{ "data": { "a": { "slug": "meta-model-api", "name": "Meta Model API", "vendor": "Meta", "vendorUrl": "https://dev.meta.ai", "kind": "model", "category": "inference", "summary": "Meta Model API is Meta's pay-as-you-go API for its hosted Muse models, including Muse Wonder and Muse Spark, through OpenAI-style Responses and Chat Completions endpoints and an Anthropic-style Messages endpoint, plus image, speech and segmentation routes.", "url": "https://www.anchorterminal.com/tools/meta-model-api", "markdownUrl": "https://www.anchorterminal.com/tools/meta-model-api.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/meta-model-api.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/meta-model-api.json", "dns": "meta-model-api.grade.anchorterminal.com", "license": "Closed service under the Meta Model API Terms of Service (last updated 9 October 2026), with Meta Platforms, Inc., or Meta Platforms Ireland Limited in the European Region, as the contracting party.", "transports": [ "http" ], "remoteUrl": "https://api.meta.ai/v1", "packages": [], "auth": "api-key", "authNotes": "A bearer API key created on the API keys tab of the Model API dashboard after a browser sign-up with email, mobile number, Facebook, Google or GitHub. Keys belong to a team, are shown once and are revoked by deletion. No key scopes were found, and every key on a team shares the team's rate limits.", "pricing": "usage", "pricingNotes": "Muse Wonder is $4.00 per million input tokens, $0.20 cached and $20.00 per million output tokens, Standard mode only (checked 2026-10-12). Muse Spark is $1.25, $0.15 and $4.25, or $0.10, $0.002 and $0.20 in Contributor mode, where Meta may train on the content. Billed in arrears to a card. No free allowance was found.", "priceSummary": "from $1.25 / 1M in", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in dev.meta.ai/llms.txt, the pricing page, the API reference or the billing help pages, checked 12 October 2026. Usage is charged to a card at a payment threshold or on the 1st of each month.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-12" }, "docsUrl": "https://dev.meta.ai/docs/overview", "llmsTxt": "https://dev.meta.ai/llms.txt", "capabilities": [ "inference.llm", "image.generate", "image.edit", "speech.stt", "speech.streaming" ], "tags": [ "official", "hosted", "model", "usage-priced", "closed-source", "llms-txt", "multimodal", "streaming", "openai-compatible", "anthropic-compatible", "card-required" ], "lastRelease": "2026-10-12", "graded": true, "anchor": { "graded": true, "score": 52.3, "grade": "D", "agentReady": false, "rank": 886, "ranked": true, "rankOf": 1350, "categoryRank": 26, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 75, "maintenance": 46, "payments": 20, "reliability": 40, "schema": 60, "security": 64, "transparency": 53 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-04" }, "negative": 0, "verdict": "Meta Model API serves Muse Wonder, in preview since 12 October 2026, and Muse Spark with 1M-token context, constrained JSON Schema output, automatic prompt caching and per-token prices published without a login. Standard-mode content is not used for training. There's no free allowance, status history, OpenAPI file, deprecation policy or way to force a tool call.", "bestFor": "Long-running agent and coding work over text, images, video, audio and PDFs with a 1M-token context, where training must stay off by default.", "strengths": [ "Muse Wonder and Muse Spark take text, image, video, audio and PDF input with a 1,048,576-token context window", "Per-token prices, per-model rate limits and rate-limit headers published without a login", "Content sent in Standard mode is not used to train Meta models, and training use is opt-in through `-contributor` model IDs", "Responses, Chat Completions and Messages endpoints, so the OpenAI and Anthropic SDKs work with a base-URL change", "llms.txt and a Markdown copy of every docs page, with an error guide that gives the Retry-After value for each retryable error" ], "weaknesses": [ "Muse Wonder is labelled a preview, and no deprecation policy or notice period was found", "No free API allowance found, and billing is set up with a card", "No readable status history. The dev.meta.ai/status page showed \"Status information is unavailable\", and `/v1/status` reports only the current state", "`tool_choice` accepts only `auto`, so a call can't be forced or ruled out", "No OpenAPI file, batch endpoint or Model API changelog found, and API keys have no scopes" ], "agentNotes": [ "Use `muse-wonder-1.0` for long multi-step work and `muse-spark-1.3` for cheaper, high-volume calls. Both take the same requests", "Keep personal or confidential data away from `-contributor` model IDs. Meta may train on that content", "Honour Retry-After on 429 and 503, which is 60 seconds for `service_overloaded`, and check `GET https://api.meta.ai/v1/status`, which needs no key", "Pass the key to the OpenAI SDK explicitly or set `OPENAI_API_KEY`. The SDK doesn't read `MODEL_API_KEY`", "Leave `tool_choice` at `auto`. The docs say `none` and `required` are not supported" ], "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": 52.3 } ], "editorialScores": { "ergonomics": 75, "maintenance": 46, "payments": 20, "reliability": 40, "schema": 60, "security": 64, "transparency": 41 }, "provenanceScore": 64, "checked": { "categories": { "ergonomics": "2026-11-04", "maintenance": "2026-11-04", "payments": "2026-11-04", "reliability": "2026-11-04", "schema": "2026-11-04", "security": "2026-11-04", "transparency": "2026-11-04" }, "last": "2026-11-04", "lastMoved": "2026-10-30", "oldest": "2026-11-04", "stale": false, "staleAfterDays": 90 } }, "connect": { "http": "curl -X POST \"https://api.meta.ai/v1/responses\" \\\n -H \"Authorization: Bearer $MODEL_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"model\": \"muse-spark-1.3\", \"input\": \"What is the capital of France?