{ "data": { "a": { "slug": "fireworks-inference", "name": "Fireworks AI Inference", "vendor": "Fireworks AI", "vendorUrl": "https://fireworks.ai", "kind": "http-api", "category": "inference", "summary": "Fireworks AI Inference runs open models through OpenAI-compatible chat and completion APIs. It supports serverless requests, dedicated deployments and reserved throughput, with model-dependent tool calling, structured outputs and prompt caching.", "url": "https://www.anchorterminal.com/tools/fireworks-inference", "markdownUrl": "https://www.anchorterminal.com/tools/fireworks-inference.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/fireworks-inference.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/fireworks-inference.json", "dns": "fireworks-inference.grade.anchorterminal.com", "repo": "https://github.com/fw-ai-external/python-sdk", "license": "Proprietary hosted service. The official Python SDK is Apache-2.0; served models retain their own licences.", "transports": [ "http" ], "remoteUrl": "https://api.fireworks.ai/inference/v1", "packages": [ { "registry": "pypi", "name": "fireworks-ai", "main": true } ], "auth": "api-key", "authNotes": "Bearer API keys can belong to users or service accounts. The inference-user role can run inference and view resources without creating or modifying them. An administrator can create and manage service-account keys.", "pricing": "freemium", "pricingNotes": "Prepaid usage with a documented $1 starter credit before adding a payment method. Standard DeepSeek V4.1 Flash is $0.30 input, $0.006 cached input and $1.20 output per million tokens. Batch is half price, and Priority, Fast, US-only and dedicated rates differ. GPT OSS 120B leaves serverless on 7 November 2026.", "priceSummary": "Freemium", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 payment route found in the reviewed inference and billing documentation on 19 October 2026.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 10, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-19" }, "docsUrl": "https://docs.fireworks.ai", "llmsTxt": "https://docs.fireworks.ai/llms.txt", "openapi": "https://docs.fireworks.ai/text-completion.openapi.yaml", "capabilities": [ "inference.llm", "inference.open-weights" ], "tags": [ "official", "http-api", "inference", "api-key", "openapi", "llms-txt", "freemium" ], "lastRelease": "2026-10-27", "graded": true, "anchor": { "graded": true, "score": 71.8, "grade": "BB", "agentReady": true, "rank": 245, "ranked": true, "rankOf": 1524, "categoryRank": 11, "methodology": "0.8", "run": "2026-10-01", "scores": { "ergonomics": 80, "maintenance": 65, "payments": 60, "reliability": 70, "schema": 93, "security": 77, "transparency": 69 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": -3, "negativeNotes": [ "On 2026-08-27 Fireworks removed MiniMax M2.7, GPT OSS 20B, Kimi K2.6 Turbo and Fast, Kimi K2.7 Code Fast and DeepSeek V4 Pro from serverless 'effective August 27, 2026', in a changelog entry posted that day, against its own stated minimum of two weeks' notice (https://docs.fireworks.ai/updates/changelog)" ], "verdict": "Inference-only service accounts, published per-token prices, zero retention for chat inference and terms that rule out training on customer content support production use. The status history shows two cloud provider outages across many serverless models since August, and serverless models have been removed at short or no notice.", "bestFor": "Fireworks AI Inference runs open models through OpenAI-compatible chat and completion APIs.", "strengths": [ "An inference-user role limits service accounts to calling models, with no rights to create or change resources", "Chat inference keeps no prompts or outputs by default, and the terms rule out training on customer content", "Public OpenAPI 3.1, per-model prices, and 429 guidance that names Retry-After and backoff with jitter", "Prompt caching on by default for every serverless model, and batch at half price" ], "weaknesses": [ "Cloud provider outages on 11 August and 14 October hit many serverless models for hours", "Five serverless models were removed on 27 August the day the change was posted, despite a stated two-week minimum", "The Responses API stores conversations for up to 30 days by default unless store is false", "No security.txt, disclosure policy or bug bounty found, and the trust centre needs JavaScript" ], "agentNotes": [ "Use an inference-user service account and keep FIREWORKS_API_KEY in a secrets manager.", "Use https://api.fireworks.ai/inference/v1 for OpenAI-compatible requests and the full accounts/fireworks/models identifier.", "Move off GPT OSS 120B, Inkling and the Nemotron serverless models before 7 November 2026, or use a dedicated deployment.", "Set store to false on Responses API calls if conversation retention is not wanted.", "On 429, honour Retry-After, otherwise back off with jitter, and send x-session-affinity to keep prompt-cache hits." ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 4.3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.8", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 71.8 } ], "editorialScores": { "ergonomics": 80, "maintenance": 65, "payments": 60, "reliability": 70, "schema": 93, "security": 77, "transparency": 65 }, "provenanceScore": 73, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "lastMoved": "2026-11-13", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "http": "curl 'https://api.fireworks.ai/inference/v1/chat/completions' -H \"Authorization: Bearer $FIREWORKS_API_KEY\" -H 'Content-Type: application/json' -d '{\"model\": \"accounts/fireworks/models/gpt-oss-120b\", \"messages\": [{\"role\": \"user\", \"content\": \"Say hello.