{ "data": { "a": { "slug": "gemini-4-hydrogen", "name": "Gemini 4 Hydrogen", "vendor": "Google", "vendorUrl": "https://ai.google.dev", "kind": "model", "category": "inference", "summary": "Gemini 4 Hydrogen is Google's fast, lower-cost Gemini 4 model for everyday coding and agent work, on every tier of the Gemini API with a 1,048,576-token limit shared between input and output.", "url": "https://www.anchorterminal.com/tools/gemini-4-hydrogen", "markdownUrl": "https://www.anchorterminal.com/tools/gemini-4-hydrogen.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/gemini-4-hydrogen.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/gemini-4-hydrogen.json", "dns": "gemini-4-hydrogen.grade.anchorterminal.com", "license": "Closed model, used through the Gemini API and Google's apps under Google's terms", "transports": [], "remoteUrl": "https://generativelanguage.googleapis.com/v1beta", "packages": [], "auth": "api-key", "authNotes": "An `x-goog-api-key` from AI Studio. Google's announcement puts Hydrogen on all tiers of AI Studio and the Gemini API, so a free-tier key with no billing works, per that post and the Gemini API listing's reading of the free tier. Paid Google AI Pro and Ultra subscribers can use it in Antigravity. On Google Cloud it's `gemini-4-hydrogen` on the Agent Platform, with Cloud credentials.", "pricing": "usage", "pricingNotes": "Google's announcement gives $1.50 per million input tokens and $7.50 output, flat across the whole 1M-token window, and names no introductory period, cached-input or batch price. Every processed token is billed, thinking included. Hydrogen's free-tier limits are on the Gemini API pricing page, now at aistudio.google.com, not yet read (checked 2026-11-13).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No machine payment. Paid use needs billing on a Cloud project, per the Gemini API listing (checked 2026-11-13).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-13" }, "docsUrl": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/guides/gemini-4-hydrogen", "llmsTxt": "https://ai.google.dev/gemini-api/docs/llms.txt", "capabilities": [ "inference.llm" ], "tags": [ "official", "hosted", "model", "multimodal", "reasoning", "long-context", "tool-calling", "usage-priced", "free-tier", "closed-source", "llms-txt", "new" ], "lastRelease": "2026-11-12", "graded": true, "anchor": { "graded": true, "score": 64.9, "grade": "B", "agentReady": false, "rank": 546, "ranked": true, "rankOf": 1524, "categoryRank": 23, "methodology": "0.8", "run": "2026-10-01", "scores": { "ergonomics": 90, "maintenance": 85, "payments": 40, "reliability": 45, "schema": 85, "security": 50, "transparency": 72 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-13" }, "negative": 0, "verdict": "Google's fast Gemini 4 model, on every tier of the Gemini API including the free one, at $1.50 and $7.50 per million tokens with a 1M-token budget, four thinking levels, function calling and structured output. Sampling parameters are ignored, explicit caching isn't supported, it's a short-term release with 45 days' notice on Cloud, and the benchmarks are Google's.", "bestFor": "Agents doing everyday coding, tool calls and document work at volume on the Gemini API, including ones that need to start on a free key, or as the executor beside Carbon or Argon.", "strengths": [ "On the free tier of the Gemini API, unlike Carbon and Argon", "$1.50 input and $7.50 output per million tokens, flat across the 1M-token window", "1,048,576 tokens shared between input and output, with long decodes to the full budget", "Four thinking levels, function calling, structured output, code execution, grounding and computer use", "The same API, keys and SDKs as Argon and Carbon, plus an OpenAI-compatible surface, so switching is a model ID" ], "weaknesses": [ "temperature, top_p and top_k are ignored, and thinking_budget, MINIMAL, penalties and extra candidates return a 400", "No explicit context caching or prefilled model turns, and strict thought-signature rules on parallel calls", "A short-term release, with a minimum of 45 days' notice before retirement on Google Cloud", "Free-tier content is used to improve Google's products and may be read by people", "Benchmark figures are Google's own, and the model card says jailbreak resistance is still being improved" ], "agentNotes": [ "Call generateContent at https://generativelanguage.googleapis.com/v1beta with model gemini-4-hydrogen and an x-goog-api-key", "Set thinking_level instead of thinking_budget; the default is HIGH, so set MEDIUM to keep 3.8 Flash's latency", "Don't send temperature, top_p, top_k, penalties or candidate_count above 1", "Pass every thought_signature back in its original part, on the first parallel functionCall only, or the call returns a 400", "Put static content of 4,096 tokens or more first so implicit caching applies, and keep confidential prompts off the free tier" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.8", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 64.9 } ], "editorialScores": { "ergonomics": 90, "maintenance": 85, "payments": 40, "reliability": 45, "schema": 85, "security": 50, "transparency": 55 }, "provenanceScore": 89, "checked": { "categories": { "ergonomics": "2026-11-13", "maintenance": "2026-11-13", "payments": "2026-11-13", "reliability": "2026-11-13", "schema": "2026-11-13", "security": "2026-11-13", "transparency": "2026-11-13" }, "last": "2026-11-13", "oldest": "2026-11-13", "stale": false, "staleAfterDays": 90 } }, "connect": { "http": "curl \"https://generativelanguage.googleapis.com/v1beta/models/gemini-4-hydrogen:generateContent\" \\\n -H \"x-goog-api-key: $GEMINI_API_KEY\" -H \"content-type: application/json\" \\\n -d '{\"contents\":[{\"parts\":[{\"text\":\"hello\"}]}]}'" }, "letme": { "capability": "https://letme.dev/inference.llm", "tool": "https://letme.dev/gemini-4-hydrogen" }, "sameCompany": [ "gemini-4-carbon", "vertex-ai", "embeddinggemma-2", "embeddinggemma-300m", "gemini-embedding", "vertex-ai-tuning", "cloud-run-gpus", "google-model-armor", "shieldgemma", "google-imagen", "gemini-omni-1-2-flash", "google-veo", "google-lyria", "google-speech-to-text", "google-cloud-tts", "gemini-live", "google-adk", "google-memory-bank", "google-secret-manager", "google-cloud-document-ai", "google-weather-api", "chrome-devtools-mcp", "puppeteer", "mcp-toolbox-databases", "google-maps-platform", "google-cloud-translation", "google-calendar-api", "firebase-cloud-messaging", "google-cloud-storage", "google-drive-api", "gemini-enterprise", "gemini-decision-1", "antigravity-cli", "gemini-cli", "harness2", "jules", "gemini-spark", "google-search-console", "google-ads-api", "google-forms", "google-sheets-api", "gmail-api", "google-people-api", "diffusiongemma-26b-a4b-it", "gemma-4-12b-it", "gemma-4-26b-a4b-it", "gemma-4-31b-it", "gemma-4-e2b-it", "gemma-4-e4b-it", "virustotal" ], "sameModel": [ "gemini-api" ], "area": "models", "unitPrices": [ { "item": "Gemini 4 Hydrogen input", "unit": "1m-tokens", "usd": 1.5, "note": "Flat across the 1M window" }, { "item": "Gemini 4 Hydrogen output", "unit": "1m-tokens", "usd": 7.5, "note": "Thinking tokens included" } ], "provenance": { "legalEntity": "Google LLC", "domain": "google.com", "domainRegistered": "1997-09-15", "domainNote": "The endpoint is on googleapis.com, Google's API domain. google.com was registered in 1997.", "endpointOnVendorDomain": true, "terms": "https://ai.google.dev/gemini-api/terms", "privacy": "https://policies.google.com/privacy", "statusPage": "https://aistudio.google.com/status", "changelog": "https://ai.google.dev/gemini-api/docs/changelog", "securityTxt": "valid", "checked": "2026-11-13", "score": 89 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/gemini-4-hydrogen.json", "live": { "slug": "gemini-4-hydrogen", "probe": { "target": "https://generativelanguage.googleapis.com/v1beta", "method": "get", "lastAt": "2026-11-13T23:58:42.468588204Z", "lastOk": true, "lastStatus": 404, "lastMs": 10, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 33, "p95ms24h": 85, "samples24h": 32, "samples30d": 32, "days": [ { "date": "2026-11-13", "probes": 32, "ok": 32 } ], "since": "2026-11-13T20:58:02.850712558Z" }, "vendorStatus": { "page": "https://aistudio.google.com/status", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-13T23:54:32.148379631Z" }, "updatedAt": "2026-11-13T23:58:42.468588204Z" }, "streak": { "days": 1, "from": "2026-11-13", "sinceWatching": true, "best": 1 } }, "answer": "Gemini 4 Hydrogen scores 64.9 (B) on agent readiness against SWE-2 Flash's 37.6 (F), and leads in 5 of 7 scored categories. SWE-2 Flash leads on reliability.", "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": 37.6, "grade": "F", "agentReady": false, "rank": 1382, "ranked": true, "rankOf": 1524, "categoryRank": 45, "methodology": "0.8", "run": "2026-10-01", "scores": { "ergonomics": 10, "maintenance": 53, "payments": 30, "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/batches/2026-11/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": "0.8", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 37.6 } ], "editorialScores": { "ergonomics": 10, "maintenance": 53, "payments": 30, "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", "lastMoved": "2026-11-13", "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" }, "sameCompany": [ "devin" ], "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": "2026-11-13T23:55:37.082199638Z" }, "securityTxt": { "url": "https://cognition.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-13T16:15:03.464575073Z" }, "llmsTxt": { "url": "https://docs.devin.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-13T15:56:08.865211016Z" }, "domain": { "domain": "cognition.com", "registered": "1995-03-03", "source": "https://rdap.verisign.com/com/v1/domain/cognition.com", "checkedAt": "2026-11-08T15:07:50.264680533Z" }, "updatedAt": "2026-11-13T23:55:37.082199638Z" } }, "edges": [ { "by": 80, "category": "ergonomics", "leads": "gemini-4-hydrogen", "name": "Agent ergonomics", "reasons": { "a": "Model reading for gemini-4-hydrogen on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Function calling, with forced calls by FunctionCallingConfig on the API (20). Structured output to a response_schema, listed as supported on the Cloud model page (13 of 15). Implicit caching on prefixes of 4,096 tokens or more with durable caching on by default and explicit caches not supported, per the Cloud model page; the announcement names no cached-input price (12 of 15). 1,048,576 tokens shared between input and output, with background long decode up to 1M (15). Batch at half price on the platform (10). Python and JavaScript SDKs, and an OpenAI-compatible Chat Completions surface (10). Error codes with backoff guidance (10 of 15). 20 + 13 + 12 + 15 + 10 + 10 + 10 = 90.", "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": 90, "b": 10 } }, { "by": 56, "category": "schema", "leads": "gemini-4-hydrogen", "name": "Schema \u0026 documentation", "reasons": { "a": "Model reading for gemini-4-hydrogen on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Discovery document for GenerateContent (20 of 25). llms.txt with Markdown twins (10). The Cloud developer guide says what Hydrogen takes, every parameter that's ignored or returns 400, the thought-signature rules and how to migrate from Gemini 3.8 Flash, though it doesn't document forced calls (15 of 20). Structured output to a JSON Schema with some keywords not enforced (10 of 15). Examples and an errors page (15). Dated changelog and model versions (15). 20 + 10 + 15 + 10 + 15 + 15 = 85.", "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": 85, "b": 29 } }, { "by": 32, "category": "maintenance", "leads": "gemini-4-hydrogen", "name": "Maintenance \u0026 community", "reasons": { "a": "Model reading for gemini-4-hydrogen on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Released on 12 November 2026, recorded in Google Cloud's release notes; the Gemini API changelog, last updated 30 October, has no entry for it yet (30). Google Cloud states a minimum of 45 days' notice before Hydrogen is retired, short and stated for Cloud only; the Gemini API's deprecations give earliest dates with no stated minimum (6 of 12). Shutdowns in the last 90 days kept to their table (4 of 8). Dated changelog (15). SDK replies not sampled (5 of 10). Current SDKs; the developer guide names the minimum google-genai, @google/genai, Go and Java versions (15). Runtimes stated (10). 