{ "data": { "a": { "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" } }, "answer": "Vercel AI Gateway scores 67.8 (B) on agent readiness against SWE-2 Flash's 36.4 (F), and leads in 6 of 7 scored categories.", "b": { "slug": "vercel-ai-gateway", "name": "Vercel AI Gateway", "vendor": "Vercel Inc.", "vendorUrl": "https://vercel.com", "kind": "router", "category": "inference", "summary": "Vercel AI Gateway is a hosted router for model APIs. One API key or Vercel OIDC token reaches models from OpenAI, Anthropic, Google and others through OpenAI-compatible, Anthropic-compatible and AI SDK interfaces, with budgets, request logs and provider failover.", "url": "https://www.anchorterminal.com/tools/vercel-ai-gateway", "markdownUrl": "https://www.anchorterminal.com/tools/vercel-ai-gateway.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/vercel-ai-gateway.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/vercel-ai-gateway.json", "dns": "vercel-ai-gateway.grade.anchorterminal.com", "repo": "https://github.com/vercel/ai", "license": "Proprietary service under Vercel's Terms of Service and AI Product Terms, with Token Pass terms on its docs page. Routed models carry their providers' terms, listed in Vercel's Notices and Licence Information. The `@ai-sdk/gateway` provider is Apache-2.0", "transports": [ "http" ], "remoteUrl": "https://ai-gateway.vercel.sh/v1", "packages": [ { "registry": "npm", "name": "@ai-sdk/gateway" }, { "registry": "npm", "name": "ai" }, { "registry": "pypi", "name": "ai" } ], "auth": "mixed", "authNotes": "An AI Gateway API key as a Bearer token from any environment, or a Vercel OIDC token on Vercel deployments (12 hours locally, refreshed with `vercel env pull`). Keys belong to a team, can be limited to one project and given an expiry and a budget, and are created in the dashboard, with the Vercel CLI or by `POST /v1/api-keys` with a Vercel access token. A person creates the Vercel account in a browser. Token Pass needs its own Token Pass API key, and OIDC tokens cannot spend Token Pass credit.", "pricing": "usage", "pricingNotes": "Prepaid AI Gateway Credits at each provider's list price, with no markup or platform fee, including BYOK. A monthly free credit covers a subset of models and needs a valid payment method on the team. Credits expire a year after purchase. Add-ons are billed separately, and Token Pass is $30 a team a month on Pro for $80 of credit on two models, in early access (https://vercel.com/docs/ai-gateway/pricing, https://vercel.com/docs/ai-gateway/token-pass, checked 2026-10-17).", "priceSummary": "$30 / mo", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the AI Gateway docs, the pricing page, the Token Pass pages or the AI Gateway entries of the changelog sitemap. Payment is by prepaid credits bought with a card, or by invoice on Enterprise (checked 2026-10-17).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 29597661, "pypiWeekly": null, "asOf": "2026-10-17" }, "docsUrl": "https://vercel.com/docs/ai-gateway", "llmsTxt": "https://vercel.com/llms.txt", "openapi": "https://vercel.com/openapi.json", "capabilities": [ "inference.router", "inference.llm", "inference.fast", "inference.decision", "obs.gateway", "obs.traces", "embed.text", "image.generate", "video.generate" ], "tags": [ "hosted", "router", "usage-based", "prepaid", "free-tier", "openai-compatible", "anthropic-compatible", "llms-txt", "openapi", "typescript", "python", "oidc", "cli", "early-access", "status-page", "bug-bounty", "soc2", "iso27001" ], "lastRelease": "2026-10-30", "graded": true, "anchor": { "graded": true, "score": 67.8, "grade": "B", "agentReady": false, "rank": 277, "ranked": true, "rankOf": 1350, "categoryRank": 10, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 83, "maintenance": 79, "payments": 20, "reliability": 79, "schema": 74, "security": 79, "transparency": 71 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": -3, "negativeNotes": [ "April 2026. Vercel's security bulletin says an attacker took over an employee's account through a compromised third-party AI tool, reached internal systems and decrypted non-sensitive environment variables of a limited subset of customers. AI Gateway was generally available then, and its docs have deployments keep AI Gateway and Token Pass API keys as environment variables. The bulletin documents remediation and marks the incident closed on 16 October 2026, so 3 of a possible 15 is taken, as for vercel-connect (https://vercel.com/kb/bulletin/vercel-april-2026-security-incident)." ], "verdict": "Token prices pass through with no markup, prompts are not stored by the gateway, and budgets, provider failover and per-request logs are built in. The free monthly credit needs a card on file, rate limits are not published as numbers, no SLA covers the API, and the contractual promise not to train on content applies to Enterprise subscriptions only.", "bestFor": "Teams that want one key, one bill, budgets and failover in front of many model providers, especially on Vercel with OIDC.", "strengths": [ "Token prices are each provider's list price with no markup or platform fee, including requests made with the customer's own provider keys", "The model list at `GET /v1/models` needs no key and gives prices, context windows, supported parameters and ZDR and no-training flags for 498 models", "Budgets per team, project, API key or team member reject spend with a 402, distinct from a 429 rate limit", "The gateway logs request metadata only. Prompt and response content is deleted when the request completes, per the FAQ and the ZDR page", "Failed provider attempts are retried on a model's other providers, and every routing attempt appears in the request logs" ], "weaknesses": [ "The free monthly credit needs a valid payment method on the team, and its amount is not stated in the reviewed docs", "No rate-limit numbers are published, and the Enterprise SLA excludes the APIs, so the inference API carries no uptime commitment", "The contractual promise not to train on AI Gateway content covers Enterprise subscriptions only. Provider no-training and ZDR filters are opt-in per request", "A failed BYOK request falls back to Vercel's credentials and is billed to credits, and the no-training filter is not applied to BYOK", "Token Pass is early access for Pro teams only, covers two models, has no failover and fails with a 403 once the $80 credit is spent" ], "agentNotes": [ "Read `GET https://ai-gateway.vercel.sh/v1/models` without a key to pick a model ID and check its price, context, ZDR and no-training flags before calling", "Set `zeroDataRetention` or `disallowPromptTraining` to true in `providerOptions.gateway` on sensitive requests. Default routing ignores provider retention and training policies", "Treat a 429 as retryable and honour `retry-after` when present. A 402 with `quota_for_entity_exceeded` is a spent budget, so do not retry it", "On a Token Pass key, a 403 with `no_providers_available` means spent credit or a model outside the pass. Retry with a standard AI Gateway key, which bills credits", "Set `inferenceRegion` when data residency matters. The default `global` may run inference outside the user's jurisdiction" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 67.8 } ], "editorialScores": { "ergonomics": 83, "maintenance": 79, "payments": 20, "reliability": 79, "schema": 74, "security": 79, "transparency": 55 }, "provenanceScore": 86, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "lastMoved": "2026-11-01", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pnpm add ai@latest", "http": "curl https://ai-gateway.vercel.sh/v1/chat/completions \\\n -H \"Authorization: Bearer $AI_GATEWAY_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"model\": \"openai/gpt-6-astra\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Explain AI Gateway in one sentence.