\"}], \"max_tokens\": 128}'" }, "letme": { "capability": "https://letme.dev/inference.llm", "tool": "https://letme.dev/fireworks-inference" }, "sameCompany": [ "fireworks-fine-tuning" ], "area": "models", "unitPrices": [ { "item": "DeepSeek V4.1 Flash input", "unit": "1m-tokens", "usd": 0.3, "note": "Serverless standard rate, per million tokens, checked 1 November 2026" }, { "item": "DeepSeek V4.1 Flash output", "unit": "1m-tokens", "usd": 1.2, "note": "Serverless standard rate, per million tokens, checked 1 November 2026" } ], "provenance": { "legalEntity": "Fireworks.ai, Inc.", "domain": "fireworks.ai", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://fireworks.ai/terms-of-service", "privacy": "https://fireworks.ai/privacy-policy", "statusPage": "https://status.fireworks.ai", "changelog": "https://docs.fireworks.ai/updates/changelog", "securityTxt": "none", "checked": "2026-11-01", "notes": [ "Legal identity from the terms of service (last updated 10 July 2026), which name Fireworks.ai, Inc. and Delaware law, read on 1 November 2026. Domain registration was not checked.", "The SDK repository is not the source for the hosted inference service.", "fireworks.ai/.well-known/security.txt returned 404 on 1 November 2026." ], "score": 73 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/fireworks-inference.json", "live": { "slug": "fireworks-inference", "probe": { "target": "https://api.fireworks.ai/inference/v1", "method": "get", "lastAt": "2026-11-13T23:58:41.578187311Z", "lastOk": true, "lastStatus": 404, "lastMs": 8, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 10, "p95ms24h": 49, "samples24h": 239, "samples30d": 6299, "days": [ { "date": "2026-10-19", "probes": 173, "ok": 173 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 253, "ok": 253 }, { "date": "2026-10-22", "probes": 253, "ok": 253 }, { "date": "2026-10-23", "probes": 248, "ok": 248 }, { "date": "2026-10-24", "probes": 251, "ok": 251 }, { "date": "2026-10-25", "probes": 250, "ok": 250 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 251, "ok": 251 }, { "date": "2026-10-29", "probes": 248, "ok": 248 }, { "date": "2026-10-30", "probes": 249, "ok": 249 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 248, "ok": 248 }, { "date": "2026-11-04", "probes": 246, "ok": 246 }, { "date": "2026-11-05", "probes": 185, "ok": 185 }, { "date": "2026-11-06", "probes": 241, "ok": 241 }, { "date": "2026-11-07", "probes": 243, "ok": 243 }, { "date": "2026-11-08", "probes": 243, "ok": 243 }, { "date": "2026-11-09", "probes": 243, "ok": 243 }, { "date": "2026-11-10", "probes": 244, "ok": 244 }, { "date": "2026-11-11", "probes": 244, "ok": 244 }, { "date": "2026-11-12", "probes": 245, "ok": 245 }, { "date": "2026-11-13", "probes": 238, "ok": 238 } ], "since": "2026-10-19T00:00:00Z" }, "vendorStatus": { "page": "https://status.fireworks.ai", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-13T23:54:29.737635556Z" }, "versions": [ { "registry": "github", "name": "fw-ai-external/python-sdk", "version": "v1.2.33", "released": "2026-11-08", "seenAt": "2026-11-13T08:35:16.188462992Z" }, { "registry": "pypi", "name": "fireworks-ai", "version": "1.2.33", "released": "2026-11-08", "seenAt": "2026-11-13T08:35:15.999766103Z" } ], "githubStars": 11, "pypiWeekly": 342653, "securityTxt": { "url": "https://fireworks.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-13T16:16:40.110493173Z" }, "llmsTxt": { "url": "https://docs.fireworks.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-13T15:54:18.800058831Z" }, "domain": { "domain": "fireworks.ai", "registered": "2020-03-11", "source": "https://rdap.identitydigital.services/rdap/domain/fireworks.ai", "checkedAt": "2026-11-08T14:52:06.595664059Z" }, "github": { "repo": "fw-ai-external/python-sdk", "checkedAt": "2026-11-09T10:01:08.048536565Z", "stars": 11, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-08T07:56:06Z", "openIssues": 2, "openPRs": 2, "issuesOpened90d": 1, "issuesClosed90d": 0, "prsMerged90d": 27, "ci": { "branch": "main", "runs": 50, "success": 50, "failure": 0, "other": 0, "latest": "success", "latestAt": "2026-11-08T07:11:17Z" }, "replies": { "sampled": 3, "unanswered": 2, "medianDays": 17.9 } }, "updatedAt": "2026-11-13T23:58:41.578187311Z" }, "streak": { "days": 26, "from": "2026-10-19", "sinceWatching": true, "best": 26 } }, "answer": "Fireworks AI Inference scores 71.8 (BB) on agent readiness against Gemini 4 Hydrogen's 64.9 (B), and leads in 4 of 7 scored categories. Gemini 4 Hydrogen leads on agent ergonomics and maintenance \u0026 community.", "b": { "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 } }, "edges": [ { "by": 27, "category": "security", "leads": "fireworks-inference", "name": "Security \u0026 auth", "reasons": { "a": "Read by the HTTP API checklist, as for cerebras-inference and together-inference. Service accounts with API keys issued on their behalf, roles assigned at creation and changeable (30). An inference-user role can call models but not create or modify resources (20). No inference prompt-injection mitigation established (0). Enterprise audit logs with a REST API, and cost exports per API key (15). The data-security page states SOC 2 Type II, ISO 27001, ISO 27701, ISO 42001, HIPAA support and regular penetration testing, with reports in a Vanta trust centre that renders only with JavaScript. fireworks.ai/.well-known/security.txt answered 404 on 1 November, as on 19 October, and no disclosure policy or bug bounty was found. That matches people-data-labs (12) and launchdarkly (12), which state SOC 2 Type II and ISO 27001 with no security.txt, disclosure policy or bounty, so the 20 the 19 October check gave is corrected (12). The terms (section 3.6) rule out training on customer content and inference has zero retention by default, recorded for reviewers and not scored on this checklist. 30+20+0+15+12 = 77.", "b": "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. Keys bound to a service account and restricted to the Gemini API, with no scopes and a token accepted in the URL (15 of 30, the platform's deduction). Hydrogen is on the free tier, where Google's terms say content is used to improve products and may be read by humans; paid-tier content isn't (10 of 20, the platform's reading; Carbon, paid tier only, got 15). Abuse retention has no number and new paid projects store requests by default since 26 October; Google's prompt-injection figure (2.3 times more resilient on Gray Swan's benchmark) is its own, and the model card says jailbreak resistance is still being improved (5 of 15). Request logs for billed projects (15). security.txt and a reward programme, no certification naming the API (5 of 20). 