30 + 6 + 4 + 15 + 5 + 15 + 10 = 85.", "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": 85, "b": 53 } }, { "by": 10, "category": "payments", "leads": "gemini-4-hydrogen", "name": "Payments \u0026 pricing", "reasons": { "a": "Model reading for gemini-4-hydrogen on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. No machine payment protocol (0). Prices published in Google's announcement without a login, $1.50 input and $7.50 output per million tokens, flat across the window; the Gemini API pricing page, now at aistudio.google.com, is still to be read for Hydrogen's row (20). A free tier with no card: Google's announcement puts Hydrogen on all tiers of the Gemini API, and the free tier needs no billing account per the gemini-api listing; its limits for Hydrogen are on that pricing page (20). A Google account and AI Studio for a key (0). 0 + 20 + 20 + 0 = 40.", "b": "Published rubric. No payment protocol (0). Plan prices are public, but no per-token price for SWE-2 Flash is on a readable page; the docs' cost table loads in the browser and the post gives only 'one-fifth the price' of SWE-2 (10). Free through 30 November 2026 on Devin Desktop and CLI, but the docs say Free tier users only have SWE-1.6, so whether the Free plan reaches it, and without a card, isn't confirmed; the in-between value used on the devin listing (10). A person signs in through a browser (0). 0 + 10 + 10 + 0 = 20. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30." }, "scores": { "a": 40, "b": 30 } }, { "by": 8, "category": "transparency", "leads": "gemini-4-hydrogen", "name": "Transparency \u0026 trust", "reasons": { "a": "Model reading for gemini-4-hydrogen on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Closed service with clear terms, SDKs Apache-2.0 (15). Free-tier content is used to improve products, paid-tier content isn't, abuse retention has no number, and request storage is on by default for new paid projects; the statements agree with each other (20 of 30). Deprecations table, and a stated 45-day minimum on Cloud (15 of 20). Data may be cached anywhere Google has facilities; no subprocessor list checked (5 of 20). A DeepMind model card gives a March 2026 knowledge cutoff, automated safety results and Frontier Safety Framework outcomes, with the full safety report marked coming soon. Every benchmark figure is Google's own. 15 + 20 + 15 + 5 = 55.", "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": 72, "b": 64 } }, { "by": 5, "category": "reliability", "leads": "swe-2-flash", "name": "Reliability", "reasons": { "a": "Model reading for gemini-4-hydrogen on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Status page at aistudio.google.com/status with no readable components or history (10 of 20) and no readable incident record (5 of 30). Rate-limit tiers and spend limits published, per-model limits in AI Studio (5 of 15). Backoff guidance for 429 and 503 and SDK retries (15). No SLA (0). Google Cloud's release notes and model page call Hydrogen generally available, a short-term release, under the same model ID; the Gemini API pages read don't name a stage, so full marks rest on Cloud's statement (10, a judgement call; Carbon, with no stage stated anywhere, got 5). 10 + 5 + 5 + 15 + 0 + 10 = 45.", "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": 45, "b": 50 } } ], "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Google", "b": "Cognition AI, Inc.", "name": "Vendor" }, { "a": "https://generativelanguage.googleapis.com/v1beta", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "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 model, used through the Gemini API and Google's apps under Google's terms", "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": "2026-11-12", "b": "2026-11-04", "name": "Last release" }, { "a": "2026-04-28", "b": "2026-06-30", "name": "Terms last updated" }, { "a": "2026-10-01", "b": "2026-03-09", "name": "Privacy policy last updated" }, { "a": "yes", "b": "yes, with an opt-out", "name": "Customer content may train models" }, { "a": "yes", "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": "not found in the text", "b": "yes", "name": "Arbitration or class-action waiver" } ], "faq": [ { "answer": "Gemini 4 Hydrogen scores 64.9 (B) on agent readiness against SWE-2 Flash's 37.6 (F), and leads in 5 of 7 scored categories. SWE-2 Flash leads on reliability.", "question": "Which is better for AI agents, Gemini 4 Hydrogen or SWE-2 Flash?" }, { "answer": "Gemini 4 Hydrogen needs an API key. SWE-2 Flash takes an API key or an OAuth sign-in.", "question": "Do Gemini 4 Hydrogen and SWE-2 Flash need an API key?" }, { "answer": "Gemini 4 Hydrogen has a hosted endpoint at https://generativelanguage.googleapis.com/v1beta. No hosted endpoint is listed for SWE-2 Flash.", "question": "Can an agent call Gemini 4 Hydrogen and SWE-2 Flash without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 85 against 29", "Agent ergonomics, 90 against 10", "Payments \u0026 pricing, 40 against 30", "Maintenance \u0026 community, 85 against 53", "Transparency \u0026 trust, 72 against 64" ], "also": [ "A hosted endpoint, with nothing to install" ], "goodFor": "Agents doing everyday coding, tool calls and document work at volume on the Gemini API, including ones that need to start on a free key, or as the executor beside Carbon or Argon.", "slug": "gemini-4-hydrogen", "watchFor": "temperature, top_p and top_k are ignored, and thinking_budget, MINIMAL, penalties and extra candidates return a 400" }, { "aheadOn": [ "Reliability, 50 against 45" ], "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": { "gemini-4-hydrogen": null, "swe-2-flash": [ { "causes": [ "method" ], "date": "2026-11-13", "delta": 1.2, "from": 36.4, "fromGrade": "F", "to": 37.6, "toGrade": "F" } ] }, "job": { "capability": "inference.llm", "name": "LLM inference" }, "others": [ { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-gemini-4-hydrogen.json", "title": "Amazon Bedrock vs Gemini 4 Hydrogen", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-gemini-4-hydrogen" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-swe-2-flash.json", "title": "Amazon Bedrock vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-gemini-4-hydrogen.json", "title": "Claude API vs Gemini 4 Hydrogen", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-gemini-4-hydrogen" }, { "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-gemini-4-hydrogen.json", "title": "Antseed vs Gemini 4 Hydrogen", "url": "https://www.anchorterminal.com/compare/antseed-vs-gemini-4-hydrogen" }, { "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/azure-openai-vs-gemini-4-hydrogen.json", "title": "Azure OpenAI in Foundry Models vs Gemini 4 Hydrogen", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-gemini-4-hydrogen" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-swe-2-flash.json", "title": "Azure OpenAI in Foundry Models vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-gemini-4-hydrogen.json", "title": "BlockRun.AI vs Gemini 4 Hydrogen", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-gemini-4-hydrogen" }, { "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-gemini-4-hydrogen.json", "title": "Cerebras Inference vs Gemini 4 Hydrogen", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-gemini-4-hydrogen" }, { "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/claude-fable-5-2-vs-gemini-4-hydrogen.json", "title": "Claude Fable 5.2 vs Gemini 4 Hydrogen", "url": "https://www.anchorterminal.com/compare/claude-fable-5-2-vs-gemini-4-hydrogen" }, { "json": "https://www.anchorterminal.com/compare/claude-fable-5-2-vs-swe-2-flash.json", "title": "Claude Fable 5.2 vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/claude-fable-5-2-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-gemini-4-hydrogen.json", "title": "Claude Mythos 5.2 vs Gemini 4 Hydrogen", "url": "https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-gemini-4-hydrogen" }, { "json": "https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-swe-2-flash.json", "title": "Claude Mythos 5.2 vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-gemini-4-hydrogen.json", "title": "Cloudflare AI Gateway vs Gemini 4 Hydrogen", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-gemini-4-hydrogen" }, { "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-gemini-4-hydrogen.json", "title": "Cloudflare Workers AI vs Gemini 4 Hydrogen", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-gemini-4-hydrogen" }, { "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-gemini-4-hydrogen.json", "title": "Cohere Chat API (Command models) vs Gemini 4 Hydrogen", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-gemini-4-hydrogen" }, { "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-gemini-4-hydrogen.json", "title": "DeepInfra vs Gemini 4 Hydrogen", "url": "https://www.anchorterminal.com/compare/deepinfra-vs-gemini-4-hydrogen" }, { "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-gemini-4-hydrogen.json", "title": "DeepSeek API vs Gemini 4 Hydrogen", "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-gemini-4-hydrogen" }, { "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/eden-ai-vs-gemini-4-hydrogen.json", "title": "Eden AI vs Gemini 4 Hydrogen", "url": "https://www.anchorterminal.com/compare/eden-ai-vs-gemini-4-hydrogen" }, { "json": "https://www.anchorterminal.com/compare/eden-ai-vs-swe-2-flash.json", "title": "Eden AI vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/eden-ai-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-gemini-4-hydrogen.json", "title": "Glimpse vs Gemini 4 Hydrogen", "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-gemini-4-hydrogen" }, { "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-gemini-4-hydrogen.json", "title": "Fireworks AI Inference vs Gemini 4 Hydrogen", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-4-hydrogen" }, { "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-4-carbon-vs-gemini-4-hydrogen.json", "title": "Gemini 4 Carbon vs Gemini 4 Hydrogen", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-gemini-4-hydrogen" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-swe-2-flash.json", "title": "Gemini 4 Carbon vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-gemini-api.json", "title": "Gemini 4 Hydrogen vs Gemini Developer API", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-gemini-api" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-groq.json", "title": "Gemini 4 Hydrogen vs GroqCloud", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-groq" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-hugging-face-inference-providers.json", "title": "Gemini 4 Hydrogen vs Hugging Face Inference Providers", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-hugging-face-inference-providers" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-hy4.json", "title": "Gemini 4 Hydrogen vs Tencent Hy4", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-hy4" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-jais-3.json", "title": "Gemini 4 Hydrogen vs Jais 3", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-meta-model-api.json", "title": "Gemini 4 Hydrogen vs Meta Model API", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-minimax-api.json", "title": "Gemini 4 Hydrogen vs MiniMax API", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-minimax-api" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-mistral-api.json", "title": "Gemini 4 Hydrogen vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-muse-ember.json", "title": "Gemini 4 Hydrogen vs Muse Ember", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-muse-spark-open.json", "title": "Gemini 4 Hydrogen vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-muse-spark-open" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-nemotron-3-5-super-vl.json", "title": "Gemini 4 Hydrogen vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-novita-ai.json", "title": "Gemini 