\"\n }\n ]\n }'" }, "letme": { "capability": "https://letme.dev/inference.router", "tool": "https://letme.dev/vercel-ai-gateway" }, "sameCompany": [ "vercel-sandbox", "vercel-connect" ], "area": "models", "unitPrices": [ { "item": "Token Pass subscription (Pro teams)", "unit": "month", "usd": 30, "note": "$80 of monthly credit on two featured models. Early access" }, { "item": "Team-wide Zero Data Retention", "unit": "1k-requests", "usd": 0.1, "note": "Pro and Enterprise. Per-request ZDR is free" }, { "item": "Team-wide provider allowlist", "unit": "1k-requests", "usd": 0.1, "note": "Successful requests, Pro and Enterprise" }, { "item": "Custom Reporting query", "unit": "1k-requests", "usd": 5, "note": "Queries to the reporting endpoint" }, { "item": "Custom Reporting write of a tag, user ID or quota entity ID", "unit": "1k-requests", "usd": 0.075, "note": "Each unique value in a request counts as one write" }, { "item": "AI Gateway trace delivered to a drain", "unit": "1k-requests", "usd": 0.05, "note": "Listed per 1,000 traces, Pro and Enterprise" }, { "item": "Trace egress", "unit": "gb", "usd": 0.5, "note": "Billed through Drains usage" } ], "provenance": { "legalEntity": "Vercel Inc.", "domain": "vercel.com", "domainRegistered": "1999-10-04", "endpointOnVendorDomain": false, "terms": "https://vercel.com/legal/terms", "privacy": "https://vercel.com/legal/privacy-policy", "statusPage": "https://www.vercel-status.com", "changelog": "https://vercel.com/changelog", "securityTxt": "valid", "checked": "2026-11-01", "notes": [ "The Terms of Service (last updated 19 October 2026) name Vercel Inc. The AI Product Terms (last updated 17 March 2026, effective 31 March 2026) have a section for AI Gateway and form part of those terms.", "The Privacy Notice is effective from 1 June 2026. The DPA (effective 31 March 2026) applies to Pro and Enterprise plans.", "https://vercel.com/.well-known/security.txt points to HackerOne and responsible.disclosure@vercel.com and expires 2027-09-28 (re-read 1 November 2026).", "The API answers at ai-gateway.vercel.sh, a Vercel domain other than vercel.com. Management calls go to api.vercel.com.", "RDAP gives vercel.com a registration date of 1999-10-04, long before Vercel, so the domain was bought later.", "AI Gateway is a component on the status page at www.vercel-status.com." ], "score": 86 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/vercel-ai-gateway.json", "live": { "slug": "vercel-ai-gateway", "probe": { "target": "https://ai-gateway.vercel.sh/v1", "method": "get", "lastAt": "2026-11-05T01:29:26.398936679Z", "lastOk": true, "lastStatus": 404, "lastMs": 34, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 38, "p95ms24h": 107, "samples24h": 247, "samples30d": 4548, "days": [ { "date": "2026-10-17", "probes": 21, "ok": 21 }, { "date": "2026-10-18", "probes": 256, "ok": 256 }, { "date": "2026-10-19", "probes": 255, "ok": 255 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 253, "ok": 253 }, { "date": "2026-10-22", "probes": 253, "ok": 253 }, { "date": "2026-10-23", "probes": 248, "ok": 248 }, { "date": "2026-10-24", "probes": 251, "ok": 251 }, { "date": "2026-10-25", "probes": 250, "ok": 250 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 250, "ok": 250 }, { "date": "2026-10-29", "probes": 249, "ok": 249 }, { "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 } ] }, "vendorStatus": { "page": "https://www.vercel-status.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-05T01:27:55.372564965Z" }, "versions": [ { "registry": "github", "name": "vercel/ai", "version": "@ai-sdk/deepinfra@1.0.64", "released": "2026-11-03", "seenAt": "2026-11-04T21:04:03.132790411Z" }, { "registry": "npm", "name": "@ai-sdk/gateway", "version": "4.0.135", "seenAt": "2026-11-04T21:04:00.711278753Z" }, { "registry": "npm", "name": "ai", "version": "7.0.162", "seenAt": "2026-11-04T21:04:01.663524941Z" }, { "registry": "pypi", "name": "ai", "version": "0.9.0", "released": "2026-11-04", "seenAt": "2026-11-04T21:04:03.003998171Z" } ], "githubStars": 27740, "npmWeekly": 42322239, "pypiWeekly": 24138, "securityTxt": { "url": "https://vercel.com/.well-known/security.txt", "state": "valid", "expires": "2027-09-28T12:00:00.000Z", "checkedAt": "2026-11-04T15:54:47.333334939Z" }, "llmsTxt": { "url": "https://vercel.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-04T15:24:29.681916955Z" }, "domain": { "domain": "vercel.com", "registered": "1999-10-04", "source": "https://rdap.verisign.com/com/v1/domain/vercel.com", "checkedAt": "2026-11-01T14:26:56.031194695Z" }, "pages": [ { "url": "https://vercel.com/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-11-04T08:35:50.237936319Z", "changedAt": "2026-11-04T08:35:50.237936319Z", "fingerprint": "bd4937bba01c" }, { "url": "https://ai-gateway.vercel.sh/v1/models", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-04T08:14:38.356706112Z", "changedAt": "0001-01-01T00:00:00Z" }, { "url": "https://vercel.com/changelog/laya-decision-model-now-available-on-ai-gateway-free-through-october-31", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-04T08:35:53.606482563Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "6bbbff189272" }, { "url": "https://vercel.com/changelog/tako-search-is-free-on-ai-gateway-through-september-30th", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-04T08:35:54.625535244Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "196bc432bb9c" }, { "url": "https://vercel.com/docs/ai-gateway/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-04T08:35:56.719108995Z", "changedAt": "2026-11-04T08:35:56.719108995Z", "fingerprint": "3b18d278aa25" }, { "url": "https://vercel.com/legal/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-04T08:36:02.623105814Z", "changedAt": "2026-10-28T04:46:11.674155692Z", "fingerprint": "c545eb853c20" }, { "url": "https://vercel.com/legal/terms", "kind": "terms", "status": 200, "checkedAt": "2026-11-04T08:36:04.92350913Z", "changedAt": "2026-10-28T04:46:13.475126487Z", "fingerprint": "100a29fa0aba" } ], "github": { "repo": "vercel/ai", "checkedAt": "2026-11-02T09:35:36.328615652Z", "stars": 27693, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-02T09:18:34Z", "openIssues": 505, "openPRs": 1043, "issuesOpened90d": 1077, "issuesClosed90d": 1415, "prsMerged90d": 