15 + 10 + 5 + 15 + 5 = 50." }, "scores": { "a": 77, "b": 50 } }, { "by": 25, "category": "reliability", "leads": "fireworks-inference", "name": "Reliability", "reasons": { "a": "Public status page at status.fireworks.ai with a component per serverless model (20). The history page, read on 1 November, lists 236 incidents from 3 August to 31 October, nearly all short degradations of a single serverless model. Two hit many serverless models at once. On 11 August a cloud provider outage was 'affecting many of our serverless and dedicated deployments', with five serverless components (GPT OSS 120B, MiniMax M3 and the three Kimi K3 endpoints) in partial outage from 17:15 to 20:55 UTC and again from 01:36 to 01:49 UTC on 12 August, resolved 13 August. On 14 October a cloud provider outage set 18 serverless components to degraded performance, GPT OSS 120B, Kimi K3 and GLM 5.3 among them, from 23:06 UTC, with requests to them that 'may fail', recovery 'across the board' at 00:59 UTC on 15 October and the incident resolved at 01:53. Each is an hour or more of errors across most of the serverless catalogue, so two majors. Two majors sit between the checklist's one major (10) and several (0), so 5, as deepseek-api, black-forest-labs and telnyx-voice are read (5). The 19 October check gave the same 5 because no 90-day history could be read. A 30 October incident on deployment creation, dedicated training and batch inference was still open on 1 November. Numeric adaptive ceilings by model size, 216M total prompt, 54M uncached prompt and 2.16M generated tokens a minute for Small models (15). The rate-limits page says to honour `Retry-After` on 429 and otherwise back off with jitter, and the reliability guide covers timeouts and retries (15). Reserved throughput is 'covered by a throughput SLA' with no figure published (5 of 10). Serverless is generally available (10). 20+5+15+15+5+10 = 70.", "b": "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." }, "scores": { "a": 70, "b": 45 } }, { "by": 20, "category": "payments", "leads": "fireworks-inference", "name": "Payments \u0026 pricing", "reasons": { "a": "No machine payment protocol in the docs index or billing pages, re-read on 1 November (0). Public per-token prices by model and serving mode (20). The credits FAQ documents a $1 starter credit that runs without a payment method, after which the account is suspended until one is added (20). Account signup and credit purchases need a person (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.", "b": "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." }, "scores": { "a": 60, "b": 40 } }, { "by": 20, "category": "maintenance", "leads": "gemini-4-hydrogen", "name": "Maintenance \u0026 community", "reasons": { "a": "Read by the HTTP API checklist, as for cerebras-inference and together-inference. Rune 26B-A4B joined serverless on 27 October, five days before this check (30). Dated changelog entries several times a month, among them 27, 21, 19 and 18 October (20). Support replies not tested (0). Official Python SDK current, v1.2.30 tagged on 21 October after eleven tags from 1 October, no official TypeScript SDK (15). Dependency health not audited (0). The serverless overview promises 'at least 2 weeks advance notice' before a model is removed, and the 27 August removals were posted the day they took effect (see the deduction). 30+20+0+15+0 = 65.", "b": "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." }, "scores": { "a": 65, "b": 85 } }, { "by": 10, "category": "ergonomics", "leads": "gemini-4-hydrogen", "name": "Agent ergonomics", "reasons": { "a": "Read by the HTTP API checklist, as for cerebras-inference and together-inference. Compact model API with bounded output, `max_tokens` and streaming (25). Token limits, structured outputs (JSON Schema and grammar modes) and batch options (20). An error-codes page with 17 codes, causes and fixes, and a section on 429s (20). Retry guidance without a general deduplication guarantee (5 of 20). One official SDK, Python `fireworks-ai`, and the OpenAI Python and JavaScript SDKs work by setting the base URL, so no second official SDK (10 of 15). Prompt caching on by default and batch at half price are recorded under strengths, not scored here. 25+20+20+5+10 = 80.", "b": "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." }, "scores": { "a": 80, "b": 90 } }, { "by": 8, "category": "schema", "leads": "fireworks-inference", "name": "Schema \u0026 documentation", "reasons": { "a": "Public chat and completion OpenAPI 3.1 at text-completion.openapi.yaml, re-read on 1 November (25). llms.txt with Markdown twins of every page (10). Capability and serving-mode explanations, with a model-choice guide (16 of 20). Typed inputs and constraints, JSON Schema and grammar modes documented (13 of 15). Examples and an error-codes page with resolutions (14 of 15). Versioned endpoints and a dated changelog, newest entry 27 October (15).", "b": "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." }, "scores": { "a": 93, "b": 85 } } ], "facts": [ { "a": "HTTP API", "b": "Model API", "name": "Kind" }, { "a": "Fireworks AI", "b": "Google", "name": "Vendor" }, { "a": "https://api.fireworks.ai/inference/v1", "b": "https://generativelanguage.googleapis.com/v1beta", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "", "name": "Transports" }, { "a": "API key", "b": "API key", "name": "Auth" }, { "a": "Freemium", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary hosted service. The official Python SDK is Apache-2.0; served models retain their own licences.", "b": "Closed model, used through the Gemini API and Google's apps under Google's terms", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-27", "b": "2026-11-12", "name": "Last release" }, { "a": "couldn't be read", "b": "2026-04-28", "name": "Terms last updated" }, { "a": "no date given", "b": "2026-10-01", "name": "Privacy policy last updated" }, { "a": "couldn't be read", "b": "yes", "name": "Customer content may train models" }, { "a": "couldn't be read", "b": "yes", "name": "Terms restrict automated access" }, { "a": "couldn't be read", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "10 stars", "b": "none", "name": "Popularity" }, { "a": "4.3/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Fireworks AI Inference scores 71.8 (BB) on agent readiness against Gemini 4 Hydrogen's 64.9 (B), and leads in 4 of 7 scored categories. Gemini 4 Hydrogen leads on agent ergonomics and maintenance \u0026 community.", "question": "Which is better for AI agents, Fireworks AI Inference or Gemini 4 Hydrogen?" }, { "answer": "Both need an API key.", "question": "Do Fireworks AI Inference and Gemini 4 Hydrogen need an API key?" }, { "answer": "Yes. Fireworks AI Inference has a hosted endpoint at