4 Hydrogen vs Novita AI", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-novita-ai" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-openai-api.json", "title": "Gemini 4 Hydrogen vs OpenAI API", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-openai-api" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-openrouter.json", "title": "Gemini 4 Hydrogen vs OpenRouter", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-openrouter" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-prism-inference.json", "title": "Gemini 4 Hydrogen vs Prism Inference", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-ramp-router.json", "title": "Gemini 4 Hydrogen vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-reflection-beam.json", "title": "Gemini 4 Hydrogen vs Beam 1.0", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-reflection-beam" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-routerplus.json", "title": "Gemini 4 Hydrogen vs RouterPlus", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-routerplus" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-sambanova.json", "title": "Gemini 4 Hydrogen vs SambaCloud", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-sambanova" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-siliconflow.json", "title": "Gemini 4 Hydrogen vs SiliconFlow", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-siliconflow" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-simplismart.json", "title": "Gemini 4 Hydrogen vs Simplismart", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-simplismart" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-stepfun-api.json", "title": "Gemini 4 Hydrogen vs StepFun API", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-stepfun-api" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-tencent-tokenhub.json", "title": "Gemini 4 Hydrogen vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-together-inference.json", "title": "Gemini 4 Hydrogen vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-together-inference" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-vercel-ai-gateway.json", "title": "Gemini 4 Hydrogen vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-vertex-ai.json", "title": "Gemini 4 Hydrogen vs Vertex AI (Gemini Enterprise Agent Platform)", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-vertex-ai" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-xai-api.json", "title": "Gemini 4 Hydrogen vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-xai-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-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/hugging-face-inference-providers-vs-swe-2-flash.json", "title": "Hugging Face Inference Providers vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-swe-2-flash.json", "title": "Tencent Hy4 vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/hy4-vs-swe-2-flash" }, { "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-swe-2-flash.json", "title": "Meta Model API vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/minimax-api-vs-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-ember-vs-swe-2-flash.json", "title": "Muse Ember vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/muse-ember-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" }, { "json": "https://www.anchorterminal.com/compare/swe-2-flash-vs-vertex-ai.json", "title": "SWE-2 Flash vs Vertex AI (Gemini Enterprise Agent Platform)", "url": "https://www.anchorterminal.com/compare/swe-2-flash-vs-vertex-ai" }, { "json": "https://www.anchorterminal.com/compare/swe-2-flash-vs-xai-api.json", "title": "SWE-2 Flash vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/swe-2-flash-vs-xai-api" } ], "panel": null, "scores": [ { "by": 5, "edge": "swe-2-flash", "gemini-4-hydrogen": 45, "key": "reliability", "name": "Reliability", "swe-2-flash": 50, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 56, "edge": "gemini-4-hydrogen", "gemini-4-hydrogen": 85, "key": "schema", "name": "Schema \u0026 documentation", "swe-2-flash": 29, "weight": 13 }, { "by": 80, "edge": "gemini-4-hydrogen", "gemini-4-hydrogen": 90, "key": "ergonomics", "name": "Agent ergonomics", "swe-2-flash": 10, "weight": 13 }, { "by": 3, "edge": "swe-2-flash", "gemini-4-hydrogen": 50, "key": "security", "name": "Security \u0026 auth", "swe-2-flash": 53, "weight": 14 }, { "by": 10, "edge": "gemini-4-hydrogen", "gemini-4-hydrogen": 40, "key": "payments", "name": "Payments \u0026 pricing", "swe-2-flash": 30, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 32, "edge": "gemini-4-hydrogen", "gemini-4-hydrogen": 85, "key": "maintenance", "name": "Maintenance \u0026 community", "swe-2-flash": 53, "weight": 7 }, { "by": 8, "edge": "gemini-4-hydrogen", "gemini-4-hydrogen": 72, "key": "transparency", "name": "Transparency \u0026 trust", "swe-2-flash": 64, "weight": 7 } ], "summary": "Gemini 4 Hydrogen scores 64.9 (B) on agent readiness against SWE-2 Flash's 37.6 (F), and leads in 5 of 7 scored categories. SWE-2 Flash leads on reliability. Both do llm inference.", "tasks": null, "tutorials": [], "verdicts": { "gemini-4-hydrogen": "Google's fast Gemini 4 model, on every tier of the Gemini API including the free one, at $1.50 and $7.50 per million tokens with a 1M-token budget, four thinking levels, function calling and structured output. Sampling parameters are ignored, explicit caching isn't supported, it's a short-term release with 45 days' notice on Cloud, and the benchmarks are Google's.", "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/gemini-4-hydrogen-vs-swe-2-flash", "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-swe-2-flash.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-swe-2-flash.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-swe-2-flash.min.md" }, "markdown": "Gemini 4 Hydrogen scores 64.9 (B) on agent readiness against SWE-2 Flash's 37.6 (F), and leads in 5 of 7 scored categories. SWE-2 Flash leads on reliability. Both do llm inference.