\"}'" }, "letme": { "capability": "https://letme.dev/inference.llm", "tool": "https://letme.dev/meta-model-api" }, "sameCompany": [ "muse-spark-open", "muse-code", "muse-glimmer-30b" ], "area": "models", "unitPrices": [ { "item": "Muse Wonder input", "unit": "1m-tokens", "usd": 4, "note": "Standard mode, muse-wonder-1.0. No long-context premium." }, { "item": "Muse Wonder cached input", "unit": "1m-tokens", "usd": 0.2 }, { "item": "Muse Wonder output", "unit": "1m-tokens", "usd": 20 }, { "item": "Muse Spark input", "unit": "1m-tokens", "usd": 1.25, "note": "Standard mode, muse-spark-1.3, 1.2 and 1.1." }, { "item": "Muse Spark cached input", "unit": "1m-tokens", "usd": 0.15 }, { "item": "Muse Spark output", "unit": "1m-tokens", "usd": 4.25 }, { "item": "Muse Spark input, Contributor mode", "unit": "1m-tokens", "usd": 0.1, "note": "Meta may use the content to train its models." }, { "item": "Muse Spark output, Contributor mode", "unit": "1m-tokens", "usd": 0.2, "note": "Cached input is $0.002 per million tokens." }, { "item": "Web search grounding", "unit": "1k-requests", "usd": 2.5, "note": "Per 1,000 search queries, on top of token cost." }, { "item": "Muse Image generated image", "unit": "image", "usd": 0.01 } ], "provenance": { "legalEntity": "Meta Platforms, Inc.", "domain": "meta.ai", "domainRegistered": "2017-12-16", "endpointOnVendorDomain": true, "terms": "https://dev.meta.ai/legal/terms-of-service", "privacy": "https://www.facebook.com/privacy/policy/", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-11-04", "notes": [ "The terms (last updated 9 October 2026) are an agreement with Meta Platforms, Inc., or Meta Platforms Ireland Limited for users in the European Region. The model card names the same two.", "The privacy field is the Meta Privacy Policy, which the terms link. www.facebook.com's robots.txt asks readers like ours not to fetch it, so it wasn't read. The terms also link a subprocessor list at forwork.meta.com/legal/mfw-subprocessor-list/ and the Meta Global Processor Terms, neither of which was read.", "The API answers at api.meta.ai, whose robots.txt disallows every path, so nothing there was requested.", "dev.meta.ai/status, linked from the site header and the error guide, opens a Model API Status page. On 4 November it showed \"Status information is unavailable\" to our reader, so no component or incident history was read. The documented `GET /v1/status` endpoint reports only the current state.", "No Model API changelog was found. The only changelog on dev.meta.ai is Muse Code's.", "dev.meta.ai/.well-known/security.txt returns 404. www.meta.ai's and www.facebook.com's robots.txt disallow ClaudeBot, so their security.txt files weren't read.", "developer.meta.com/ai/ redirects to dev.meta.ai." ], "score": 64 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/meta-model-api.json", "live": { "slug": "meta-model-api", "probe": { "target": "https://api.meta.ai/v1", "method": "get", "lastAt": "2026-11-05T01:29:08.569549435Z", "lastOk": true, "lastStatus": 404, "lastMs": 63, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 78, "p95ms24h": 146, "samples24h": 247, "samples30d": 5815, "days": [ { "date": "2026-10-12", "probes": 33, "ok": 33 }, { "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 } ] }, "securityTxt": { "url": "https://meta.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-04T15:52:55.744618885Z" }, "llmsTxt": { "url": "https://dev.meta.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-04T15:23:25.972409133Z" }, "domain": { "domain": "meta.ai", "registered": "2017-12-16", "source": "https://rdap.identitydigital.services/rdap/domain/meta.ai", "checkedAt": "2026-11-01T14:15:25.518716318Z" }, "pages": [ { "url": "https://dev.meta.ai/legal/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-11-04T08:17:55.538014405Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "0ef10c66f1b3" } ], "updatedAt": "2026-11-05T01:29:08.569549435Z" } }, "answer": "Meta Model API scores 52.3 (D) on agent readiness against SWE-2 Flash's 36.4 (F), and leads in 3 of 7 scored categories. SWE-2 Flash leads on reliability, maintenance \u0026 community 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": 65, "category": "ergonomics", "leads": "meta-model-api", "name": "Agent ergonomics", "reasons": { "a": "Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Tool calls on all three endpoints, parallel calls, tool search with deferred loading, built-in web search and a computer-use tool, but `tool_choice` accepts only `auto`, so a call can't be forced or forbidden (15 of 20). Output constrained to the JSON Schema on every surface (15). Automatic prompt caching with no setup, and cached input at 5 per cent of the input price on Muse Wonder (15). 1,048,576-token context on Muse Wonder and every Muse Spark version, with no long-context premium (15). No batch endpoint or discount found. Background responses run asynchronously at the normal price (0). No SDK of Meta's own. The docs use the OpenAI and Anthropic SDKs against compatible endpoints, the same reading as StepFun (0). OpenAI-style error envelope with `type` and `code`, per-status fixes and named retryable codes (15). 