October check, not re-read on 4 November, as the terms bar automated access to the site and docs.", "b": "Published rubric. No payment protocol (0). Plan prices are public, but no per-token price for SWE-2 Flash is on a readable page; the docs' cost table loads in the browser and the post gives only 'one-fifth the price' of SWE-2 (10). Free through 30 November 2026 on Devin Desktop and CLI, but the docs say Free tier users only have SWE-1.6, so whether the Free plan reaches it, and without a card, isn't confirmed; the in-between value used on the devin listing (10). A person signs in through a browser (0). 0 + 10 + 10 + 0 = 20." }, "scores": { "a": 35, "b": 20 } }, { "by": 13, "category": "maintenance", "leads": "novita-ai", "name": "Maintenance \u0026 community", "reasons": { "a": "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.", "b": "Model reading. Released 4 November 2026 (30). Churn and notice in place of release counts: SWE-1.6, SWE-1.7, SWE-1.7 Lightning, SWE-2 (10 September) and now SWE-2 Flash in a few months, with no model deprecation notice period found and short names that move to the newest model (10 of 20). Public release notes and a support address, no public tracker (10 of 25). No official SDK for the model (0 of 15). The docs are kept current but don't yet cover this model (3 of 10). 30 + 10 + 10 + 0 + 3 = 53." }, "scores": { "a": 66, "b": 53 } }, { "by": 12, "category": "security", "leads": "novita-ai", "name": "Security \u0026 auth", "reasons": { "a": "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.", "b": "Read as a hosted model reached through Devin's local clients. The CLI signs in through a browser, or the enterprise identity provider, and stores an API token in credentials.toml that by default is persistent and does not expire and carries the user's access, with no scopes found for it (10 of 30). Devin CLI documents an OS-level sandbox with network filtering, hooks that can block tool calls, and enterprise model allowlists and team settings (14 of 20). Guardrails against prompt injection are Enterprise only and cover user messages, as on the devin listing (8 of 15). Enterprise analytics count tool calls and consumption by model and user; no per-user audit log for the CLI was found (8 of 15). SOC 2 Type II and ISO/IEC 27001:2022, a disclosure address, no bug bounty and no security.txt, per the devin listing (13 of 20). Training: self-serve customer data may train Cognition's models by default, with an opt-out on paid plans that also turns on zero data retention at model providers. Cognition withheld the weights over cyber misuse, which is recorded as a fact, not scored. 10 + 14 + 8 + 8 + 13 = 53." }, "scores": { "a": 65, "b": 53 } } ], "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Novita AI", "b": "Cognition AI, Inc.", "name": "Vendor" }, { "a": "https://api.novita.ai/openai", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "", "name": "Transports" }, { "a": "API key", "b": "OAuth or key", "name": "Auth" }, { "a": "Pay per use", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under the Novita AI Terms of Service. The agent skill and the MCP server are MIT", "b": "Proprietary model, used through Devin Desktop and Devin CLI under Cognition's Platform Terms of Service. The weights are not public; Cognition says it is building a programme to share them with industry partners and researchers", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-22", "b": "2026-11-04", "name": "Last release" }, { "a": "2026-08-05", "b": "2026-06-30", "name": "Terms last updated" }, { "a": "2026-05-13", "b": "2026-03-09", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "yes, with an opt-out", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "6 stars, 1.4k npm/wk", "b": "none", "name": "Popularity" } ], "faq": [ { "answer": "Novita AI scores 53.9 (D) on agent readiness against SWE-2 Flash's 36.4 (F), and leads in 5 of 7 scored categories. SWE-2 Flash leads on reliability and transparency \u0026 trust.", "question": "Which is better for AI agents, Novita AI or SWE-2 Flash?" }, { "answer": "Novita AI needs an API key. SWE-2 Flash takes an API key or an OAuth sign-in.", "question": "Do Novita AI and SWE-2 Flash need an API key?" }, { "answer": "Novita AI has a hosted endpoint at https://api.novita.ai/openai. No hosted endpoint is listed for SWE-2 Flash.", "question": "Can an agent call Novita AI and SWE-2 Flash without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 62 against 29", "Agent ergonomics, 72 against 10", "Security \u0026 auth, 65 