\n\n- Gemini 4 Hydrogen: grade B, 64.9/100, rank #546 of 1524. Markdown https://www.anchorterminal.com/tools/gemini-4-hydrogen.md · JSON https://www.anchorterminal.com/api/v1/tools/gemini-4-hydrogen.json\n- SWE-2 Flash: grade F, 37.6/100, rank #1382 of 1524. 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 1044 models comparisons: https://www.anchorterminal.com/compare/inference/index.md\n\n## Which one, for what\n\n### Gemini 4 Hydrogen (B)\n\nGood for: Agents doing everyday coding, tool calls and document work at volume on the Gemini API, including ones that need to start on a free key, or as the executor beside Carbon or Argon.\n\nAhead on:\n- Schema \u0026 documentation, 85 against 29\n- Agent ergonomics, 90 against 10\n- Payments \u0026 pricing, 40 against 30\n- Maintenance \u0026 community, 85 against 53\n- Transparency \u0026 trust, 72 against 64\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: temperature, top_p and top_k are ignored, and thinking_budget, MINIMAL, penalties and extra candidates return a 400\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 45\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: Gemini 4 Hydrogen +80\n\n- Gemini 4 Hydrogen (90): Model reading for gemini-4-hydrogen on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Function calling, with forced calls by FunctionCallingConfig on the API (20). Structured output to a response_schema, listed as supported on the Cloud model page (13 of 15). Implicit caching on prefixes of 4,096 tokens or more with durable caching on by default and explicit caches not supported, per the Cloud model page; the announcement names no cached-input price (12 of 15). 1,048,576 tokens shared between input and output, with background long decode up to 1M (15). Batch at half price on the platform (10). Python and JavaScript SDKs, and an OpenAI-compatible Chat Completions surface (10). Error codes with backoff guidance (10 of 15). 20 + 13 + 12 + 15 + 10 + 10 + 10 = 90.\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: Gemini 4 Hydrogen +56\n\n- Gemini 4 Hydrogen (85): Model reading for gemini-4-hydrogen on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Discovery document for GenerateContent (20 of 25). llms.txt with Markdown twins (10). The Cloud developer guide says what Hydrogen takes, every parameter that's ignored or returns 400, the thought-signature rules and how to migrate from Gemini 3.8 Flash, though it doesn't document forced calls (15 of 20). Structured output to a JSON Schema with some keywords not enforced (10 of 15). Examples and an errors page (15). Dated changelog and model versions (15). 20 + 10 + 15 + 10 + 15 + 15 = 85.\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### Maintenance \u0026 community: Gemini 4 Hydrogen +32\n\n- Gemini 4 Hydrogen (85): Model reading for gemini-4-hydrogen on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Released on 12 November 2026, recorded in Google Cloud's release notes; the Gemini API changelog, last updated 30 October, has no entry for it yet (30). Google Cloud states a minimum of 45 days' notice before Hydrogen is retired, short and stated for Cloud only; the Gemini API's deprecations give earliest dates with no stated minimum (6 of 12). Shutdowns in the last 90 days kept to their table (4 of 8). Dated changelog (15). SDK replies not sampled (5 of 10). Current SDKs; the developer guide names the minimum google-genai, @google/genai, Go and Java versions (15). Runtimes stated (10). 30 + 6 + 4 + 15 + 5 + 15 + 10 = 85.\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### Payments \u0026 pricing: Gemini 4 Hydrogen +10\n\n- Gemini 4 Hydrogen (40): Model reading for gemini-4-hydrogen on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. No machine payment protocol (0). Prices published in Google's announcement without a login, $1.50 input and $7.50 output per million tokens, flat across the window; the Gemini API pricing page, now at aistudio.google.com, is still to be read for Hydrogen's row (20). A free tier with no card: Google's announcement puts Hydrogen on all tiers of the Gemini API, and the free tier needs no billing account per the gemini-api listing; its limits for Hydrogen are on that pricing page (20). A Google account and AI Studio for a key (0). 0 + 20 + 20 + 0 = 40.\n- SWE-2 Flash (30): Published rubric. No payment protocol (0). Plan prices are public, but no per-token price for SWE-2 Flash is on a readable page; the docs' cost table loads in the browser and the post gives only 'one-fifth the price' of SWE-2 (10). Free through 30 November 2026 on Devin Desktop and CLI, but the docs say Free tier users only have SWE-1.6, so whether the Free plan reaches it, and without a card, isn't confirmed; the in-between value used on the devin listing (10). A person signs in through a browser (0). 0 + 10 + 10 + 0 = 20. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30.\n\n### Transparency \u0026 trust: Gemini 4 Hydrogen +8\n\n- Gemini 4 Hydrogen (72): Model reading for gemini-4-hydrogen on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Closed service with clear terms, SDKs Apache-2.0 (15). Free-tier content is used to improve products, paid-tier content isn't, abuse retention has no number, and request storage is on by default for new paid projects; the statements agree with each other (20 of 30). Deprecations table, and a stated 45-day minimum on Cloud (15 of 20). Data may be cached anywhere Google has facilities; no subprocessor list checked (5 of 20). A DeepMind model card gives a March 2026 knowledge cutoff, automated safety results and Frontier Safety Framework outcomes, with the full safety report marked coming soon. Every benchmark figure is Google's own. 15 + 20 + 15 + 5 = 55.\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 +5\n\n- Gemini 4 Hydrogen (45): Model reading for gemini-4-hydrogen on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Status page at aistudio.google.com/status with no readable components or history (10 of 20) and no readable incident record (5 of 30). Rate-limit tiers and spend limits published, per-model limits in AI Studio (5 of 15). Backoff guidance for 429 and 503 and SDK retries (15). No SLA (0). Google Cloud's release notes and model page call Hydrogen generally available, a short-term release, under the same model ID; the Gemini API pages read don't name a stage, so full marks rest on Cloud's statement (10, a judgement call; Carbon, with no stage stated anywhere, got 5). 