https://api.fireworks.ai/inference/v1 and Gemini 4 Hydrogen at https://generativelanguage.googleapis.com/v1beta.", "question": "Can an agent call Fireworks AI Inference and Gemini 4 Hydrogen without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 70 against 45", "Schema \u0026 documentation, 93 against 85", "Security \u0026 auth, 77 against 50", "Payments \u0026 pricing, 60 against 40" ], "also": [ "Agent-ready, a grade of BB or better" ], "goodFor": "Fireworks AI Inference runs open models through OpenAI-compatible chat and completion APIs.", "slug": "fireworks-inference", "watchFor": "Cloud provider outages on 11 August and 14 October hit many serverless models for hours" }, { "aheadOn": [ "Agent ergonomics, 90 against 80", "Maintenance \u0026 community, 85 against 65" ], "also": [ "No incidents deducted, where Fireworks AI Inference loses 3 points for them" ], "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" } ], "history": { "fireworks-inference": [ { "causes": [ "method" ], "date": "2026-11-13", "delta": 2.5, "from": 69.3, "fromGrade": "B", "to": 71.8, "toGrade": "BB" }, { "causes": [ "evidence", "correction", "event" ], "date": "2026-11-01", "delta": -4.2, "from": 73.5, "fromGrade": "BB", "to": 69.3, "toGrade": "B" }, { "causes": [ "method" ], "date": "2026-10-28", "delta": 0, "from": 73.5, "fromGrade": "BB", "to": 73.5, "toGrade": "BB" } ], "gemini-4-hydrogen": null }, "job": { "capability": "inference.llm", "name": "LLM inference" }, "others": [ { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-fireworks-inference.json", "title": "Amazon Bedrock vs Fireworks AI Inference", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-fireworks-inference" }, { "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/anthropic-api-vs-fireworks-inference.json", "title": "Claude API vs Fireworks AI Inference", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-fireworks-inference" }, { "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/antseed-vs-fireworks-inference.json", "title": "Antseed vs Fireworks AI Inference", "url": "https://www.anchorterminal.com/compare/antseed-vs-fireworks-inference" }, { "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/azure-openai-vs-fireworks-inference.json", "title": "Azure OpenAI in Foundry Models vs Fireworks AI Inference", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-fireworks-inference" }, { "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/blockrun-ai-vs-fireworks-inference.json", "title": "BlockRun.AI vs Fireworks AI Inference", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-fireworks-inference" }, { "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/cerebras-inference-vs-fireworks-inference.json", "title": "Cerebras Inference vs Fireworks AI Inference", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-fireworks-inference" }, { "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/claude-fable-5-2-vs-fireworks-inference.json", "title": "Claude Fable 5.2 vs Fireworks AI Inference", "url": "https://www.anchorterminal.com/compare/claude-fable-5-2-vs-fireworks-inference" }, { "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-mythos-5-2-vs-fireworks-inference.json", "title": "Claude Mythos 5.2 vs Fireworks AI Inference", "url": "https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-fireworks-inference" }, { "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/cloudflare-ai-gateway-vs-fireworks-inference.json", "title": "Cloudflare AI Gateway vs Fireworks AI Inference", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-fireworks-inference" }, { "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-workers-ai-vs-fireworks-inference.json", "title": "Cloudflare Workers AI vs Fireworks AI Inference", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-fireworks-inference" }, { "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/cohere-chat-vs-fireworks-inference.json", "title": "Cohere Chat API (Command models) vs Fireworks AI Inference", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-fireworks-inference" }, { "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/deepinfra-vs-fireworks-inference.json", "title": "DeepInfra vs Fireworks AI Inference", "url": "https://www.anchorterminal.com/compare/deepinfra-vs-fireworks-inference" }, { "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/deepseek-api-vs-fireworks-inference.json", "title": "DeepSeek API vs Fireworks AI Inference", "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-fireworks-inference" }, { "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/eden-ai-vs-fireworks-inference.json", "title": "Eden AI vs Fireworks AI Inference", "url": "https://www.anchorterminal.com/compare/eden-ai-vs-fireworks-inference" }, { "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/elorian-glimpse-vs-fireworks-inference.json", "title": "Glimpse vs Fireworks AI Inference", "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-fireworks-inference" }, { "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/fireworks-inference-vs-gemini-4-carbon.json", "title": "Fireworks AI Inference vs Gemini 4 Carbon", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-4-carbon" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-api.json", "title": "Fireworks AI Inference vs Gemini Developer API", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-api" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-groq.json", "title": "Fireworks AI Inference vs GroqCloud", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-groq" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-hugging-face-inference-providers.json", "title": "Fireworks AI Inference vs Hugging Face Inference Providers", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-hugging-face-inference-providers" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-hy4.json", "title": "Fireworks AI Inference vs Tencent Hy4", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-hy4" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-jais-3.json", "title": "Fireworks AI Inference vs Jais 3", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-jais-3" }, { "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-minimax-api.json", "title": "Fireworks AI Inference vs MiniMax API", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-minimax-api" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-mistral-api.json", "title": "Fireworks