15 + 15 + 15 + 15 + 0 + 0 + 15 = 75.", "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": 75, "b": 10 } }, { "by": 31, "category": "schema", "leads": "meta-model-api", "name": "Schema \u0026 documentation", "reasons": { "a": "No OpenAPI or similar machine-readable contract found. The reference is Markdown pages with schema sections, and /openapi.json paths on dev.meta.ai return 404 (0). llms.txt at dev.meta.ai/llms.txt, and every docs page has a Markdown copy (10). The models page says when to choose Muse Wonder and when Muse Spark, and the tool-calling and structured-output guides state their limits, such as `tool_choice` only accepting `auto` and which schema keywords `strict` allows (16 of 20). JSON Schema tools and output, `reasoning_effort` an enum from minimal to max, a strict subset that returns 400 when violated, though `tool_choice` has one value (12 of 15). Curl, Python and TypeScript examples on each page and an error guide covering 400 to 504 with the error envelope, codes and a fix for each (15). Versioned model IDs (muse-spark-1.1 to 1.3, muse-wonder-1.0) and dated launch posts on the developer blog, but no API changelog (7 of 15). 0 + 10 + 16 + 12 + 15 + 7 = 60.", "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": 60, "b": 29 } }, { "by": 11, "category": "security", "leads": "meta-model-api", "name": "Security \u0026 auth", "reasons": { "a": "Model reading. Bearer keys per team, named, shown once and revoked by deletion, with rotation advice. No scopes, read-only keys or per-key limits found (20 of 30). The terms say Meta will not use Content submitted to the Standard Services to train Meta Models, and training applies only to the `-contributor` model IDs a caller picks. Content may still be used to develop and improve safety and security systems (17 of 20). Retention is 'as needed' for the service, the law, flagged violations and safety review, with no period stated. Zero data retention for qualified accounts through sales, with flagged content kept up to 2 years (10 of 15). The usage dashboard shows tokens and requests per day by model, with no per-key or per-call log found (5 of 15). No security.txt on dev.meta.ai. Meta's bug bounty at bugbounty.meta.com is named in the Muse Code SDK's security policy, and a security commitments page describes TLS 1.2 or later, PCI-DSS card handling and an ISMS, with no named certification for the API (12 of 20). 20 + 17 + 10 + 5 + 12 = 64.", "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": 64, "b": 53 } }, { "by": 11, "category": "transparency", "leads": "swe-2-flash", "name": "Transparency \u0026 trust", "reasons": { "a": "Closed service with clear terms, under California law with AAA arbitration for Meta Platforms, Inc. and Irish law and courts for Meta Platforms Ireland Limited, with liability capped at the greater of 12 months of fees or $1,000. Muse Glimmer's open weights don't change the hosted service (15). The terms, the models page, the pricing page and the zero-retention help page agree that Standard content isn't used for training and Contributor content may be, but retention periods are not stated outside zero retention, and the privacy policy is Meta's general one (18 of 30). No deprecation policy or dated notices found, and the terms let Meta remove functionality without notice (0). A subprocessor list is linked from the terms but wasn't read, and no data locations were found (8 of 20). 15 + 18 + 0 + 8 = 41.", "b": "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." }, "scores": { "a": 53, "b": 64 } }, { "by": 10, "category": "reliability", "leads": "swe-2-flash", "name": "Reliability", "reasons": { "a": "No status page with readable component history. The error guide's dev.meta.ai/status link now opens a Model API Status page, which showed \"Status information is unavailable\" to our reader on 4 November, its content drawn by script that we don't request, and the documented `GET /v1/status` reports only the current state (0). No readable incident history (5). Rate limits published per team and per model, 3,000 RPM and 4,000,000 TPM for muse-wonder-1.0, 150 RPM and 3,000,000 TPM for the contributor variants, 600 background submissions a minute (15). 429 and 503 carry Retry-After (60 seconds for `service_overloaded` and `backend_unavailable`), with backoff-with-jitter guidance, rate-limit headers on every token response and a documented mid-stream `server_shutting_down` event to retry, a generation call read as stateless as gemini-api's (15). No SLA found, and the terms let Meta throttle or suspend access without notice (0). Muse Wonder is labelled a preview. Muse Spark 1.3 carries no preview label, but the API opened on 8 July 2026 as a public preview and we found no general-availability notice, so half (5 of 10, the 12 October partial, kept). 0 + 5 + 15 + 15 + 0 + 5 = 40.", "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": 40, "b": 50 } }, { "by": 7, "category": "maintenance", "leads": "swe-2-flash", "name": "Maintenance \u0026 community", "reasons": { "a": "Model reading. Muse Wonder launched on 12 October 2026 (30). No deprecation policy or notice period found. All three Muse Spark versions are still served, so no retirement has tested one (0 of 12). Dated launches on the API since 6 August that we read, Muse Image on 25 August, Muse Voice Transcribe on 3 September and Muse Wonder on 12 October (8 of 8). Muse Code leaving beta on 31 August is a separate product and isn't counted. No Model API changelog. A help centre with support tickets, answered 'typically within two business days' by Meta's own account, which we didn't test (8 of 15). No SDK of Meta's own for the API (0 of 15, 0 of 10). 