against 53", "Payments \u0026 pricing, 35 against 20", "Maintenance \u0026 community, 66 against 53" ], "also": [ "A hosted endpoint, with nothing to install" ], "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" }, { "aheadOn": [ "Reliability, 50 against 28", "Transparency \u0026 trust, 64 against 57" ], "also": null, "goodFor": "People already using Devin Desktop or Devin CLI who want a cheaper, faster model for routine coding work such as automations, reviews and small changes, while it is free in November 2026.", "slug": "swe-2-flash", "watchFor": "No model API, OpenAPI entry or model card. The Devin API's session agents list SWE-2 but not SWE-2 Flash" } ], "history": { "novita-ai": [ { "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" } ], "swe-2-flash": null }, "job": { "capability": "inference.llm", "name": "LLM inference" }, "others": [ { "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/anthropic-api-vs-swe-2-flash.json", "title": "Claude API vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-swe-2-flash" }, { "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/antseed-vs-swe-2-flash.json", "title": "Antseed vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/antseed-vs-swe-2-flash" }, { "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/blockrun-ai-vs-swe-2-flash.json", "title": "BlockRun.AI vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-swe-2-flash" }, { "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/cerebras-inference-vs-swe-2-flash.json", "title": "Cerebras Inference vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-swe-2-flash" }, { "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-ai-gateway-vs-swe-2-flash.json", "title": "Cloudflare AI Gateway vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-swe-2-flash" }, { "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/cloudflare-workers-ai-vs-swe-2-flash.json", "title": "Cloudflare Workers AI vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-swe-2-flash" }, { "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/cohere-chat-vs-swe-2-flash.json", "title": "Cohere Chat API (Command models) vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-swe-2-flash" }, { "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/deepinfra-vs-swe-2-flash.json", "title": "DeepInfra vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/deepinfra-vs-swe-2-flash" }, { "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/deepseek-api-vs-swe-2-flash.json", "title": "DeepSeek API vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-swe-2-flash" }, { "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/elorian-glimpse-vs-swe-2-flash.json", "title": "Glimpse vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-swe-2-flash" }, { "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/fireworks-inference-vs-swe-2-flash.json", "title": "Fireworks AI Inference vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-swe-2-flash" }, { "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/gemini-api-vs-swe-2-flash.json", "title": "Gemini Developer API vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/gemini-api-vs-swe-2-flash" }, { "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/groq-vs-swe-2-flash.json", "title": "GroqCloud vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/groq-vs-swe-2-flash" }, { "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/jais-3-vs-swe-2-flash.json", "title": "Jais 3 vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/jais-3-vs-swe-2-flash" }, { "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/meta-model-api-vs-swe-2-flash.json", "title": "Meta Model API vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-swe-2-flash" }, { "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/minimax-api-vs-swe-2-flash.json", "title": "MiniMax API vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/minimax-api-vs-swe-2-flash" }, { "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/mistral-api-vs-swe-2-flash.json", "title": "Mistral AI API vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-novita-ai.json", "title": "Muse Spark Open vs Novita AI", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-novita-ai" }, { "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-swe-2-flash.json", "title": "Muse Spark Open vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-swe-2-flash.json", "title": "Nemotron 3.5 Super VL vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/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-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/openai-api-vs-swe-2-flash.json", "title": "OpenAI API vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/openai-api-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/openrouter-vs-swe-2-flash.json", "title": "OpenRouter vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/openrouter-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/prism-inference-vs-swe-2-flash.json", "title": "Prism Inference vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/prism-inference-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/ramp-router-vs-swe-2-flash.json", "title": "Router.com (Ramp Router) vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/ramp-router-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/reflection-beam-vs-swe-2-flash.json", "title": "Beam 1.0 vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/reflection-beam-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/routerplus-vs-swe-2-flash.json", "title": "RouterPlus vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/routerplus-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/sambanova-vs-swe-2-flash.json", "title": "SambaCloud vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/sambanova-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/siliconflow-vs-swe-2-flash.json", "title": "SiliconFlow vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/siliconflow-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/simplismart-vs-swe-2-flash.json", "title": "Simplismart vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/simplismart-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/stepfun-api-vs-swe-2-flash.json", "title": "StepFun API vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/stepfun-api-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/swe-2-flash-vs-tencent-tokenhub.json", "title": "SWE-2 Flash vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/swe-2-flash-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/swe-2-flash-vs-together-inference.json", "title": "SWE-2 Flash vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/swe-2-flash-vs-together-inference" }, { "json": "https://www.anchorterminal.com/compare/swe-2-flash-vs-vercel-ai-gateway.json", "title": "SWE-2 Flash vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/swe-2-flash-vs-vercel-ai-gateway" }, { "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": 22, "edge": "swe-2-flash", "key": "reliability", "name": "Reliability", "novita-ai": 28, "swe-2-flash": 50, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 33, "edge": "novita-ai", "key": "schema", "name": "Schema \u0026 documentation", "novita-ai": 62, "swe-2-flash": 29, "weight": 13 }, { "by": 62, "edge": "novita-ai", "key": "ergonomics", "name": "Agent ergonomics", "novita-ai": 72, "swe-2-flash": 10, "weight": 13 }, { "by": 12, "edge": "novita-ai", "key": "security", "name": "Security \u0026 auth", "novita-ai": 65, "swe-2-flash": 53, "weight": 14 }, { "by": 15, "edge": "novita-ai", "key": "payments", "name": "Payments \u0026 pricing", "novita-ai": 35, "swe-2-flash": 20, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 13, "edge": "novita-ai", "key": "maintenance", "name": "Maintenance \u0026 community", "novita-ai": 66, "swe-2-flash": 53, "weight": 7 }, { "by": 7, "edge": "swe-2-flash", "key": "transparency", "name": "Transparency \u0026 trust", "novita-ai": 57, "swe-2-flash": 64, "weight": 7 } ], "summary": "Novita AI scores 53.9 (D) on agent readiness against SWE-2 Flash's 36.4 (F), and leads in 5 of 7 scored categories. SWE-2 Flash leads on reliability and transparency \u0026 trust. Both do llm inference.", "tasks": null, "tutorials": [], "verdicts": { "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.", "swe-2-flash": "A new small coding model from Cognition that anyone can try free in Devin Desktop and Devin CLI until 30 November 2026, with strong vendor-reported coding scores. It has no model API, no published per-token price, context length or model card, and no public weights, so an agent can reach it only by driving Devin's own CLI." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/novita-ai-vs-swe-2-flash", "json": "https://www.anchorterminal.com/compare/novita-ai-vs-swe-2-flash.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/novita-ai-vs-swe-2-flash.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/novita-ai-vs-swe-2-flash.min.md" }, "markdown": "Novita AI scores 53.9 (D) on agent readiness against SWE-2 Flash's 36.4 (F), and leads in 5 of 7 scored categories. SWE-2 Flash leads on reliability and transparency \u0026 trust. Both do llm inference.