2573, "ci": { "branch": "main", "runs": 50, "success": 48, "failure": 2, "other": 0, "latest": "success", "latestAt": "2026-11-02T05:34:51Z" }, "advisories": [ { "ghsa": "GHSA-g3x3-7q3h-gmhj", "severity": "medium", "published": "2026-10-01T19:22:11Z" }, { "ghsa": "GHSA-4mqq-99j3-3hmv", "severity": "high", "published": "2026-09-28T17:44:55Z" }, { "ghsa": "GHSA-222v-gj5h-ff73", "severity": "high", "published": "2026-08-20T21:21:04Z" }, { "ghsa": "GHSA-vmqp-7rwf-cq3w", "severity": "medium", "published": "2026-08-14T01:39:36Z" }, { "ghsa": "GHSA-qw9h-448j-6rph", "cve": "CVE-2026-64650", "severity": "medium", "published": "2026-07-20T20:16:06Z" }, { "ghsa": "GHSA-g48p-5rr5-8rgq", "cve": "CVE-2026-64651", "severity": "medium", "published": "2026-07-20T20:15:50Z" } ], "replies": { "sampled": 25, "unanswered": 14, "medianDays": 0.1 } }, "updatedAt": "2026-11-05T01:29:26.398936679Z" } }, "edges": [ { "by": 73, "category": "ergonomics", "leads": "vercel-ai-gateway", "name": "Agent ergonomics", "reasons": { "a": "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.", "b": "Router, read on the model lines. Tool calling is documented on all six surfaces and 303 of 498 models carry the tool-use tag on 1 November, with behaviour depending on the model routed (16 of 20). Structured output is documented per surface and tagged on 278 models (13 of 15). `caching: 'auto'` adds Anthropic cache markers, `cache_ttl` asks for one-hour entries, `x-session-affinity` keeps a conversation on one provider, and cache-read prices are listed per model (14 of 15). 162 models list a context of one million tokens or more, a judgement call since a router has no default model (15). The SDK source has a `gateway-batch.ts` file, but no batch endpoint or batch discount was found in the docs (2 of 10). The AI SDK for TypeScript, the AI SDK for Python in beta, and the OpenAI and Anthropic SDKs with a changed base URL (10). Errors return `message` and `type`, an exceeded budget answers 402 apart from a 429, the SDK has ten typed `Gateway*Error` classes, and the FAQ maps each status to a fix (13 of 15)." }, "scores": { "a": 10, "b": 83 } }, { "by": 45, "category": "schema", "leads": "vercel-ai-gateway", "name": "Schema \u0026 documentation", "reasons": { "a": "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.", "b": "Router, scored on the API lines. Vercel's OpenAPI 3.0.3 document has AI Gateway management paths (budgets, routing rules, virtual model configs, routers) and `POST /api-keys`. It does not cover the inference routes on ai-gateway.vercel.sh or `/v1/models`, `/v1/credits`, `/v1/generation` and `/v1/report`, which follow the OpenAI and Anthropic formats and the REST reference page (12 of 25). Every docs page is served as Markdown, and vercel.com/llms.txt lists AI Gateway and the keyless model list (10). The docs say when to use AI Gateway, which API format suits which client, and what each control leaves out, such as BYOK spend outside budgets (16 of 20). `providerOptions.gateway` fields are documented in tables with types, and the model list names each model's supported parameters. The request bodies have no published schema of their own (9 of 15). cURL, TypeScript and Python examples on most pages, and error tables in the FAQ, the REST reference and the Token Pass pages. The Chat Completions error list omits 402 (13 of 15). Paths carry `/v1`, the changelog is dated, with 95 entries naming AI Gateway from 3 August to 30 October 2026, and `@ai-sdk/gateway` keeps a CHANGELOG. The changelog sitemap dates one AI Gateway entry to 25 March 2025, before the alpha (14 of 15)." }, "scores": { "a": 29, "b": 74 } }, { "by": 29, "category": "reliability", "leads": "vercel-ai-gateway", "name": "Reliability", "reasons": { "a": "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.", "b": "Hosted reading. AI Gateway is a component on www.vercel-status.com (20). The history feed, re-read on 1 November 2026, has 25 entries from 23 July to 23 October, so it covers the whole 90 days from 3 August. None names AI Gateway in its title or text. The Drains, Logs and Observability incidents (6, 17 and 20 August, 16 to 17 September, 10 October in Washington, which names delayed logs, metrics and traces in general, and 23 October) name no AI Gateway surface, and none reports requests failing. Component tags sit in the status API, which robots.txt disallows, so they were not used. A readable page that posts incidents, none touching the product, is a clean record, as vercel-connect's incidents were read from the same feed (30). The rate-limit page, re-read on 1 November, says it describes behaviour rather than fixed numbers. The paid tier has no gateway limit, and the free tier's per-model limits are not published (5 of 15). A 429 has a documented JSON body, some carry `retry-after`, the docs give backoff code and separate a 429 from a 402 budget rejection, and failed provider attempts are retried on other providers (14 of 15). The Enterprise SLA excludes the APIs and CLI, and no SLA naming AI Gateway was found (0). Generally available since 21 August 2025. Token Pass is early access and the Python SDK is in beta (10)." }, "scores": { "a": 50, "b": 79 } }, { "by": 26, "category": "security", "leads": "vercel-ai-gateway", "name": "Security \u0026 auth", "reasons": { "a": "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.", "b": "Router, read on the model lines. AI Gateway API keys belong to a team, can be limited to one project and given an expiry and a budget, are deactivated when their creator leaves the team, and can be revoked without authentication by reporting a leaked key. Keys carry no per-model or read-only scope apart from the Token Pass key type. On Vercel, project OIDC tokens replace long-lived keys (24 of 30). Vercel says it does not train on prompts, and the AI Product Terms make that a warranty only for Enterprise subscriptions. Provider training is filtered only when `disallowPromptTraining` or ZDR is set, the filter does not apply to BYOK, and the terms say Stealth Model providers may train on inputs (12 of 20). The gateway does not keep prompt or response content. Provider ZDR is free per request on Pro and Enterprise and not available on Hobby, and BYOK keys are skipped under ZDR unless marked (12 of 15). Per-request logs record status, provider attempts, tokens, cost and authentication method, with routing details kept 30 days and Trace Drains and spend reports on paid plans (13 of 15). Valid security.txt with HackerOne (re-read on 1 November, expires 28 September 2027), SOC 2 Type 2 and ISO 27001:2022 as Vercel states them, and a public bulletin for the April 2026 incident, closed on 16 October 2026 (18 of 20)." }, "scores": { "a": 53, "b": 79 } }, { "by": 26, "category": "maintenance", "leads": "vercel-ai-gateway", "name": "Maintenance \u0026 community", "reasons": { "a": "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.", "b": "Closed service, read on the model lines. The newest changelog entry naming AI Gateway is dated 30 October 2026 (30). Twelve models in the model list carry a `deprecated_at` date on 1 November, from 5 November 2026 (4 days ahead) to 26 February 2027. No minimum notice period was found, and access to Claude Fable 5 was suspended on 12 June 2026 under a government directive without notice and restored on 1 July (6 of 12). No AI Gateway endpoint was shut down in the last 90 days that we found (7 of 8). 