30 + 0 + 8 + 8 + 0 = 46.", "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": 46, "b": 53 } } ], "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Meta", "b": "Cognition AI, Inc.", "name": "Vendor" }, { "a": "https://api.meta.ai/v1", "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": "Closed service under the Meta Model API Terms of Service (last updated 9 October 2026), with Meta Platforms, Inc., or Meta Platforms Ireland Limited in the European Region, as the contracting party.", "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": "2026-10-12", "b": "2026-11-04", "name": "Last release" }, { "a": "2026-10-02", "b": "2026-06-30", "name": "Terms last updated" }, { "a": "couldn't be read", "b": "2026-03-09", "name": "Privacy policy last updated" }, { "a": "yes", "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": "yes", "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" } ], "faq": [ { "answer": "Meta Model API scores 52.3 (D) on agent readiness against SWE-2 Flash's 36.4 (F), and leads in 3 of 7 scored categories. SWE-2 Flash leads on reliability, maintenance \u0026 community and transparency \u0026 trust.", "question": "Which is better for AI agents, Meta Model API or SWE-2 Flash?" }, { "answer": "Meta Model API needs an API key. SWE-2 Flash takes an API key or an OAuth sign-in.", "question": "Do Meta Model API and SWE-2 Flash need an API key?" }, { "answer": "Meta Model API has a hosted endpoint at https://api.meta.ai/v1. No hosted endpoint is listed for SWE-2 Flash.", "question": "Can an agent call Meta Model API and SWE-2 Flash without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 60 against 29", "Agent ergonomics, 75 against 10", "Security \u0026 auth, 64 against 53" ], "also": [ "A hosted endpoint, with nothing to install" ], "goodFor": "Long-running agent and coding work over text, images, video, audio and PDFs with a 1M-token context, where training must stay off by default.", "slug": "meta-model-api", "watchFor": "Muse Wonder is labelled a preview, and no deprecation policy or notice period was found" }, { "aheadOn": [ "Reliability, 50 against 40", "Maintenance \u0026 community, 53 against 46", "Transparency \u0026 trust, 64 against 53" ], "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": { "meta-model-api": [ { "causes": [ "method" ], "date": "2026-10-30", "delta": -0.2, "from": 52.5, "fromGrade": "D", "to": 52.3, "toGrade": "D" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.3, "from": 52.2, "fromGrade": "D", "to": 52.5, "toGrade": "D" } ], "swe-2-flash": null }, "job": { "capability": "inference.llm", "name": "LLM inference" }, "others": [ { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-meta-model-api.json", "title": "Claude API vs Meta Model API", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-meta-model-api" }, { "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-meta-model-api.json", "title": "Antseed vs Meta Model API", "url": "https://www.anchorterminal.com/compare/antseed-vs-meta-model-api" }, { "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-meta-model-api.json", "title": "BlockRun.AI vs Meta Model API", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-meta-model-api" }, { "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-meta-model-api.json", "title": "Cerebras Inference vs Meta Model API", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-meta-model-api" }, { "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-meta-model-api.json", "title": "Cloudflare AI Gateway vs Meta Model API", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-meta-model-api" }, { "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-meta-model-api.json", "title": "Cloudflare Workers AI vs Meta Model API", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-meta-model-api" }, { "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-meta-model-api.json", "title": "Cohere Chat API (Command models) vs Meta Model API", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-meta-model-api" }, { "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-meta-model-api.json", "title": "DeepInfra vs Meta Model API", "url": "https://www.anchorterminal.com/compare/deepinfra-vs-meta-model-api" }, { "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-meta-model-api.json", "title": "DeepSeek API vs Meta Model API", "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-meta-model-api" }, { "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-meta-model-api.json", "title": "Glimpse vs Meta Model API", "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-meta-model-api" }, { "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-meta-model-api.json", "title": "Fireworks AI Inference vs Meta Model API", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-meta-model-api" }, { "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-meta-model-api.json", "title": "Gemini Developer API vs Meta Model API", "url": "https://www.anchorterminal.com/compare/gemini-api-vs-meta-model-api" }, { "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-meta-model-api.json", "title": "GroqCloud