\n\n- Novita AI: grade D, 53.9/100, rank #831 of 1350. Markdown https://www.anchorterminal.com/tools/novita-ai.md · JSON https://www.anchorterminal.com/api/v1/tools/novita-ai.json\n- SWE-2 Flash: grade F, 36.4/100, rank #1243 of 1350. Markdown https://www.anchorterminal.com/tools/swe-2-flash.md · JSON https://www.anchorterminal.com/api/v1/tools/swe-2-flash.json\n- Best model APIs and inference for AI agents: https://www.anchorterminal.com/best/inference/index.md\n- All 562 models comparisons: https://www.anchorterminal.com/compare/inference/index.md\n\n## Which one, for what\n\n### Novita AI (D)\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- Schema \u0026 documentation, 62 against 29\n- Agent ergonomics, 72 against 10\n- Security \u0026 auth, 65 against 53\n- Payments \u0026 pricing, 35 against 20\n- Maintenance \u0026 community, 66 against 53\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\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### SWE-2 Flash (F)\n\nGood for: People already using Devin Desktop or Devin CLI who want a cheaper, faster model for routine coding work such as automations, reviews and small changes, while it is free in November 2026.\n\nAhead on:\n- Reliability, 50 against 28\n- Transparency \u0026 trust, 64 against 57\n\nWatch for: No model API, OpenAPI entry or model card. The Devin API's session agents list SWE-2 but not SWE-2 Flash\n\n\n## Why the edge\n\n### Agent ergonomics: Novita AI +62\n\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- SWE-2 Flash (10): Model reading (tool use, structured output, caching, context, batch, SDKs). Tool use is Devin's harness, not something a caller configures; no context length, output limit or cache price is published for SWE-2 Flash (5 of 25). No documented output-size or reasoning controls for this model; SWE-2's effort levels aren't stated for Flash (0 of 20). No model-level error documentation (0 of 20). No idempotency or retry guidance (0 of 20). One flag or picker selects it and `devin -p` runs a single turn and prints to stdout, but there is no SDK or direct endpoint (5 of 15). 5 + 0 + 0 + 0 + 5 = 10.\n\n### Schema \u0026 documentation: Novita AI +33\n\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- SWE-2 Flash (29): Model reading. No model API, so no OpenAPI entry; the Devin v3 OpenAPI file lists SWE-2 agents only, and no model card was found (0). docs.devin.ai serves llms.txt and Markdown copies of every page (10). The launch post says what it is for (automations, code review, feature development, documentation) and the CLI docs say when to pick a SWE model, but the models pages don't list SWE-2 Flash yet (6 of 20). No documented model ID, reasoning settings, context or output limits to type (0 of 15). The CLI pages show `--model` and `/model` examples, with no model-specific errors (3 of 15). Named, dated model versions on Cognition's blog and public release notes, but no release note for SWE-2 Flash yet; the newest is 2 November (10 of 15). 0 + 10 + 6 + 0 + 3 + 10 = 29.\n\n### Reliability: SWE-2 Flash +22\n\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- SWE-2 Flash (50): Model reading, for the surface it runs on, Devin Desktop and Devin CLI. Status page at www.devinstatus.com (Atlassian Statuspage) with Desktop Agent and Desktop Tab components besides the cloud ones, read on 4 November 2026 (20). The history feed for the 90 days from 6 August lists 'Devin unavailable' for 20 minutes on 13 August with no component named, read as across the board and a major as on the devin listing; Devin Cloud unavailable on 13 August and the web app down on 24 September name cloud surfaces this model doesn't use; the rest are degraded-performance incidents (new sessions on 3 September, 'multiple services' on 17 September, Ask Devin on 26 October, automation triggers on 4 November) and session queuing on 10 and 11 August, read as minor and a scheduled Devin Desktop extension marketplace upgrade on 7 August, read as maintenance. One major (10). No rate limit figures for the model or the CLI; usage is a daily and weekly quota with no numbers (0). No 429, backoff or retry guidance for this surface (0). Cognition publishes an SLA (25 February 2026) with uptime and response times that applies when included in an order form, read as a contractual SLA on Enterprise, as on other listings (10). The launch post makes it available today with no preview or beta label (10). 20 + 10 + 0 + 0 + 10 + 10 = 50.