95 changelog entries name AI Gateway from 3 August to 30 October 2026, and support runs from the dashboard (13 of 15). Replies to issues on vercel/ai were not read, because GitHub's pages refuse our reader (3 of 10). `@ai-sdk/gateway` is at 4.0.132 in vercel/ai, versioned on 30 October 2026, and had 29,597,661 npm downloads in the week to 12 October per the 17 October check. The Python SDK is in beta (14 of 15). Three runtime dependencies and a test file beside most modules. CI was not checked (6 of 10)." }, "scores": { "a": 53, "b": 79 } }, { "by": 7, "category": "transparency", "leads": "vercel-ai-gateway", "name": "Transparency \u0026 trust", "reasons": { "a": "Editorial half. Closed model under Cognition's platform terms; the weights aren't public and the sharing programme isn't described yet (15). Terms, privacy policy, security page and DPA agree, with training on self-serve data by default and no retention periods, as read for the devin listing (18). The API versioning policy covers API endpoints, not models, and no model deprecation notice was found (5 of 20). Sub-processors listed with purpose and country, per the devin listing's 8 October check (18). 15 + 18 + 5 + 18 = 56.", "b": "Closed service under the Terms of Service last updated 19 October 2026, the AI Product Terms with an AI Gateway section, and Token Pass terms on its docs page. Routed models carry the terms of 64 providers listed in the Notices and Licence Information, and the SDK is Apache-2.0 (18 of 30). The FAQ, the ZDR page and the logs page agree that prompt and response content is not kept. The terms place content sent to providers under the providers' own terms, give the no-training warranty only to Enterprise and bar sensitive personal information in Input. The DPA covers Pro and Enterprise, not Hobby, and the privacy notice gives retention criteria, not periods (17 of 30). No deprecation policy found. Model retirements carry dates in the model list, and the AI Product Terms let Vercel change fees, change or end anything in beta without notice, and end Token Pass with a pro-rata refund (8 of 20). Provider terms are listed per provider and regional inference names four regions, while the gateway itself may process a request in any Vercel region. The subprocessor list on security.vercel.com was not read (12 of 20)." }, "scores": { "a": 64, "b": 71 } } ], "facts": [ { "a": "Model API", "b": "Model router", "name": "Kind" }, { "a": "Cognition AI, Inc.", "b": "Vercel Inc.", "name": "Vendor" }, { "a": "no (local only)", "b": "https://ai-gateway.vercel.sh/v1", "name": "Hosted endpoint" }, { "a": "", "b": "HTTP", "name": "Transports" }, { "a": "OAuth or key", "b": "OAuth or key", "name": "Auth" }, { "a": "Freemium", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "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", "b": "Proprietary service under Vercel's Terms of Service and AI Product Terms, with Token Pass terms on its docs page. Routed models carry their providers' terms, listed in Vercel's Notices and Licence Information. The `@ai-sdk/gateway` provider is Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-11-04", "b": "2026-10-30", "name": "Last release" }, { "a": "2026-06-30", "b": "2026-06-01", "name": "Terms last updated" }, { "a": "2026-03-09", "b": "2026-06-01", "name": "Privacy policy last updated" }, { "a": "yes, with an opt-out", "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": "yes", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "29.6M npm/wk", "name": "Popularity" }, { "a": "none", "b": "3/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Vercel AI Gateway scores 67.8 (B) on agent readiness against SWE-2 Flash's 36.4 (F), and leads in 6 of 7 scored categories.", "question": "Which is better for AI agents, SWE-2 Flash or Vercel AI Gateway?" }, { "answer": "Both take an API key or an OAuth sign-in.", "question": "Do SWE-2 Flash and Vercel AI Gateway need an API key?" }, { "answer": "No hosted endpoint is listed for SWE-2 Flash. Vercel AI Gateway has a hosted endpoint at https://ai-gateway.vercel.sh/v1.", "question": "Can an agent call SWE-2 Flash and Vercel AI Gateway without installing anything?" } ], "goodFor": [ { "aheadOn": null, "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" }, { "aheadOn": [ "Reliability, 79 against 50", "Schema \u0026 documentation, 74 against 29", "Agent ergonomics, 83 against 10", "Security \u0026 auth, 79 against 53", "Maintenance \u0026 community, 79 against 53", "Transparency \u0026 trust, 71 against 64" ], "also": [ "A hosted endpoint, with nothing to install" ], "goodFor": "Teams that want one key, one bill, budgets and failover in front of many model providers, especially on Vercel with OIDC.", "slug": "vercel-ai-gateway", "watchFor": "The free monthly credit needs a valid payment method on the team, and its amount is not stated in the reviewed docs" } ], "history": { "swe-2-flash": null, "vercel-ai-gateway": [ { "causes": [ "correction" ], "date": "2026-11-01", "delta": 1, "from": 66.8, "fromGrade": "B", "to": 67.8, "toGrade": "B" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 66.7, "fromGrade": "B", "to": 66.8, "toGrade": "B" } ] }, "job": { "capability": "inference.llm", "name": "LLM inference" }, "others": [ { "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/anthropic-api-vs-vercel-ai-gateway.json", "title": "Claude API vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-vercel-ai-gateway" }, { "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-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/blockrun-ai-vs-vercel-ai-gateway.json", "title": "BlockRun.AI vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-vercel-ai-gateway" }, { "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/cerebras-inference-vs-vercel-ai-gateway.json", "title": "Cerebras Inference vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-vercel-ai-gateway" }, { "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-ai-gateway-vs-vercel-ai-gateway.json", "title": "Cloudflare AI Gateway vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-vercel-ai-gateway" }, { "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/cloudflare-workers-ai-vs-vercel-ai-gateway.json", "title": "Cloudflare Workers AI vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-vercel-ai-gateway" }, { "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/cohere-chat-vs-vercel-ai-gateway.json", "title": "Cohere Chat API (Command models) vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-vercel-ai-gateway" }, { "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/deepinfra-vs-vercel-ai-gateway.json", "title": "DeepInfra vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/deepinfra-vs-vercel-ai-gateway" }, { "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/deepseek-api-vs-vercel-ai-gateway.json", "title": "DeepSeek API vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-vercel-ai-gateway" }, { "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/elorian-glimpse-vs-vercel-ai-gateway.json", "title": "Glimpse vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-vercel-ai-gateway" }, { "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/fireworks-inference-vs-vercel-ai-gateway.json", "title": "Fireworks AI Inference vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-vercel-ai-gateway" }, { "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/gemini-api-vs-vercel-ai-gateway.json", "title": "Gemini Developer API vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/gemini-api-vs-vercel-ai-gateway" }, { "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/groq-vs-vercel-ai-gateway.json", "title": "GroqCloud vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/groq-vs-vercel-ai-gateway" }, { "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/jais-3-vs-vercel-ai-gateway.json", "title": "Jais 3 vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/jais-3-vs-vercel-ai-gateway" }, { "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/meta-model-api-vs-vercel-ai-gateway.json", "title": "Meta Model API vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-vercel-ai-gateway" }, { "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/minimax-api-vs-vercel-ai-gateway.json", "title": "MiniMax API vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/minimax-api-vs-vercel-ai-gateway" }, { "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/mistral-api-vs-vercel-ai-gateway.json", "title": "Mistral AI API vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-swe-2-flash.json", "title": "Muse Spark Open vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-vercel-ai-gateway.json", "title": "Muse Spark Open vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-swe-2-flash.json", "title": "Nemotron 3.5 Super VL vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-vercel-ai-gateway.json", "title": "Nemotron 3.5 Super VL vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/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-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/openai-api-vs-vercel-ai-gateway.json", "title": "OpenAI API vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/openai-api-vs-vercel-ai-gateway" }, { "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/openrouter-vs-vercel-ai-gateway.json", "title": "OpenRouter vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/openrouter-vs-vercel-ai-gateway" }, { "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/reflection-beam-vs-vercel-ai-gateway.json", "title": "Beam 1.0 vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/reflection-beam-vs-vercel-ai-gateway" }, { "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/sambanova-vs-vercel-ai-gateway.json", "title": "SambaCloud vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/sambanova-vs-vercel-ai-gateway" }, { "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/siliconflow-vs-vercel-ai-gateway.json", "title": "SiliconFlow vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/siliconflow-vs-vercel-ai-gateway" }, { "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/simplismart-vs-vercel-ai-gateway.json", "title": "Simplismart vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/simplismart-vs-vercel-ai-gateway" }, { "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/stepfun-api-vs-vercel-ai-gateway.json", "title": "StepFun API vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/stepfun-api-vs-vercel-ai-gateway" }, { "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/together-inference-vs-vercel-ai-gateway.json", "title": "Together AI Inference vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/together-inference-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/antseed-vs-vercel-ai-gateway.json", "title": "Antseed vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/antseed-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/ramp-router-vs-vercel-ai-gateway.json", "title": "Router.com (Ramp Router) vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/ramp-router-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/routerplus-vs-vercel-ai-gateway.json", "title": "RouterPlus vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/routerplus-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/tencent-tokenhub-vs-vercel-ai-gateway.json", "title": "Tencent Cloud TokenHub vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/tencent-tokenhub-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/prism-inference-vs-vercel-ai-gateway.json", "title": "Prism Inference vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/prism-inference-vs-vercel-ai-gateway" } ], "panel": null, "scores": [ { "by": 29, "edge": "vercel-ai-gateway", "key": "reliability", "name": "Reliability", "swe-2-flash": 50, "vercel-ai-gateway": 79, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 45, "edge": "vercel-ai-gateway", "key": "schema", "name": "Schema \u0026 documentation", "swe-2-flash": 29, "vercel-ai-gateway": 74, "weight": 13 }, { "by": 73, "edge": "vercel-ai-gateway", "key": "ergonomics", "name": "Agent ergonomics", "swe-2-flash": 10, "vercel-ai-gateway": 83, "weight": 13 }, { "by": 26, "edge": "vercel-ai-gateway", "key": "security", "name": "Security \u0026 auth", "swe-2-flash": 53, "vercel-ai-gateway": 79, "weight": 14 }, { "by": 0, "edge": "", "key": "payments", "name": "Payments \u0026 pricing", "swe-2-flash": 20, "vercel-ai-gateway": 20, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 26, "edge": "vercel-ai-gateway", "key": "maintenance", "name": "Maintenance \u0026 community", "swe-2-flash": 53, "vercel-ai-gateway": 79, "weight": 7 }, { "by": 7, "edge": "vercel-ai-gateway", "key": "transparency", "name": "Transparency \u0026 trust", "swe-2-flash": 64, "vercel-ai-gateway": 71, "weight": 7 } ], "summary": "Vercel AI Gateway scores 67.8 (B) on agent readiness against SWE-2 Flash's 36.4 (F), and leads in 6 of 7 scored categories. Both do llm inference.", "tasks": null, "tutorials": [], "verdicts": { "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.", "vercel-ai-gateway": "Token prices pass through with no markup, prompts are not stored by the gateway, and budgets, provider failover and per-request logs are built in. The free monthly credit needs a card on file, rate limits are not published as numbers, no SLA covers the API, and the contractual promise not to train on content applies to Enterprise subscriptions only." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/swe-2-flash-vs-vercel-ai-gateway", "json": "https://www.anchorterminal.com/compare/swe-2-flash-vs-vercel-ai-gateway.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/swe-2-flash-vs-vercel-ai-gateway.