vs Meta Model API", "url": "https://www.anchorterminal.com/compare/groq-vs-meta-model-api" }, { "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-meta-model-api.json", "title": "Jais 3 vs Meta Model API", "url": "https://www.anchorterminal.com/compare/jais-3-vs-meta-model-api" }, { "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-minimax-api.json", "title": "Meta Model API vs MiniMax API", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-minimax-api" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-mistral-api.json", "title": "Meta Model API vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-muse-spark-open.json", "title": "Meta Model API vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-muse-spark-open" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-nemotron-3-5-super-vl.json", "title": "Meta Model API vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/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-openai-api.json", "title": "Meta Model API vs OpenAI API", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-openai-api" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-openrouter.json", "title": "Meta Model API vs OpenRouter", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-openrouter" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-prism-inference.json", "title": "Meta Model API vs Prism Inference", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-ramp-router.json", "title": "Meta Model API vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-reflection-beam.json", "title": "Meta Model API vs Beam 1.0", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-reflection-beam" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-routerplus.json", "title": "Meta Model API vs RouterPlus", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-routerplus" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-sambanova.json", "title": "Meta Model API vs SambaCloud", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-sambanova" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-siliconflow.json", "title": "Meta Model API vs SiliconFlow", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-siliconflow" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-simplismart.json", "title": "Meta Model API vs Simplismart", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-simplismart" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-stepfun-api.json", "title": "Meta Model API vs StepFun API", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-stepfun-api" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-tencent-tokenhub.json", "title": "Meta Model API vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-together-inference.json", "title": "Meta Model API vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-together-inference" }, { "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/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-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-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/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" } ], "panel": null, "scores": [ { "by": 10, "edge": "swe-2-flash", "key": "reliability", "meta-model-api": 40, "name": "Reliability", "swe-2-flash": 50, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 31, "edge": "meta-model-api", "key": "schema", "meta-model-api": 60, "name": "Schema \u0026 documentation", "swe-2-flash": 29, "weight": 13 }, { "by": 65, "edge": "meta-model-api", "key": "ergonomics", "meta-model-api": 75, "name": "Agent ergonomics", "swe-2-flash": 10, "weight": 13 }, { "by": 11, "edge": "meta-model-api", "key": "security", "meta-model-api": 64, "name": "Security \u0026 auth", "swe-2-flash": 53, "weight": 14 }, { "by": 0, "edge": "", "key": "payments", "meta-model-api": 20, "name": "Payments \u0026 pricing", "swe-2-flash": 20, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 7, "edge": "swe-2-flash", "key": "maintenance", "meta-model-api": 46, "name": "Maintenance \u0026 community", "swe-2-flash": 53, "weight": 7 }, { "by": 11, "edge": "swe-2-flash", "key": "transparency", "meta-model-api": 53, "name": "Transparency \u0026 trust", "swe-2-flash": 64, "weight": 7 } ], "summary": "Meta Model API scores 52.3 (D) on agent readiness against SWE-2 Flash's 36.4 (F), and leads in 3 of 7 scored categories. SWE-2 Flash leads on reliability, maintenance \u0026 community and transparency \u0026 trust. Both do llm inference.", "tasks": null, "tutorials": [], "verdicts": { "meta-model-api": "Meta Model API serves Muse Wonder, in preview since 12 October 2026, and Muse Spark with 1M-token context, constrained JSON Schema output, automatic prompt caching and per-token prices published without a login. Standard-mode content is not used for training. There's no free allowance, status history, OpenAPI file, deprecation policy or way to force a tool call.", "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/meta-model-api-vs-swe-2-flash", "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-swe-2-flash.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/meta-model-api-vs-swe-2-flash.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/meta-model-api-vs-swe-2-flash.min.md" }, "markdown": "Meta Model API scores 52.3 (D) on agent readiness against SWE-2 Flash's 36.4 (F), and leads in 3 of 7 scored categories. SWE-2 Flash leads on reliability, maintenance \u0026 community and transparency \u0026 trust. Both do llm inference.