10 + 5 + 5 + 15 + 0 + 10 = 45.\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## Score by category\n\n| Category | Weight | Gemini 4 Hydrogen | SWE-2 Flash | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 45 | 50 | SWE-2 Flash +5 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 85 | 29 | Gemini 4 Hydrogen +56 |\n| Agent ergonomics | 13% (16.2 this run) | 90 | 10 | Gemini 4 Hydrogen +80 |\n| Security \u0026 auth | 14% (17.5 this run) | 50 | 53 | SWE-2 Flash +3 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 30 | Gemini 4 Hydrogen +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 85 | 53 | Gemini 4 Hydrogen +32 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 72 | 64 | Gemini 4 Hydrogen +8 |\n| Negative events | ≤15 | 0 | -2 | |\n| **Total** | | **64.9 · B** | **37.6 · F** | |\n\n## Facts side by side\n\n| Fact | Gemini 4 Hydrogen | SWE-2 Flash |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Google | Cognition AI, Inc. |\n| Hosted endpoint | `https://generativelanguage.googleapis.com/v1beta` | no (local only) |\n| Transports | | |\n| Auth | API key | OAuth or key |\n| Pricing | Pay per use | Freemium |\n| x402 | no | no |\n| Licence | Closed model, used through the Gemini API and Google's apps under Google's terms | 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 | 2026-11-12 | 2026-11-04 |\n| Terms last updated | 2026-04-28 | 2026-06-30 |\n| Privacy policy last updated | 2026-10-01 | 2026-03-09 |\n| Customer content may train models | yes | yes, with an opt-out |\n| Terms restrict automated access | yes | 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 | not found in the text | yes |\n\n## How the scores have moved\n\n### Gemini 4 Hydrogen\n\nNo score change since it was listed.\n\n### SWE-2 Flash\n\n- +1.2 on 13 November 2026: checklist\n\n## Verdicts\n\n**Gemini 4 Hydrogen.** Google's fast Gemini 4 model, on every tier of the Gemini API including the free one, at $1.50 and $7.50 per million tokens with a 1M-token budget, four thinking levels, function calling and structured output. Sampling parameters are ignored, explicit caching isn't supported, it's a short-term release with 45 days' notice on Cloud, and the benchmarks are Google's.\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### Gemini 4 Hydrogen\n\n1. Call generateContent at https://generativelanguage.googleapis.com/v1beta with model gemini-4-hydrogen and an x-goog-api-key\n2. Set thinking_level instead of thinking_budget; the default is HIGH, so set MEDIUM to keep 3.8 Flash's latency\n3. Don't send temperature, top_p, top_k, penalties or candidate_count above 1\n4. Pass every thought_signature back in its original part, on the first parallel functionCall only, or the call returns a 400\n5. Put static content of 4,096 tokens or more first so implicit caching applies, and keep confidential prompts off the free tier\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, Gemini 4 Hydrogen or SWE-2 Flash?\n\nGemini 4 Hydrogen scores 64.9 (B) on agent readiness against SWE-2 Flash's 37.6 (F), and leads in 5 of 7 scored categories. SWE-2 Flash leads on reliability.\n\n### Do Gemini 4 Hydrogen and SWE-2 Flash need an API key?\n\nGemini 4 Hydrogen needs an API key. SWE-2 Flash takes an API key or an OAuth sign-in.\n\n### Can an agent call Gemini 4 Hydrogen and SWE-2 Flash without installing anything?\n\nGemini 4 Hydrogen has a hosted endpoint at https://generativelanguage.googleapis.com/v1beta. 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/gemini-4-hydrogen-vs-swe-2-flash.json, and with the fewest tokens: https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-swe-2-flash.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"gemini-4-hydrogen\", \"b\": \"swe-2-flash\"}`. From a terminal: `anchor compare gemini-4-hydrogen swe-2-flash`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/gemini-4-hydrogen.json and https://www.anchorterminal.com/api/v1/tools/swe-2-flash.json\n\n## Other comparisons with Gemini 4 Hydrogen or SWE-2 Flash\n\n- [Amazon Bedrock vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/amazon-bedrock-vs-gemini-4-hydrogen.md)\n- [Amazon Bedrock vs SWE-2 Flash](https://www.anchorterminal.com/compare/amazon-bedrock-vs-swe-2-flash.md)\n- [Claude API vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/anthropic-api-vs-gemini-4-hydrogen.md)\n- [Claude API vs SWE-2 Flash](https://www.anchorterminal.com/compare/anthropic-api-vs-swe-2-flash.md)\n- [Antseed vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/antseed-vs-gemini-4-hydrogen.md)\n- [Antseed vs SWE-2 Flash](https://www.anchorterminal.com/compare/antseed-vs-swe-2-flash.md)\n- [Azure OpenAI in Foundry Models vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/azure-openai-vs-gemini-4-hydrogen.md)\n- [Azure OpenAI in Foundry Models vs SWE-2 Flash](https://www.anchorterminal.com/compare/azure-openai-vs-swe-2-flash.md)\n- [BlockRun.AI vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/blockrun-ai-vs-gemini-4-hydrogen.md)\n- [BlockRun.AI vs SWE-2 Flash](https://www.anchorterminal.com/compare/blockrun-ai-vs-swe-2-flash.md)\n- [Cerebras Inference vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/cerebras-inference-vs-gemini-4-hydrogen.md)\n- [Cerebras Inference vs SWE-2 Flash](https://www.anchorterminal.com/compare/cerebras-inference-vs-swe-2-flash.md)\n- [Claude Fable 5.2 vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/claude-fable-5-2-vs-gemini-4-hydrogen.md)\n- [Claude Fable 5.2 vs SWE-2 Flash](https://www.anchorterminal.com/compare/claude-fable-5-2-vs-swe-2-flash.md)\n- [Claude Mythos 5.2 vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-gemini-4-hydrogen.md)\n- [Claude Mythos 5.2 vs SWE-2 Flash](https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-swe-2-flash.md)\n- [Cloudflare AI Gateway vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-gemini-4-hydrogen.