\n\n### Payments \u0026 pricing: Novita AI +15\n\n- Novita AI (35): No machine payment protocol was found in the docs index, the site map, the pricing page or the skill repository (0). Per-token prices for each model on the pricing page without a login, such as `deepseek/deepseek-v4.1-flash` at $0.30 in and $1.20 out per 1M tokens (20). Two language models are listed as free and the FAQ describes a voucher for new users. Whether a card is needed to use either was not stated in the pages read (15 of 20). A person signs up in a browser, keys are created only in the console, and the OAuth route needs the user to sign in and approve (0). Per the 9 October check, not re-read on 4 November, as the terms bar automated access to the site and docs.\n- SWE-2 Flash (20): Published rubric. No payment protocol (0). Plan prices are public, but no per-token price for SWE-2 Flash is on a readable page; the docs' cost table loads in the browser and the post gives only 'one-fifth the price' of SWE-2 (10). Free through 30 November 2026 on Devin Desktop and CLI, but the docs say Free tier users only have SWE-1.6, so whether the Free plan reaches it, and without a card, isn't confirmed; the in-between value used on the devin listing (10). A person signs in through a browser (0). 0 + 10 + 10 + 0 = 20.\n\n### Maintenance \u0026 community: Novita AI +13\n\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- SWE-2 Flash (53): Model reading. Released 4 November 2026 (30). Churn and notice in place of release counts: SWE-1.6, SWE-1.7, SWE-1.7 Lightning, SWE-2 (10 September) and now SWE-2 Flash in a few months, with no model deprecation notice period found and short names that move to the newest model (10 of 20). Public release notes and a support address, no public tracker (10 of 25). No official SDK for the model (0 of 15). The docs are kept current but don't yet cover this model (3 of 10). 30 + 10 + 10 + 0 + 3 = 53.\n\n### Security \u0026 auth: Novita AI +12\n\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- SWE-2 Flash (53): Read as a hosted model reached through Devin's local clients. The CLI signs in through a browser, or the enterprise identity provider, and stores an API token in credentials.toml that by default is persistent and does not expire and carries the user's access, with no scopes found for it (10 of 30). Devin CLI documents an OS-level sandbox with network filtering, hooks that can block tool calls, and enterprise model allowlists and team settings (14 of 20). Guardrails against prompt injection are Enterprise only and cover user messages, as on the devin listing (8 of 15). Enterprise analytics count tool calls and consumption by model and user; no per-user audit log for the CLI was found (8 of 15). SOC 2 Type II and ISO/IEC 27001:2022, a disclosure address, no bug bounty and no security.txt, per the devin listing (13 of 20). Training: self-serve customer data may train Cognition's models by default, with an opt-out on paid plans that also turns on zero data retention at model providers. Cognition withheld the weights over cyber misuse, which is recorded as a fact, not scored. 10 + 14 + 8 + 8 + 13 = 53.\n\n## Score by category\n\n| Category | Weight | Novita AI | SWE-2 Flash | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 28 | 50 | SWE-2 Flash +22 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 62 | 29 | Novita AI +33 |\n| Agent ergonomics | 13% (16.2 this run) | 72 | 10 | Novita AI +62 |\n| Security \u0026 auth | 14% (17.5 this run) | 65 | 53 | Novita AI +12 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 35 | 20 | Novita AI +15 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 66 | 53 | Novita AI +13 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 57 | 64 | SWE-2 Flash +7 |\n| Negative events | ≤15 | 0 | -2 | |\n| **Total** | | **53.9 · D** | **36.4 · F** | |\n\n## Facts side by side\n\n| Fact | Novita AI | SWE-2 Flash |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Novita AI | Cognition AI, Inc. |\n| Hosted endpoint | `https://api.novita.ai/openai` | no (local only) |\n| Transports | HTTP | |\n| Auth | API key | OAuth or key |\n| Pricing | Pay per use | Freemium |\n| x402 | no | no |\n| Licence | Proprietary service under the Novita AI Terms of Service. The agent skill and the MCP server are MIT | Proprietary model, used through Devin Desktop and Devin CLI under Cognition's Platform Terms of Service. The weights are not public; Cognition says it is building a programme to share them with industry partners and researchers |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-22 | 2026-11-04 |\n| Terms last updated | 2026-08-05 | 2026-06-30 |\n| Privacy policy last updated | 2026-05-13 | 2026-03-09 |\n| Customer content may train models | not found in the text | yes, with an opt-out |\n| Terms restrict automated access | not found in the text | not found in the text |\n| Terms restrict benchmarking | not found in the text | yes |\n| Terms or service can change without notice | yes | not found in the text |\n| Arbitration or class-action waiver | yes | yes |\n| Popularity | 6 stars, 1.4k npm/wk | none |\n\n## How the scores have moved\n\n### Novita AI\n\n- +0.4 on 4 November 2026: new evidence\n- no change on 27 October 2026: checklist\n\n### SWE-2 Flash\n\nNo score change since it was listed.\n\n## Verdicts\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**SWE-2 Flash.** A new small coding model from Cognition that anyone can try free in Devin Desktop and Devin CLI until 30 November 2026, with strong vendor-reported coding scores. It has no model API, no published per-token price, context length or model card, and no public weights, so an agent can reach it only by driving Devin's own CLI.\n\n## Before you call either\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### SWE-2 Flash\n\n1. There is no endpoint to call. Run Devin CLI single-turn with `devin -p` and pick the model with `--model`; the SWE-2 Flash model ID isn't documented yet, so check `/model` in the CLI first\n2. Don't rely on the short name `swe`. The docs say it resolves to the latest model in the family, which may be SWE-2 rather than SWE-2 Flash\n3. Plan for billing to start on 1 December 2026. The free period covers Devin Desktop and CLI only, not Devin cloud sessions\n4. Treat Cognition's benchmark figures as the vendor's. No independent result for SWE-2 Flash was found\n5. Keep `credentials.toml` private. The token in it doesn't expire by default and carries the signed-in user's access\n\n## Questions\n\n### Which is better for AI agents, Novita AI or SWE-2 Flash?\n\nNovita AI scores 53.9 (D) on agent readiness against SWE-2 Flash's 36.4 (F), and leads in 5 of 7 scored categories. SWE-2 Flash leads on reliability and transparency \u0026 trust.\n\n### Do Novita AI and SWE-2 Flash need an API key?\n\nNovita AI needs an API key. SWE-2 Flash takes an API key or an OAuth sign-in.\n\n### Can an agent call Novita AI and SWE-2 Flash without installing anything?\n\nNovita AI has a hosted endpoint at https://api.novita.ai/openai. No hosted endpoint is listed for SWE-2 Flash.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/novita-ai-vs-swe-2-flash.json, and with the fewest tokens: https://www.anchorterminal.com/compare/novita-ai-vs-swe-2-flash.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"novita-ai\", \"b\": \"swe-2-flash\"}`. From a terminal: `anchor compare novita-ai swe-2-flash`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/novita-ai.json and https://www.anchorterminal.com/api/v1/tools/swe-2-flash.json\n\n## Other comparisons with Novita AI or SWE-2 Flash\n\n- [Claude API vs Novita AI](https://www.anchorterminal.com/compare/anthropic-api-vs-novita-ai.md)\n- [Claude API vs SWE-2 Flash](https://www.anchorterminal.com/compare/anthropic-api-vs-swe-2-flash.md)\n- [Antseed vs Novita AI](https://www.anchorterminal.com/compare/antseed-vs-novita-ai.md)\n- [Antseed vs SWE-2 Flash](https://www.anchorterminal.com/compare/antseed-vs-swe-2-flash.md)\n- [BlockRun.AI vs Novita AI](https://www.anchorterminal.com/compare/blockrun-ai-vs-novita-ai.md)\n- [BlockRun.AI vs SWE-2 Flash](https://www.anchorterminal.com/compare/blockrun-ai-vs-swe-2-flash.md)\n- [Cerebras Inference vs Novita AI](https://www.anchorterminal.com/compare/cerebras-inference-vs-novita-ai.md)\n- [Cerebras Inference vs SWE-2 Flash](https://www.anchorterminal.com/compare/cerebras-inference-vs-swe-2-flash.md)\n- [Cloudflare AI Gateway vs Novita AI](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-novita-ai.md)\n- [Cloudflare AI Gateway vs SWE-2 Flash](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-swe-2-flash.md)\n- [Cloudflare Workers AI vs Novita AI](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-novita-ai.md)\n- [Cloudflare Workers AI vs SWE-2 Flash](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-swe-2-flash.md)\n- [Cohere Chat API (Command models) vs Novita AI](https://www.anchorterminal.com/compare/cohere-chat-vs-novita-ai.md)\n- [Cohere Chat API (Command models) vs SWE-2 Flash](https://www.anchorterminal.com/compare/cohere-chat-vs-swe-2-flash.md)\n- [DeepInfra