\n\n- Meta Model API: grade D, 52.3/100, rank #886 of 1350. Markdown https://www.anchorterminal.com/tools/meta-model-api.md · JSON https://www.anchorterminal.com/api/v1/tools/meta-model-api.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### Meta Model API (D)\n\nGood for: Long-running agent and coding work over text, images, video, audio and PDFs with a 1M-token context, where training must stay off by default.\n\nAhead on:\n- Schema \u0026 documentation, 60 against 29\n- Agent ergonomics, 75 against 10\n- Security \u0026 auth, 64 against 53\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: Muse Wonder is labelled a preview, and no deprecation policy or notice period was found\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 40\n- Maintenance \u0026 community, 53 against 46\n- Transparency \u0026 trust, 64 against 53\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: Meta Model API +65\n\n- Meta Model API (75): Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Tool calls on all three endpoints, parallel calls, tool search with deferred loading, built-in web search and a computer-use tool, but `tool_choice` accepts only `auto`, so a call can't be forced or forbidden (15 of 20). Output constrained to the JSON Schema on every surface (15). Automatic prompt caching with no setup, and cached input at 5 per cent of the input price on Muse Wonder (15). 1,048,576-token context on Muse Wonder and every Muse Spark version, with no long-context premium (15). No batch endpoint or discount found. Background responses run asynchronously at the normal price (0). No SDK of Meta's own. The docs use the OpenAI and Anthropic SDKs against compatible endpoints, the same reading as StepFun (0). OpenAI-style error envelope with `type` and `code`, per-status fixes and named retryable codes (15). 15 + 15 + 15 + 15 + 0 + 0 + 15 = 75.\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: Meta Model API +31\n\n- Meta Model API (60): No OpenAPI or similar machine-readable contract found. The reference is Markdown pages with schema sections, and /openapi.json paths on dev.meta.ai return 404 (0). llms.txt at dev.meta.ai/llms.txt, and every docs page has a Markdown copy (10). The models page says when to choose Muse Wonder and when Muse Spark, and the tool-calling and structured-output guides state their limits, such as `tool_choice` only accepting `auto` and which schema keywords `strict` allows (16 of 20). JSON Schema tools and output, `reasoning_effort` an enum from minimal to max, a strict subset that returns 400 when violated, though `tool_choice` has one value (12 of 15). Curl, Python and TypeScript examples on each page and an error guide covering 400 to 504 with the error envelope, codes and a fix for each (15). Versioned model IDs (muse-spark-1.1 to 1.3, muse-wonder-1.0) and dated launch posts on the developer blog, but no API changelog (7 of 15). 0 + 10 + 16 + 12 + 15 + 7 = 60.\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### Security \u0026 auth: Meta Model API +11\n\n- Meta Model API (64): Model reading. Bearer keys per team, named, shown once and revoked by deletion, with rotation advice. No scopes, read-only keys or per-key limits found (20 of 30). The terms say Meta will not use Content submitted to the Standard Services to train Meta Models, and training applies only to the `-contributor` model IDs a caller picks. Content may still be used to develop and improve safety and security systems (17 of 20). Retention is 'as needed' for the service, the law, flagged violations and safety review, with no period stated. Zero data retention for qualified accounts through sales, with flagged content kept up to 2 years (10 of 15). The usage dashboard shows tokens and requests per day by model, with no per-key or per-call log found (5 of 15). No security.txt on dev.meta.ai. Meta's bug bounty at bugbounty.meta.com is named in the Muse Code SDK's security policy, and a security commitments page describes TLS 1.2 or later, PCI-DSS card handling and an ISMS, with no named certification for the API (12 of 20). 20 + 17 + 10 + 5 + 12 = 64.\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### Transparency \u0026 trust: SWE-2 Flash +11\n\n- Meta Model API (53): Closed service with clear terms, under California law with AAA arbitration for Meta Platforms, Inc. and Irish law and courts for Meta Platforms Ireland Limited, with liability capped at the greater of 12 months of fees or $1,000. Muse Glimmer's open weights don't change the hosted service (15). The terms, the models page, the pricing page and the zero-retention help page agree that Standard content isn't used for training and Contributor content may be, but retention periods are not stated outside zero retention, and the privacy policy is Meta's general one (18 of 30). No deprecation policy or dated notices found, and the terms let Meta remove functionality without notice (0). A subprocessor list is linked from the terms but wasn't read, and no data locations were found (8 of 20). 15 + 18 + 0 + 8 = 41.\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\n### Reliability: SWE-2 Flash +10\n\n- Meta Model API (40): No status page with readable component history. The error guide's dev.meta.ai/status link now opens a Model API Status page, which showed \"Status information is unavailable\" to our reader on 4 November, its content drawn by script that we don't request, and the documented `GET /v1/status` reports only the current state (0). No readable incident history (5). Rate limits published per team and per model, 3,000 RPM and 4,000,000 TPM for muse-wonder-1.0, 150 RPM and 3,000,000 TPM for the contributor variants, 600 background submissions a minute (15). 