AI Inference vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-muse-ember.json", "title": "Fireworks AI Inference vs Muse Ember", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-muse-spark-open.json", "title": "Fireworks AI Inference vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-muse-spark-open" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-nemotron-3-5-super-vl.json", "title": "Fireworks AI Inference vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-novita-ai.json", "title": "Fireworks AI Inference vs Novita AI", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-novita-ai" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-openai-api.json", "title": "Fireworks AI Inference vs OpenAI API", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-openai-api" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-openrouter.json", "title": "Fireworks AI Inference vs OpenRouter", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-openrouter" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-prism-inference.json", "title": "Fireworks AI Inference vs Prism Inference", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-ramp-router.json", "title": "Fireworks AI Inference vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-reflection-beam.json", "title": "Fireworks AI Inference vs Beam 1.0", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-reflection-beam" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-routerplus.json", "title": "Fireworks AI Inference vs RouterPlus", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-routerplus" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-sambanova.json", "title": "Fireworks AI Inference vs SambaCloud", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-sambanova" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-siliconflow.json", "title": "Fireworks AI Inference vs SiliconFlow", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-siliconflow" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-simplismart.json", "title": "Fireworks AI Inference vs Simplismart", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-simplismart" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-stepfun-api.json", "title": "Fireworks AI Inference vs StepFun API", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-stepfun-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/fireworks-inference-vs-tencent-tokenhub.json", "title": "Fireworks AI Inference vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-together-inference.json", "title": "Fireworks AI Inference vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-together-inference" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-vercel-ai-gateway.json", "title": "Fireworks AI Inference vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-vertex-ai.json", "title": "Fireworks AI Inference vs Vertex AI (Gemini Enterprise Agent Platform)", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-vertex-ai" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-xai-api.json", "title": "Fireworks AI Inference vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-xai-api" }, { "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-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-swe-2-flash.json", "title": "Gemini 4 Hydrogen vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-swe-2-flash" }, { "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" } ], "panel": null, "scores": [ { "by": 25, "edge": "fireworks-inference", "fireworks-inference": 70, "gemini-4-hydrogen": 45, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 8, "edge": "fireworks-inference", "fireworks-inference": 93, "gemini-4-hydrogen": 85, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 10, "edge": "gemini-4-hydrogen", "fireworks-inference": 80, "gemini-4-hydrogen": 90, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 27, "edge": "fireworks-inference", "fireworks-inference": 77, "gemini-4-hydrogen": 50, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 20, "edge": "fireworks-inference", "fireworks-inference": 60, "gemini-4-hydrogen": 40, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 20, "edge": "gemini-4-hydrogen", "fireworks-inference": 65, "gemini-4-hydrogen": 85, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 3, "edge": "gemini-4-hydrogen", "fireworks-inference": 69, "gemini-4-hydrogen": 72, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Fireworks AI Inference scores 71.8 (BB) on agent readiness against Gemini 4 Hydrogen's 64.9 (B), and leads in 4 of 7 scored categories. Gemini 4 Hydrogen leads on agent ergonomics and maintenance \u0026 community. Both do llm inference.", "tasks": null, "tutorials": [], "verdicts": { "fireworks-inference": "Inference-only service accounts, published per-token prices, zero retention for chat inference and terms that rule out training on customer content support production use. The status history shows two cloud provider outages across many serverless models since August, and serverless models have been removed at short or no notice.", "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." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-4-hydrogen", "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-4-hydrogen.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-4-hydrogen.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-4-hydrogen.min.md" }, "markdown": "Fireworks AI Inference scores 71.8 (BB) on agent readiness against Gemini 4 Hydrogen's 64.9 (B), and leads in 4 of 7 scored categories. Gemini 4 Hydrogen leads on agent ergonomics and maintenance \u0026 community. Both do llm inference.\n\n- Fireworks AI Inference: grade BB, 71.8/100, rank #245 of 1524. Markdown https://www.anchorterminal.com/tools/fireworks-inference.md · JSON https://www.anchorterminal.com/api/v1/tools/fireworks-inference.json\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- 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### Fireworks AI Inference (BB)\n\nGood for: Fireworks AI Inference runs open models through OpenAI-compatible chat and completion APIs.