vs Novita AI](https://www.anchorterminal.com/compare/deepinfra-vs-novita-ai.md)\n- [DeepInfra vs SWE-2 Flash](https://www.anchorterminal.com/compare/deepinfra-vs-swe-2-flash.md)\n- [DeepSeek API vs Novita AI](https://www.anchorterminal.com/compare/deepseek-api-vs-novita-ai.md)\n- [DeepSeek API vs SWE-2 Flash](https://www.anchorterminal.com/compare/deepseek-api-vs-swe-2-flash.md)\n- [Glimpse vs Novita AI](https://www.anchorterminal.com/compare/elorian-glimpse-vs-novita-ai.md)\n- [Glimpse vs SWE-2 Flash](https://www.anchorterminal.com/compare/elorian-glimpse-vs-swe-2-flash.md)\n- [Fireworks AI Inference vs Novita AI](https://www.anchorterminal.com/compare/fireworks-inference-vs-novita-ai.md)\n- [Fireworks AI Inference vs SWE-2 Flash](https://www.anchorterminal.com/compare/fireworks-inference-vs-swe-2-flash.md)\n- [Gemini Developer API vs Novita AI](https://www.anchorterminal.com/compare/gemini-api-vs-novita-ai.md)\n- [Gemini Developer API vs SWE-2 Flash](https://www.anchorterminal.com/compare/gemini-api-vs-swe-2-flash.md)\n- [GroqCloud vs Novita AI](https://www.anchorterminal.com/compare/groq-vs-novita-ai.md)\n- [GroqCloud vs SWE-2 Flash](https://www.anchorterminal.com/compare/groq-vs-swe-2-flash.md)\n- [Jais 3 vs Novita AI](https://www.anchorterminal.com/compare/jais-3-vs-novita-ai.md)\n- [Jais 3 vs SWE-2 Flash](https://www.anchorterminal.com/compare/jais-3-vs-swe-2-flash.md)\n- [Meta Model API vs Novita AI](https://www.anchorterminal.com/compare/meta-model-api-vs-novita-ai.md)\n- [Meta Model API vs SWE-2 Flash](https://www.anchorterminal.com/compare/meta-model-api-vs-swe-2-flash.md)\n- [MiniMax API vs Novita AI](https://www.anchorterminal.com/compare/minimax-api-vs-novita-ai.md)\n- [MiniMax API vs SWE-2 Flash](https://www.anchorterminal.com/compare/minimax-api-vs-swe-2-flash.md)\n- [Mistral AI API vs Novita AI](https://www.anchorterminal.com/compare/mistral-api-vs-novita-ai.md)\n- [Mistral AI API vs SWE-2 Flash](https://www.anchorterminal.com/compare/mistral-api-vs-swe-2-flash.md)\n- [Muse Spark Open vs Novita AI](https://www.anchorterminal.com/compare/muse-spark-open-vs-novita-ai.md)\n- [Muse Spark Open vs SWE-2 Flash](https://www.anchorterminal.com/compare/muse-spark-open-vs-swe-2-flash.md)\n- [Nemotron 3.5 Super VL vs SWE-2 Flash](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-swe-2-flash.md)\n- [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 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- [OpenAI API vs SWE-2 Flash](https://www.anchorterminal.com/compare/openai-api-vs-swe-2-flash.md)\n- [OpenRouter vs SWE-2 Flash](https://www.anchorterminal.com/compare/openrouter-vs-swe-2-flash.md)\n- [Prism Inference vs SWE-2 Flash](https://www.anchorterminal.com/compare/prism-inference-vs-swe-2-flash.md)\n- [Router.com (Ramp Router) vs SWE-2 Flash](https://www.anchorterminal.com/compare/ramp-router-vs-swe-2-flash.md)\n- [Beam 1.0 vs SWE-2 Flash](https://www.anchorterminal.com/compare/reflection-beam-vs-swe-2-flash.md)\n- [RouterPlus vs SWE-2 Flash](https://www.anchorterminal.com/compare/routerplus-vs-swe-2-flash.md)\n- [SambaCloud vs SWE-2 Flash](https://www.anchorterminal.com/compare/sambanova-vs-swe-2-flash.md)\n- [SiliconFlow vs SWE-2 Flash](https://www.anchorterminal.com/compare/siliconflow-vs-swe-2-flash.md)\n- [Simplismart vs SWE-2 Flash](https://www.anchorterminal.com/compare/simplismart-vs-swe-2-flash.md)\n- [StepFun API vs SWE-2 Flash](https://www.anchorterminal.com/compare/stepfun-api-vs-swe-2-flash.md)\n- [SWE-2 Flash vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/swe-2-flash-vs-tencent-tokenhub.md)\n- [SWE-2 Flash vs Together AI Inference](https://www.anchorterminal.com/compare/swe-2-flash-vs-together-inference.md)\n- [SWE-2 Flash vs Vercel AI Gateway](https://www.anchorterminal.com/compare/swe-2-flash-vs-vercel-ai-gateway.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": "2026-11-05", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Novita AI vs SWE-2 Flash", "url": "" } ], "description": "Novita AI scores 53.9 (D) to SWE-2 Flash's 36.4 (F) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Novita AI D 53.9", "SWE-2 Flash F 36.4", "scores" ], "h1": "Novita AI vs SWE-2 Flash", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/novita-ai-vs-swe-2-flash", "published": "2026-10-01", "section": "tools", "title": "Novita AI vs SWE-2 Flash for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-04", "url": "https://www.anchorterminal.com/compare/novita-ai-vs-swe-2-flash" }, "tokens": { "markdown": 6550, "slim": 3630 }, "version": 1 }