429 and 503 carry Retry-After (60 seconds for `service_overloaded` and `backend_unavailable`), with backoff-with-jitter guidance, rate-limit headers on every token response and a documented mid-stream `server_shutting_down` event to retry, a generation call read as stateless as gemini-api's (15). No SLA found, and the terms let Meta throttle or suspend access without notice (0). Muse Wonder is labelled a preview. Muse Spark 1.3 carries no preview label, but the API opened on 8 July 2026 as a public preview and we found no general-availability notice, so half (5 of 10, the 12 October partial, kept). 0 + 5 + 15 + 15 + 0 + 5 = 40.\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### Maintenance \u0026 community: SWE-2 Flash +7\n\n- Meta Model API (46): Model reading. Muse Wonder launched on 12 October 2026 (30). No deprecation policy or notice period found. All three Muse Spark versions are still served, so no retirement has tested one (0 of 12). Dated launches on the API since 6 August that we read, Muse Image on 25 August, Muse Voice Transcribe on 3 September and Muse Wonder on 12 October (8 of 8). Muse Code leaving beta on 31 August is a separate product and isn't counted. No Model API changelog. A help centre with support tickets, answered 'typically within two business days' by Meta's own account, which we didn't test (8 of 15). No SDK of Meta's own for the API (0 of 15, 0 of 10). 30 + 0 + 8 + 8 + 0 = 46.\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## Score by category\n\n| Category | Weight | Meta Model API | SWE-2 Flash | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 40 | 50 | SWE-2 Flash +10 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 60 | 29 | Meta Model API +31 |\n| Agent ergonomics | 13% (16.2 this run) | 75 | 10 | Meta Model API +65 |\n| Security \u0026 auth | 14% (17.5 this run) | 64 | 53 | Meta Model API +11 |\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) | 46 | 53 | SWE-2 Flash +7 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 53 | 64 | SWE-2 Flash +11 |\n| Negative events | ≤15 | 0 | -2 | |\n| **Total** | | **52.3 · D** | **36.4 · F** | |\n\n## Facts side by side\n\n| Fact | Meta Model API | SWE-2 Flash |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Meta | Cognition AI, Inc. |\n| Hosted endpoint | `https://api.meta.ai/v1` | 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 | Closed service under the Meta Model API Terms of Service (last updated 9 October 2026), with Meta Platforms, Inc., or Meta Platforms Ireland Limited in the European Region, as the contracting party. | 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 | 2026-10-12 | 2026-11-04 |\n| Terms last updated | 2026-10-02 | 2026-06-30 |\n| Privacy policy last updated | couldn't be read | 2026-03-09 |\n| Customer content may train models | yes | 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 | yes |\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\n## How the scores have moved\n\n### Meta Model API\n\n- -0.2 on 30 October 2026: checklist\n- +0.3 on 27 October 2026: checklist\n\n### SWE-2 Flash\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Meta Model API.** Meta Model API serves Muse Wonder, in preview since 12 October 2026, and Muse Spark with 1M-token context, constrained JSON Schema output, automatic prompt caching and per-token prices published without a login. Standard-mode content is not used for training. There's no free allowance, status history, OpenAPI file, deprecation policy or way to force a tool call.\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### Meta Model API\n\n1. Use `muse-wonder-1.0` for long multi-step work and `muse-spark-1.3` for cheaper, high-volume calls. Both take the same requests\n2. Keep personal or confidential data away from `-contributor` model IDs. Meta may train on that content\n3. Honour Retry-After on 429 and 503, which is 60 seconds for `service_overloaded`, and check `GET https://api.meta.ai/v1/status`, which needs no key\n4. Pass the key to the OpenAI SDK explicitly or set `OPENAI_API_KEY`. The SDK doesn't read `MODEL_API_KEY`\n5. Leave `tool_choice` at `auto`. The docs say `none` and `required` are not supported\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, Meta Model API or SWE-2 Flash?\n\nMeta Model API scores 52.3 (D) on agent readiness against SWE-2 Flash's 36.4 (F), and leads in 3 of 7 scored categories. SWE-2 Flash leads on reliability, maintenance \u0026 community and transparency \u0026 trust.\n\n### Do Meta Model API and SWE-2 Flash need an API key?\n\nMeta Model API needs an API key. SWE-2 Flash takes an API key or an OAuth sign-in.\n\n### Can an agent call Meta Model API and SWE-2 Flash without installing anything?\n\nMeta Model API has a hosted endpoint at https://api.meta.ai/v1. 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/meta-model-api-vs-swe-2-flash.json, and with the fewest tokens: https://www.anchorterminal.com/compare/meta-model-api-vs-swe-2-flash.