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/swe-2-flash-vs-vercel-ai-gateway.min.md" }, "markdown": "Vercel AI Gateway scores 67.8 (B) on agent readiness against SWE-2 Flash's 36.4 (F), and leads in 6 of 7 scored categories. Both do llm inference.\n\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- Vercel AI Gateway: grade B, 67.8/100, rank #277 of 1350. Markdown https://www.anchorterminal.com/tools/vercel-ai-gateway.md · JSON https://www.anchorterminal.com/api/v1/tools/vercel-ai-gateway.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### 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\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### Vercel AI Gateway (B)\n\nGood for: Teams that want one key, one bill, budgets and failover in front of many model providers, especially on Vercel with OIDC.\n\nAhead on:\n- Reliability, 79 against 50\n- Schema \u0026 documentation, 74 against 29\n- Agent ergonomics, 83 against 10\n- Security \u0026 auth, 79 against 53\n- Maintenance \u0026 community, 79 against 53\n- Transparency \u0026 trust, 71 against 64\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: The free monthly credit needs a valid payment method on the team, and its amount is not stated in the reviewed docs\n\n\n## Why the edge\n\n### Agent ergonomics: Vercel AI Gateway +73\n\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- Vercel AI Gateway (83): Router, read on the model lines. Tool calling is documented on all six surfaces and 303 of 498 models carry the tool-use tag on 1 November, with behaviour depending on the model routed (16 of 20). Structured output is documented per surface and tagged on 278 models (13 of 15). `caching: 'auto'` adds Anthropic cache markers, `cache_ttl` asks for one-hour entries, `x-session-affinity` keeps a conversation on one provider, and cache-read prices are listed per model (14 of 15). 162 models list a context of one million tokens or more, a judgement call since a router has no default model (15). The SDK source has a `gateway-batch.ts` file, but no batch endpoint or batch discount was found in the docs (2 of 10). The AI SDK for TypeScript, the AI SDK for Python in beta, and the OpenAI and Anthropic SDKs with a changed base URL (10). Errors return `message` and `type`, an exceeded budget answers 402 apart from a 429, the SDK has ten typed `Gateway*Error` classes, and the FAQ maps each status to a fix (13 of 15).\n\n### Schema \u0026 documentation: Vercel AI Gateway +45\n\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- Vercel AI Gateway (74): Router, scored on the API lines. Vercel's OpenAPI 3.0.3 document has AI Gateway management paths (budgets, routing rules, virtual model configs, routers) and `POST /api-keys`. It does not cover the inference routes on ai-gateway.vercel.sh or `/v1/models`, `/v1/credits`, `/v1/generation` and `/v1/report`, which follow the OpenAI and Anthropic formats and the REST reference page (12 of 25). Every docs page is served as Markdown, and vercel.com/llms.txt lists AI Gateway and the keyless model list (10). The docs say when to use AI Gateway, which API format suits which client, and what each control leaves out, such as BYOK spend outside budgets (16 of 20). `providerOptions.gateway` fields are documented in tables with types, and the model list names each model's supported parameters. The request bodies have no published schema of their own (9 of 15). cURL, TypeScript and Python examples on most pages, and error tables in the FAQ, the REST reference and the Token Pass pages. The Chat Completions error list omits 402 (13 of 15). Paths carry `/v1`, the changelog is dated, with 95 entries naming AI Gateway from 3 August to 30 October 2026, and `@ai-sdk/gateway` keeps a CHANGELOG. The changelog sitemap dates one AI Gateway entry to 25 March 2025, before the alpha (14 of 15).\n\n### Reliability: Vercel AI Gateway +29\n\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- Vercel AI Gateway (79): Hosted reading. AI Gateway is a component on www.vercel-status.com (20). The history feed, re-read on 1 November 2026, has 25 entries from 23 July to 23 October, so it covers the whole 90 days from 3 August. None names AI Gateway in its title or text. The Drains, Logs and Observability incidents (6, 17 and 20 August, 16 to 17 September, 10 October in Washington, which names delayed logs, metrics and traces in general, and 23 October) name no AI Gateway surface, and none reports requests failing. Component tags sit in the status API, which robots.txt disallows, so they were not used. A readable page that posts incidents, none touching the product, is a clean record, as vercel-connect's incidents were read from the same feed (30). The rate-limit page, re-read on 1 November, says it describes behaviour rather than fixed numbers. The paid tier has no gateway limit, and the free tier's per-model limits are not published (5 of 15). A 429 has a documented JSON body, some carry `retry-after`, the docs give backoff code and separate a 429 from a 402 budget rejection, and failed provider attempts are retried on other providers (14 of 15). The Enterprise SLA excludes the APIs and CLI, and no SLA naming AI Gateway was found (0). Generally available since 21 August 2025. Token Pass is early access and the Python SDK is in beta (10).\n\n### Security \u0026 auth: Vercel AI Gateway +26\n\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- Vercel AI Gateway (79): Router, read on the model lines. AI Gateway API keys belong to a team, can be limited to one project and given an expiry and a budget, are deactivated when their creator leaves the team, and can be revoked without authentication by reporting a leaked key. Keys carry no per-model or read-only scope apart from the Token Pass key type. On Vercel, project OIDC tokens replace long-lived keys (24 of 30). Vercel says it does not train on prompts, and the AI Product Terms make that a warranty only for Enterprise subscriptions. Provider training is filtered only when `disallowPromptTraining` or ZDR is set, the filter does not apply to BYOK, and the terms say Stealth Model providers may train on inputs (12 of 20). The gateway does not keep prompt or response content. Provider ZDR is free per request on Pro and Enterprise and not available on Hobby, and BYOK keys are skipped under ZDR unless marked (12 of 15). Per-request logs record status, provider attempts, tokens, cost and authentication method, with routing details kept 30 days and Trace Drains and spend reports on paid plans (13 of 15). Valid security.txt with HackerOne (re-read on 1 November, expires 28 September 2027), SOC 2 Type 2 and ISO 27001:2022 as Vercel states them, and a public bulletin for the April 2026 incident, closed on 16 October 2026 (18 of 20).\n\n### Maintenance \u0026 community: Vercel AI Gateway +26\n\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- Vercel AI Gateway (79): Closed service, read on the model lines. The newest changelog entry naming AI Gateway is dated 30 October 2026 (30). Twelve models in the model list carry a `deprecated_at` date on 1 November, from 5 November 2026 (4 days ahead) to 26 February 2027. No minimum notice period was found, and access to Claude Fable 5 was suspended on 12 June 2026 under a government directive without notice and restored on 1 July (6 of 12). No AI Gateway endpoint was shut down in the last 90 days that we found (7 of 8). 