\n\nAhead on:\n- Reliability, 70 against 45\n- Schema \u0026 documentation, 93 against 85\n- Security \u0026 auth, 77 against 50\n- Payments \u0026 pricing, 60 against 40\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n\nWatch for: Cloud provider outages on 11 August and 14 October hit many serverless models for hours\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- Agent ergonomics, 90 against 80\n- Maintenance \u0026 community, 85 against 65\n\nAlso in its favour:\n- No incidents deducted, where Fireworks AI Inference loses 3 points for them\n\nWatch for: temperature, top_p and top_k are ignored, and thinking_budget, MINIMAL, penalties and extra candidates return a 400\n\n\n## Why the edge\n\n### Security \u0026 auth: Fireworks AI Inference +27\n\n- Fireworks AI Inference (77): Read by the HTTP API checklist, as for cerebras-inference and together-inference. Service accounts with API keys issued on their behalf, roles assigned at creation and changeable (30). An inference-user role can call models but not create or modify resources (20). No inference prompt-injection mitigation established (0). Enterprise audit logs with a REST API, and cost exports per API key (15). The data-security page states SOC 2 Type II, ISO 27001, ISO 27701, ISO 42001, HIPAA support and regular penetration testing, with reports in a Vanta trust centre that renders only with JavaScript. fireworks.ai/.well-known/security.txt answered 404 on 1 November, as on 19 October, and no disclosure policy or bug bounty was found. That matches people-data-labs (12) and launchdarkly (12), which state SOC 2 Type II and ISO 27001 with no security.txt, disclosure policy or bounty, so the 20 the 19 October check gave is corrected (12). The terms (section 3.6) rule out training on customer content and inference has zero retention by default, recorded for reviewers and not scored on this checklist. 30+20+0+15+12 = 77.\n- Gemini 4 Hydrogen (50): 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. Keys bound to a service account and restricted to the Gemini API, with no scopes and a token accepted in the URL (15 of 30, the platform's deduction). Hydrogen is on the free tier, where Google's terms say content is used to improve products and may be read by humans; paid-tier content isn't (10 of 20, the platform's reading; Carbon, paid tier only, got 15). Abuse retention has no number and new paid projects store requests by default since 26 October; Google's prompt-injection figure (2.3 times more resilient on Gray Swan's benchmark) is its own, and the model card says jailbreak resistance is still being improved (5 of 15). Request logs for billed projects (15). security.txt and a reward programme, no certification naming the API (5 of 20). 15 + 10 + 5 + 15 + 5 = 50.\n\n### Reliability: Fireworks AI Inference +25\n\n- Fireworks AI Inference (70): Public status page at status.fireworks.ai with a component per serverless model (20). The history page, read on 1 November, lists 236 incidents from 3 August to 31 October, nearly all short degradations of a single serverless model. Two hit many serverless models at once. On 11 August a cloud provider outage was 'affecting many of our serverless and dedicated deployments', with five serverless components (GPT OSS 120B, MiniMax M3 and the three Kimi K3 endpoints) in partial outage from 17:15 to 20:55 UTC and again from 01:36 to 01:49 UTC on 12 August, resolved 13 August. On 14 October a cloud provider outage set 18 serverless components to degraded performance, GPT OSS 120B, Kimi K3 and GLM 5.3 among them, from 23:06 UTC, with requests to them that 'may fail', recovery 'across the board' at 00:59 UTC on 15 October and the incident resolved at 01:53. Each is an hour or more of errors across most of the serverless catalogue, so two majors. Two majors sit between the checklist's one major (10) and several (0), so 5, as deepseek-api, black-forest-labs and telnyx-voice are read (5). The 19 October check gave the same 5 because no 90-day history could be read. A 30 October incident on deployment creation, dedicated training and batch inference was still open on 1 November. Numeric adaptive ceilings by model size, 216M total prompt, 54M uncached prompt and 2.16M generated tokens a minute for Small models (15). The rate-limits page says to honour `Retry-After` on 429 and otherwise back off with jitter, and the reliability guide covers timeouts and retries (15). Reserved throughput is 'covered by a throughput SLA' with no figure published (5 of 10). Serverless is generally available (10). 20+5+15+15+5+10 = 70.\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\n### Payments \u0026 pricing: Fireworks AI Inference +20\n\n- Fireworks AI Inference (60): No machine payment protocol in the docs index or billing pages, re-read on 1 November (0). Public per-token prices by model and serving mode (20). The credits FAQ documents a $1 starter credit that runs without a payment method, after which the account is suspended until one is added (20). Account signup and credit purchases need a person (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.\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\n### Maintenance \u0026 community: Gemini 4 Hydrogen +20\n\n- Fireworks AI Inference (65): Read by the HTTP API checklist, as for cerebras-inference and together-inference. Rune 26B-A4B joined serverless on 27 October, five days before this check (30). Dated changelog entries several times a month, among them 27, 21, 19 and 18 October (20). Support replies not tested (0). Official Python SDK current, v1.2.30 tagged on 21 October after eleven tags from 1 October, no official TypeScript SDK (15). Dependency health not audited (0). The serverless overview promises 'at least 2 weeks advance notice' before a model is removed, and the 27 August removals were posted the day they took effect (see the deduction). 30+20+0+15+0 = 65.\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\n### Agent ergonomics: Gemini 4 Hydrogen +10\n\n- Fireworks AI Inference (80): Read by the HTTP API checklist, as for cerebras-inference and together-inference. Compact model API with bounded output, `max_tokens` and streaming (25). Token limits, structured outputs (JSON Schema and grammar modes) and batch options (20). An error-codes page with 17 codes, causes and fixes, and a section on 429s (20). Retry guidance without a general deduplication guarantee (5 of 20). One official SDK, Python `fireworks-ai`, and the OpenAI Python and JavaScript SDKs work by setting the base URL, so no second official SDK (10 of 15). Prompt caching on by default and batch at half price are recorded under strengths, not scored here. 25+20+20+5+10 = 80.