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"meta-model-api\", \"b\": \"swe-2-flash\"}`. From a terminal: `anchor compare meta-model-api swe-2-flash`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/meta-model-api.json and https://www.anchorterminal.com/api/v1/tools/swe-2-flash.json\n\n## Other comparisons with Meta Model API or SWE-2 Flash\n\n- [Claude API vs Meta Model API](https://www.anchorterminal.com/compare/anthropic-api-vs-meta-model-api.md)\n- [Claude API vs SWE-2 Flash](https://www.anchorterminal.com/compare/anthropic-api-vs-swe-2-flash.md)\n- [Antseed vs Meta Model API](https://www.anchorterminal.com/compare/antseed-vs-meta-model-api.md)\n- [Antseed vs SWE-2 Flash](https://www.anchorterminal.com/compare/antseed-vs-swe-2-flash.md)\n- [BlockRun.AI vs Meta Model API](https://www.anchorterminal.com/compare/blockrun-ai-vs-meta-model-api.md)\n- [BlockRun.AI vs SWE-2 Flash](https://www.anchorterminal.com/compare/blockrun-ai-vs-swe-2-flash.md)\n- [Cerebras Inference vs Meta Model API](https://www.anchorterminal.com/compare/cerebras-inference-vs-meta-model-api.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 Meta Model API](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-meta-model-api.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 Meta Model API](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-meta-model-api.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 Meta Model API](https://www.anchorterminal.com/compare/cohere-chat-vs-meta-model-api.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 Meta Model API](https://www.anchorterminal.com/compare/deepinfra-vs-meta-model-api.md)\n- [DeepInfra vs SWE-2 Flash](https://www.anchorterminal.com/compare/deepinfra-vs-swe-2-flash.md)\n- [DeepSeek API vs Meta Model API](https://www.anchorterminal.com/compare/deepseek-api-vs-meta-model-api.md)\n- [DeepSeek API vs SWE-2 Flash](https://www.anchorterminal.com/compare/deepseek-api-vs-swe-2-flash.md)\n- [Glimpse vs Meta Model API](https://www.anchorterminal.com/compare/elorian-glimpse-vs-meta-model-api.md)\n- [Glimpse vs SWE-2 Flash](https://www.anchorterminal.com/compare/elorian-glimpse-vs-swe-2-flash.md)\n- [Fireworks AI Inference vs Meta Model API](https://www.anchorterminal.com/compare/fireworks-inference-vs-meta-model-api.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 Meta Model API](https://www.anchorterminal.com/compare/gemini-api-vs-meta-model-api.md)\n- [Gemini Developer API vs SWE-2 Flash](https://www.anchorterminal.com/compare/gemini-api-vs-swe-2-flash.md)\n- [GroqCloud vs Meta Model API](https://www.anchorterminal.com/compare/groq-vs-meta-model-api.md)\n- [GroqCloud vs SWE-2 Flash](https://www.anchorterminal.com/compare/groq-vs-swe-2-flash.md)\n- [Jais 3 vs Meta Model API](https://www.anchorterminal.com/compare/jais-3-vs-meta-model-api.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 MiniMax API](https://www.anchorterminal.com/compare/meta-model-api-vs-minimax-api.md)\n- [Meta Model API vs Mistral AI API](https://www.anchorterminal.com/compare/meta-model-api-vs-mistral-api.md)\n- [Meta Model API vs Muse Spark Open](https://www.anchorterminal.com/compare/meta-model-api-vs-muse-spark-open.md)\n- [Meta Model API vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/meta-model-api-vs-nemotron-3-5-super-vl.md)\n- [Meta Model API vs Novita AI](https://www.anchorterminal.com/compare/meta-model-api-vs-novita-ai.md)\n- [Meta Model API vs OpenAI API](https://www.anchorterminal.com/compare/meta-model-api-vs-openai-api.md)\n- [Meta Model API vs OpenRouter](https://www.anchorterminal.com/compare/meta-model-api-vs-openrouter.md)\n- [Meta Model API vs Prism Inference](https://www.anchorterminal.com/compare/meta-model-api-vs-prism-inference.md)\n- [Meta Model API vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/meta-model-api-vs-ramp-router.md)\n- [Meta Model API vs Beam 1.0](https://www.anchorterminal.com/compare/meta-model-api-vs-reflection-beam.md)\n- [Meta Model API vs RouterPlus](https://www.anchorterminal.com/compare/meta-model-api-vs-routerplus.md)\n- [Meta Model API vs SambaCloud](https://www.anchorterminal.com/compare/meta-model-api-vs-sambanova.md)\n- [Meta Model API vs SiliconFlow](https://www.anchorterminal.com/compare/meta-model-api-vs-siliconflow.md)\n- [Meta Model API vs Simplismart](https://www.anchorterminal.com/compare/meta-model-api-vs-simplismart.md)\n- [Meta Model API vs StepFun API](https://www.anchorterminal.com/compare/meta-model-api-vs-stepfun-api.md)\n- [Meta Model API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/meta-model-api-vs-tencent-tokenhub.md)\n- [Meta Model API vs Together AI Inference](https://www.anchorterminal.com/compare/meta-model-api-vs-together-inference.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- [Mistral AI API vs SWE-2 Flash](https://www.anchorterminal.com/compare/mistral-api-vs-swe-2-flash.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 SWE-2 Flash](https://www.anchorterminal.com/compare/novita-ai-vs-swe-2-flash.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", "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": "Meta Model API vs SWE-2 Flash", "url": "" } ], "description": "Meta Model scores 52.3 (D) to SWE-2 Flash's 36.4 (F) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Meta Model API D 52.3", "SWE-2 Flash F 36.4", "scores" ], "h1": "Meta Model API vs SWE-2 Flash", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/meta-model-api-vs-swe-2-flash", "published": "2026-10-01", "section": "tools", "title": "Meta Model vs SWE-2 Flash for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-04", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-swe-2-flash" }, "tokens": { "markdown": 6550, "slim": 3480 }, "version": 1 }