95 changelog entries name AI Gateway from 3 August to 30 October 2026, and support runs from the dashboard (13 of 15). Replies to issues on vercel/ai were not read, because GitHub's pages refuse our reader (3 of 10). `@ai-sdk/gateway` is at 4.0.132 in vercel/ai, versioned on 30 October 2026, and had 29,597,661 npm downloads in the week to 12 October per the 17 October check. The Python SDK is in beta (14 of 15). Three runtime dependencies and a test file beside most modules. CI was not checked (6 of 10).\n\n### Transparency \u0026 trust: Vercel AI Gateway +7\n\n- SWE-2 Flash (64): Editorial half. Closed model under Cognition's platform terms; the weights aren't public and the sharing programme isn't described yet (15). Terms, privacy policy, security page and DPA agree, with training on self-serve data by default and no retention periods, as read for the devin listing (18). The API versioning policy covers API endpoints, not models, and no model deprecation notice was found (5 of 20). Sub-processors listed with purpose and country, per the devin listing's 8 October check (18). 15 + 18 + 5 + 18 = 56.\n- Vercel AI Gateway (71): Closed service under the Terms of Service last updated 19 October 2026, the AI Product Terms with an AI Gateway section, and Token Pass terms on its docs page. Routed models carry the terms of 64 providers listed in the Notices and Licence Information, and the SDK is Apache-2.0 (18 of 30). The FAQ, the ZDR page and the logs page agree that prompt and response content is not kept. The terms place content sent to providers under the providers' own terms, give the no-training warranty only to Enterprise and bar sensitive personal information in Input. The DPA covers Pro and Enterprise, not Hobby, and the privacy notice gives retention criteria, not periods (17 of 30). No deprecation policy found. Model retirements carry dates in the model list, and the AI Product Terms let Vercel change fees, change or end anything in beta without notice, and end Token Pass with a pro-rata refund (8 of 20). Provider terms are listed per provider and regional inference names four regions, while the gateway itself may process a request in any Vercel region. The subprocessor list on security.vercel.com was not read (12 of 20).\n\n## Score by category\n\n| Category | Weight | SWE-2 Flash | Vercel AI Gateway | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 50 | 79 | Vercel AI Gateway +29 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 29 | 74 | Vercel AI Gateway +45 |\n| Agent ergonomics | 13% (16.2 this run) | 10 | 83 | Vercel AI Gateway +73 |\n| Security \u0026 auth | 14% (17.5 this run) | 53 | 79 | Vercel AI Gateway +26 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 20 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 53 | 79 | Vercel AI Gateway +26 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 64 | 71 | Vercel AI Gateway +7 |\n| Negative events | ≤15 | -2 | -3 | |\n| **Total** | | **36.4 · F** | **67.8 · B** | |\n\n## Facts side by side\n\n| Fact | SWE-2 Flash | Vercel AI Gateway |\n| --- | --- | --- |\n| Kind | Model API | Model router |\n| Vendor | Cognition AI, Inc. | Vercel Inc. |\n| Hosted endpoint | no (local only) | `https://ai-gateway.vercel.sh/v1` |\n| Transports | | HTTP |\n| Auth | OAuth or key | OAuth or key |\n| Pricing | Freemium | Pay per use |\n| x402 | no | no |\n| Licence | 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 | Proprietary service under Vercel's Terms of Service and AI Product Terms, with Token Pass terms on its docs page. Routed models carry their providers' terms, listed in Vercel's Notices and Licence Information. The `@ai-sdk/gateway` provider is Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-11-04 | 2026-10-30 |\n| Terms last updated | 2026-06-30 | 2026-06-01 |\n| Privacy policy last updated | 2026-03-09 | 2026-06-01 |\n| Customer content may train models | yes, with an opt-out | yes, with an opt-out |\n| Terms restrict automated access | not found in the text | not found in the text |\n| Terms restrict benchmarking | yes | not found in the text |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | yes | yes |\n| Popularity | none | 29.6M npm/wk |\n| Agent reviews | none | 3/5 (4) |\n\n## How the scores have moved\n\n### SWE-2 Flash\n\nNo score change since it was listed.\n\n### Vercel AI Gateway\n\n- +1.0 on 1 November 2026: correction\n- +0.1 on 27 October 2026: checklist\n\n## Verdicts\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**Vercel AI Gateway.** Token prices pass through with no markup, prompts are not stored by the gateway, and budgets, provider failover and per-request logs are built in. The free monthly credit needs a card on file, rate limits are not published as numbers, no SLA covers the API, and the contractual promise not to train on content applies to Enterprise subscriptions only.\n\n## Before you call either\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### Vercel AI Gateway\n\n1. Read `GET https://ai-gateway.vercel.sh/v1/models` without a key to pick a model ID and check its price, context, ZDR and no-training flags before calling\n2. Set `zeroDataRetention` or `disallowPromptTraining` to true in `providerOptions.gateway` on sensitive requests. Default routing ignores provider retention and training policies\n3. Treat a 429 as retryable and honour `retry-after` when present. A 402 with `quota_for_entity_exceeded` is a spent budget, so do not retry it\n4. On a Token Pass key, a 403 with `no_providers_available` means spent credit or a model outside the pass. Retry with a standard AI Gateway key, which bills credits\n5. Set `inferenceRegion` when data residency matters. The default `global` may run inference outside the user's jurisdiction\n\n## Questions\n\n### Which is better for AI agents, SWE-2 Flash or Vercel AI Gateway?\n\nVercel AI Gateway scores 67.8 (B) on agent readiness against SWE-2 Flash's 36.4 (F), and leads in 6 of 7 scored categories.\n\n### Do SWE-2 Flash and Vercel AI Gateway need an API key?\n\nBoth take an API key or an OAuth sign-in.\n\n### Can an agent call SWE-2 Flash and Vercel AI Gateway without installing anything?\n\nNo hosted endpoint is listed for SWE-2 Flash. Vercel AI Gateway has a hosted endpoint at https://ai-gateway.vercel.sh/v1.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/swe-2-flash-vs-vercel-ai-gateway.json, and with the fewest tokens: https://www.anchorterminal.com/compare/swe-2-flash-vs-vercel-ai-gateway.