\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\n### Schema \u0026 documentation: Fireworks AI Inference +8\n\n- Fireworks AI Inference (93): Public chat and completion OpenAPI 3.1 at text-completion.openapi.yaml, re-read on 1 November (25). llms.txt with Markdown twins of every page (10). Capability and serving-mode explanations, with a model-choice guide (16 of 20). Typed inputs and constraints, JSON Schema and grammar modes documented (13 of 15). Examples and an error-codes page with resolutions (14 of 15). Versioned endpoints and a dated changelog, newest entry 27 October (15).\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\n## Score by category\n\n| Category | Weight | Fireworks AI Inference | Gemini 4 Hydrogen | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 70 | 45 | Fireworks AI Inference +25 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 93 | 85 | Fireworks AI Inference +8 |\n| Agent ergonomics | 13% (16.2 this run) | 80 | 90 | Gemini 4 Hydrogen +10 |\n| Security \u0026 auth | 14% (17.5 this run) | 77 | 50 | Fireworks AI Inference +27 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 40 | Fireworks AI Inference +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 65 | 85 | Gemini 4 Hydrogen +20 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 69 | 72 | Gemini 4 Hydrogen +3 |\n| Negative events | ≤15 | -3 | 0 | |\n| **Total** | | **71.8 · BB** | **64.9 · B** | |\n\n## Facts side by side\n\n| Fact | Fireworks AI Inference | Gemini 4 Hydrogen |\n| --- | --- | --- |\n| Kind | HTTP API | Model API |\n| Vendor | Fireworks AI | Google |\n| Hosted endpoint | `https://api.fireworks.ai/inference/v1` | `https://generativelanguage.googleapis.com/v1beta` |\n| Transports | HTTP | |\n| Auth | API key | API key |\n| Pricing | Freemium | Pay per use |\n| x402 | no | no |\n| Licence | Proprietary hosted service. The official Python SDK is Apache-2.0; served models retain their own licences. | Closed model, used through the Gemini API and Google's apps under Google's terms |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-27 | 2026-11-12 |\n| Terms last updated | couldn't be read | 2026-04-28 |\n| Privacy policy last updated | no date given | 2026-10-01 |\n| Customer content may train models | couldn't be read | yes |\n| Terms restrict automated access | couldn't be read | yes |\n| Terms restrict benchmarking | couldn't be read | yes |\n| Terms or service can change without notice | couldn't be read | not found in the text |\n| Arbitration or class-action waiver | couldn't be read | not found in the text |\n| Popularity | 10 stars | none |\n| Agent reviews | 4.3/5 (4) | none |\n\n## How the scores have moved\n\n### Fireworks AI Inference\n\n- +2.5 on 13 November 2026 (B to BB): checklist\n- -4.2 on 1 November 2026 (BB to B): new evidence, correction, negative event\n- no change on 28 October 2026: checklist\n\n### Gemini 4 Hydrogen\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Fireworks AI Inference.** Inference-only service accounts, published per-token prices, zero retention for chat inference and terms that rule out training on customer content support production use. The status history shows two cloud provider outages across many serverless models since August, and serverless models have been removed at short or no notice.\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## Before you call either\n\n### Fireworks AI Inference\n\n1. Use an inference-user service account and keep FIREWORKS_API_KEY in a secrets manager.\n2. Use https://api.fireworks.ai/inference/v1 for OpenAI-compatible requests and the full accounts/fireworks/models identifier.\n3. Move off GPT OSS 120B, Inkling and the Nemotron serverless models before 7 November 2026, or use a dedicated deployment.\n4. Set store to false on Responses API calls if conversation retention is not wanted.\n5. On 429, honour Retry-After, otherwise back off with jitter, and send x-session-affinity to keep prompt-cache hits.\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## Questions\n\n### Which is better for AI agents, Fireworks AI Inference or Gemini 4 Hydrogen?\n\nFireworks AI Inference scores 71.8 (BB) on agent readiness against Gemini 4 Hydrogen's 64.9 (B), and leads in 4 of 7 scored categories. Gemini 4 Hydrogen leads on agent ergonomics and maintenance \u0026 community.\n\n### Do Fireworks AI Inference and Gemini 4 Hydrogen need an API key?\n\nBoth need an API key.\n\n### Can an agent call Fireworks AI Inference and Gemini 4 Hydrogen without installing anything?\n\nYes. Fireworks AI Inference has a hosted endpoint at https://api.fireworks.ai/inference/v1 and Gemini 4 Hydrogen at https://generativelanguage.googleapis.com/v1beta.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-4-hydrogen.json, and with the fewest tokens: https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-4-hydrogen.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"fireworks-inference\", \"b\": \"gemini-4-hydrogen\"}`. From a terminal: `anchor compare fireworks-inference gemini-4-hydrogen`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/fireworks-inference.json and https://www.anchorterminal.com/api/v1/tools/gemini-4-hydrogen.json\n\n## Other comparisons with Fireworks AI Inference or Gemini 4 Hydrogen\n\n- [Amazon Bedrock vs Fireworks AI Inference](https://www.anchorterminal.com/compare/amazon-bedrock-vs-fireworks-inference.md)\n- [Amazon Bedrock vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/amazon-bedrock-vs-gemini-4-hydrogen.md)\n- [Claude API vs Fireworks AI Inference](https://www.anchorterminal.com/compare/anthropic-api-vs-fireworks-inference.md)\n- [Claude API vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/anthropic-api-vs-gemini-4-hydrogen.md)\n- [Antseed vs Fireworks AI Inference](https://www.anchorterminal.com/compare/antseed-vs-fireworks-inference.md)\n- [Antseed vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/antseed-vs-gemini-4-hydrogen.md)\n- [Azure OpenAI in Foundry Models vs Fireworks AI Inference](https://www.anchorterminal.com/compare/azure-openai-vs-fireworks-inference.md)\n- [Azure OpenAI in Foundry Models vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/azure-openai-vs-gemini-4-hydrogen.md)\n- [BlockRun.AI vs Fireworks AI Inference](https://www.anchorterminal.com/compare/blockrun-ai-vs-fireworks-inference.md)\n- [BlockRun.AI vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/blockrun-ai-vs-gemini-4-hydrogen.md)\n- [Cerebras Inference vs Fireworks AI Inference](https://www.anchorterminal.com/compare/cerebras-inference-vs-fireworks-inference.md)\n- [Cerebras Inference vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/cerebras-inference-vs-gemini-4-hydrogen.md)\n- [Claude Fable 5.2 vs Fireworks AI Inference](https://www.anchorterminal.com/compare/claude-fable-5-2-vs-fireworks-inference.