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 Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-gemini-4-hydrogen.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 Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/cohere-chat-vs-gemini-4-hydrogen.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 Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/deepinfra-vs-gemini-4-hydrogen.md)\n- [DeepInfra vs SWE-2 Flash](https://www.anchorterminal.com/compare/deepinfra-vs-swe-2-flash.md)\n- [DeepSeek API vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/deepseek-api-vs-gemini-4-hydrogen.md)\n- [DeepSeek API vs SWE-2 Flash](https://www.anchorterminal.com/compare/deepseek-api-vs-swe-2-flash.md)\n- [Eden AI vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/eden-ai-vs-gemini-4-hydrogen.md)\n- [Eden AI vs SWE-2 Flash](https://www.anchorterminal.com/compare/eden-ai-vs-swe-2-flash.md)\n- [Glimpse vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/elorian-glimpse-vs-gemini-4-hydrogen.md)\n- [Glimpse vs SWE-2 Flash](https://www.anchorterminal.com/compare/elorian-glimpse-vs-swe-2-flash.md)\n- [Fireworks AI Inference vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-4-hydrogen.md)\n- [Fireworks AI Inference vs SWE-2 Flash](https://www.anchorterminal.com/compare/fireworks-inference-vs-swe-2-flash.md)\n- [Gemini 4 Carbon vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-gemini-4-hydrogen.md)\n- [Gemini 4 Carbon vs SWE-2 Flash](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-swe-2-flash.md)\n- [Gemini 4 Hydrogen vs Gemini Developer API](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-gemini-api.md)\n- [Gemini 4 Hydrogen vs GroqCloud](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-groq.md)\n- [Gemini 4 Hydrogen vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-hugging-face-inference-providers.md)\n- [Gemini 4 Hydrogen vs Tencent Hy4](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-hy4.md)\n- [Gemini 4 Hydrogen vs Jais 3](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-jais-3.md)\n- [Gemini 4 Hydrogen vs Meta Model API](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-meta-model-api.md)\n- [Gemini 4 Hydrogen vs MiniMax API](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-minimax-api.md)\n- [Gemini 4 Hydrogen vs Mistral AI API](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-mistral-api.md)\n- [Gemini 4 Hydrogen vs Muse Ember](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-muse-ember.md)\n- [Gemini 4 Hydrogen vs Muse Spark Open](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-muse-spark-open.md)\n- [Gemini 4 Hydrogen vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-nemotron-3-5-super-vl.md)\n- [Gemini 4 Hydrogen vs Novita AI](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-novita-ai.md)\n- [Gemini 4 Hydrogen vs OpenAI API](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-openai-api.md)\n- [Gemini 4 Hydrogen vs OpenRouter](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-openrouter.md)\n- [Gemini 4 Hydrogen vs Prism Inference](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-prism-inference.md)\n- [Gemini 4 Hydrogen vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-ramp-router.md)\n- [Gemini 4 Hydrogen vs Beam 1.0](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-reflection-beam.md)\n- [Gemini 4 Hydrogen vs RouterPlus](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-routerplus.md)\n- [Gemini 4 Hydrogen vs SambaCloud](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-sambanova.md)\n- [Gemini 4 Hydrogen vs SiliconFlow](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-siliconflow.md)\n- [Gemini 4 Hydrogen vs Simplismart](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-simplismart.md)\n- [Gemini 4 Hydrogen vs StepFun API](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-stepfun-api.md)\n- [Gemini 4 Hydrogen vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-tencent-tokenhub.md)\n- [Gemini 4 Hydrogen vs Together AI Inference](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-together-inference.md)\n- [Gemini 4 Hydrogen vs Vercel AI Gateway](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-vercel-ai-gateway.md)\n- [Gemini 4 Hydrogen vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-vertex-ai.md)\n- [Gemini 4 Hydrogen vs xAI API (Grok)](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-xai-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 SWE-2 Flash](https://www.anchorterminal.com/compare/groq-vs-swe-2-flash.md)\n- [Hugging Face Inference Providers vs SWE-2 Flash](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-swe-2-flash.md)\n- [Tencent Hy4 vs SWE-2 Flash](https://www.anchorterminal.com/compare/hy4-vs-swe-2-flash.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 SWE-2 Flash](https://www.anchorterminal.com/compare/meta-model-api-vs-swe-2-flash.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 Ember vs SWE-2 Flash](https://www.anchorterminal.com/compare/muse-ember-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- [SWE-2 Flash vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/swe-2-flash-vs-vertex-ai.md)\n- [SWE-2 Flash vs xAI API (Grok)](https://www.anchorterminal.com/compare/swe-2-flash-vs-xai-api.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": "2026-11-14", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.8", "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": "Gemini 4 Hydrogen vs SWE-2 Flash", "url": "" } ], "description": "Gemini 4 Hydrogen scores 64.9 (B) to SWE-2 Flash's 37.6 (F) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Gemini 4 Hydrogen B 64.9", "SWE-2 Flash F 37.6", "scores" ], "h1": "Gemini 4 Hydrogen vs SWE-2 Flash", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/gemini-4-hydrogen-vs-swe-2-flash", "published": "2026-10-01", "section": "tools", "title": "Gemini 4 Hydrogen vs SWE-2 Flash for AI agents (2026)", "toc": null, "updated": "2026-11-13", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-swe-2-flash" }, "tokens": { "markdown": 6950, "slim": 980 }, "version": 1 }