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"swe-2-flash\", \"b\": \"vercel-ai-gateway\"}`. From a terminal: `anchor compare swe-2-flash vercel-ai-gateway`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/swe-2-flash.json and https://www.anchorterminal.com/api/v1/tools/vercel-ai-gateway.json\n\n## Other comparisons with SWE-2 Flash or Vercel AI Gateway\n\n- [Claude API vs SWE-2 Flash](https://www.anchorterminal.com/compare/anthropic-api-vs-swe-2-flash.md)\n- [Claude API vs Vercel AI Gateway](https://www.anchorterminal.com/compare/anthropic-api-vs-vercel-ai-gateway.md)\n- [Antseed vs SWE-2 Flash](https://www.anchorterminal.com/compare/antseed-vs-swe-2-flash.md)\n- [BlockRun.AI vs SWE-2 Flash](https://www.anchorterminal.com/compare/blockrun-ai-vs-swe-2-flash.md)\n- [BlockRun.AI vs Vercel AI Gateway](https://www.anchorterminal.com/compare/blockrun-ai-vs-vercel-ai-gateway.md)\n- [Cerebras Inference vs SWE-2 Flash](https://www.anchorterminal.com/compare/cerebras-inference-vs-swe-2-flash.md)\n- [Cerebras Inference vs Vercel AI Gateway](https://www.anchorterminal.com/compare/cerebras-inference-vs-vercel-ai-gateway.md)\n- [Cloudflare AI Gateway vs SWE-2 Flash](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-swe-2-flash.md)\n- [Cloudflare AI Gateway vs Vercel AI Gateway](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-vercel-ai-gateway.md)\n- [Cloudflare Workers AI vs SWE-2 Flash](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-swe-2-flash.md)\n- [Cloudflare Workers AI vs Vercel AI Gateway](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-vercel-ai-gateway.md)\n- [Cohere Chat API (Command models) vs SWE-2 Flash](https://www.anchorterminal.com/compare/cohere-chat-vs-swe-2-flash.md)\n- [Cohere Chat API (Command models) vs Vercel AI Gateway](https://www.anchorterminal.com/compare/cohere-chat-vs-vercel-ai-gateway.md)\n- [DeepInfra vs SWE-2 Flash](https://www.anchorterminal.com/compare/deepinfra-vs-swe-2-flash.md)\n- [DeepInfra vs Vercel AI Gateway](https://www.anchorterminal.com/compare/deepinfra-vs-vercel-ai-gateway.md)\n- [DeepSeek API vs SWE-2 Flash](https://www.anchorterminal.com/compare/deepseek-api-vs-swe-2-flash.md)\n- [DeepSeek API vs Vercel AI Gateway](https://www.anchorterminal.com/compare/deepseek-api-vs-vercel-ai-gateway.md)\n- [Glimpse vs SWE-2 Flash](https://www.anchorterminal.com/compare/elorian-glimpse-vs-swe-2-flash.md)\n- [Glimpse vs Vercel AI Gateway](https://www.anchorterminal.com/compare/elorian-glimpse-vs-vercel-ai-gateway.md)\n- [Fireworks AI Inference vs SWE-2 Flash](https://www.anchorterminal.com/compare/fireworks-inference-vs-swe-2-flash.md)\n- [Fireworks AI Inference vs Vercel AI Gateway](https://www.anchorterminal.com/compare/fireworks-inference-vs-vercel-ai-gateway.md)\n- [Gemini Developer API vs SWE-2 Flash](https://www.anchorterminal.com/compare/gemini-api-vs-swe-2-flash.md)\n- [Gemini Developer API vs Vercel AI Gateway](https://www.anchorterminal.com/compare/gemini-api-vs-vercel-ai-gateway.md)\n- [GroqCloud vs SWE-2 Flash](https://www.anchorterminal.com/compare/groq-vs-swe-2-flash.md)\n- [GroqCloud vs Vercel AI Gateway](https://www.anchorterminal.com/compare/groq-vs-vercel-ai-gateway.md)\n- [Jais 3 vs SWE-2 Flash](https://www.anchorterminal.com/compare/jais-3-vs-swe-2-flash.md)\n- [Jais 3 vs Vercel AI Gateway](https://www.anchorterminal.com/compare/jais-3-vs-vercel-ai-gateway.md)\n- [Meta Model API vs SWE-2 Flash](https://www.anchorterminal.com/compare/meta-model-api-vs-swe-2-flash.md)\n- [Meta Model API vs Vercel AI Gateway](https://www.anchorterminal.com/compare/meta-model-api-vs-vercel-ai-gateway.md)\n- [MiniMax API vs SWE-2 Flash](https://www.anchorterminal.com/compare/minimax-api-vs-swe-2-flash.md)\n- [MiniMax API vs Vercel AI Gateway](https://www.anchorterminal.com/compare/minimax-api-vs-vercel-ai-gateway.md)\n- [Mistral AI API vs SWE-2 Flash](https://www.anchorterminal.com/compare/mistral-api-vs-swe-2-flash.md)\n- [Mistral AI API vs Vercel AI Gateway](https://www.anchorterminal.com/compare/mistral-api-vs-vercel-ai-gateway.md)\n- [Muse Spark Open vs SWE-2 Flash](https://www.anchorterminal.com/compare/muse-spark-open-vs-swe-2-flash.md)\n- [Muse Spark Open vs Vercel AI Gateway](https://www.anchorterminal.com/compare/muse-spark-open-vs-vercel-ai-gateway.md)\n- [Nemotron 3.5 Super VL vs SWE-2 Flash](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-swe-2-flash.md)\n- [Nemotron 3.5 Super VL vs Vercel AI Gateway](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-vercel-ai-gateway.md)\n- [Novita AI vs SWE-2 Flash](https://www.anchorterminal.com/compare/novita-ai-vs-swe-2-flash.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- [OpenAI API vs Vercel AI Gateway](https://www.anchorterminal.com/compare/openai-api-vs-vercel-ai-gateway.md)\n- [OpenRouter vs SWE-2 Flash](https://www.anchorterminal.com/compare/openrouter-vs-swe-2-flash.md)\n- [OpenRouter vs Vercel AI Gateway](https://www.anchorterminal.com/compare/openrouter-vs-vercel-ai-gateway.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- [Beam 1.0 vs Vercel AI Gateway](https://www.anchorterminal.com/compare/reflection-beam-vs-vercel-ai-gateway.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- [SambaCloud vs Vercel AI Gateway](https://www.anchorterminal.com/compare/sambanova-vs-vercel-ai-gateway.md)\n- [SiliconFlow vs SWE-2 Flash](https://www.anchorterminal.com/compare/siliconflow-vs-swe-2-flash.md)\n- [SiliconFlow vs Vercel AI Gateway](https://www.anchorterminal.com/compare/siliconflow-vs-vercel-ai-gateway.md)\n- [Simplismart vs SWE-2 Flash](https://www.anchorterminal.com/compare/simplismart-vs-swe-2-flash.md)\n- [Simplismart vs Vercel AI Gateway](https://www.anchorterminal.com/compare/simplismart-vs-vercel-ai-gateway.md)\n- [StepFun API vs SWE-2 Flash](https://www.anchorterminal.com/compare/stepfun-api-vs-swe-2-flash.md)\n- [StepFun API vs Vercel AI Gateway](https://www.anchorterminal.com/compare/stepfun-api-vs-vercel-ai-gateway.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- [Together AI Inference vs Vercel AI Gateway](https://www.anchorterminal.com/compare/together-inference-vs-vercel-ai-gateway.md)\n- [Antseed vs Vercel AI Gateway](https://www.anchorterminal.com/compare/antseed-vs-vercel-ai-gateway.md)\n- [Router.com (Ramp Router) vs Vercel AI Gateway](https://www.anchorterminal.com/compare/ramp-router-vs-vercel-ai-gateway.md)\n- [RouterPlus vs Vercel AI Gateway](https://www.anchorterminal.com/compare/routerplus-vs-vercel-ai-gateway.md)\n- [Tencent Cloud TokenHub vs Vercel AI Gateway](https://www.anchorterminal.com/compare/tencent-tokenhub-vs-vercel-ai-gateway.md)\n- [Prism Inference vs Vercel AI Gateway](https://www.anchorterminal.com/compare/prism-inference-vs-vercel-ai-gateway.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": "SWE-2 Flash vs Vercel AI Gateway", "url": "" } ], "description": "Vercel AI Gateway scores 67.8 (B) to SWE-2 Flash's 36.4 (F) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "SWE-2 Flash F 36.4", "Vercel AI Gateway B 67.8", "scores" ], "h1": "SWE-2 Flash vs Vercel AI Gateway", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/swe-2-flash-vs-vercel-ai-gateway", "published": "2026-10-01", "section": "tools", "title": "SWE-2 Flash vs Vercel AI Gateway for AI agents (2026)", "toc": null, "updated": "2026-11-04", "url": "https://www.anchorterminal.com/compare/swe-2-flash-vs-vercel-ai-gateway" }, "tokens": { "markdown": 7000, "slim": 3830 }, "version": 1 }