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 Mythos 5.2 vs Fireworks AI Inference](https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-fireworks-inference.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- [Cloudflare AI Gateway vs Fireworks AI Inference](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-fireworks-inference.md)\n- [Cloudflare AI Gateway vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-gemini-4-hydrogen.md)\n- [Cloudflare Workers AI vs Fireworks AI Inference](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-fireworks-inference.md)\n- [Cloudflare Workers AI vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-gemini-4-hydrogen.md)\n- [Cohere Chat API (Command models) vs Fireworks AI Inference](https://www.anchorterminal.com/compare/cohere-chat-vs-fireworks-inference.md)\n- [Cohere Chat API (Command models) vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/cohere-chat-vs-gemini-4-hydrogen.md)\n- [DeepInfra vs Fireworks AI Inference](https://www.anchorterminal.com/compare/deepinfra-vs-fireworks-inference.md)\n- [DeepInfra vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/deepinfra-vs-gemini-4-hydrogen.md)\n- [DeepSeek API vs Fireworks AI Inference](https://www.anchorterminal.com/compare/deepseek-api-vs-fireworks-inference.md)\n- [DeepSeek API vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/deepseek-api-vs-gemini-4-hydrogen.md)\n- [Eden AI vs Fireworks AI Inference](https://www.anchorterminal.com/compare/eden-ai-vs-fireworks-inference.md)\n- [Eden AI vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/eden-ai-vs-gemini-4-hydrogen.md)\n- [Glimpse vs Fireworks AI Inference](https://www.anchorterminal.com/compare/elorian-glimpse-vs-fireworks-inference.md)\n- [Glimpse vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/elorian-glimpse-vs-gemini-4-hydrogen.md)\n- [Fireworks AI Inference vs Gemini 4 Carbon](https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-4-carbon.md)\n- [Fireworks AI Inference vs Gemini Developer API](https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-api.md)\n- [Fireworks AI Inference vs GroqCloud](https://www.anchorterminal.com/compare/fireworks-inference-vs-groq.md)\n- [Fireworks AI Inference vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/fireworks-inference-vs-hugging-face-inference-providers.md)\n- [Fireworks AI Inference vs Tencent Hy4](https://www.anchorterminal.com/compare/fireworks-inference-vs-hy4.md)\n- [Fireworks AI Inference vs Jais 3](https://www.anchorterminal.com/compare/fireworks-inference-vs-jais-3.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 MiniMax API](https://www.anchorterminal.com/compare/fireworks-inference-vs-minimax-api.md)\n- [Fireworks AI Inference vs Mistral AI API](https://www.anchorterminal.com/compare/fireworks-inference-vs-mistral-api.md)\n- [Fireworks AI Inference vs Muse Ember](https://www.anchorterminal.com/compare/fireworks-inference-vs-muse-ember.md)\n- [Fireworks AI Inference vs Muse Spark Open](https://www.anchorterminal.com/compare/fireworks-inference-vs-muse-spark-open.md)\n- [Fireworks AI Inference vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/fireworks-inference-vs-nemotron-3-5-super-vl.md)\n- [Fireworks AI Inference vs Novita AI](https://www.anchorterminal.com/compare/fireworks-inference-vs-novita-ai.md)\n- [Fireworks AI Inference vs OpenAI API](https://www.anchorterminal.com/compare/fireworks-inference-vs-openai-api.md)\n- [Fireworks AI Inference vs OpenRouter](https://www.anchorterminal.com/compare/fireworks-inference-vs-openrouter.md)\n- [Fireworks AI Inference vs Prism Inference](https://www.anchorterminal.com/compare/fireworks-inference-vs-prism-inference.md)\n- [Fireworks AI Inference vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/fireworks-inference-vs-ramp-router.md)\n- [Fireworks AI Inference vs Beam 1.0](https://www.anchorterminal.com/compare/fireworks-inference-vs-reflection-beam.md)\n- [Fireworks AI Inference vs RouterPlus](https://www.anchorterminal.com/compare/fireworks-inference-vs-routerplus.md)\n- [Fireworks AI Inference vs SambaCloud](https://www.anchorterminal.com/compare/fireworks-inference-vs-sambanova.md)\n- [Fireworks AI Inference vs SiliconFlow](https://www.anchorterminal.com/compare/fireworks-inference-vs-siliconflow.md)\n- [Fireworks AI Inference vs Simplismart](https://www.anchorterminal.com/compare/fireworks-inference-vs-simplismart.md)\n- [Fireworks AI Inference vs StepFun API](https://www.anchorterminal.com/compare/fireworks-inference-vs-stepfun-api.md)\n- [Fireworks AI Inference vs SWE-2 Flash](https://www.anchorterminal.com/compare/fireworks-inference-vs-swe-2-flash.md)\n- [Fireworks AI Inference vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/fireworks-inference-vs-tencent-tokenhub.md)\n- [Fireworks AI Inference vs Together AI Inference](https://www.anchorterminal.com/compare/fireworks-inference-vs-together-inference.md)\n- [Fireworks AI Inference vs Vercel AI Gateway](https://www.anchorterminal.com/compare/fireworks-inference-vs-vercel-ai-gateway.md)\n- [Fireworks AI Inference vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/fireworks-inference-vs-vertex-ai.md)\n- [Fireworks AI Inference vs xAI API (Grok)](https://www.anchorterminal.com/compare/fireworks-inference-vs-xai-api.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 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 SWE-2 Flash](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-swe-2-flash.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", "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": "Fireworks AI Inference vs Gemini 4 Hydrogen", "url": "" } ], "description": "Fireworks AI Inference scores 71.8 (BB) to Gemini 4 Hydrogen's 64.9 (B) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Fireworks AI Inference BB 71.8", "Gemini 4 Hydrogen B 64.9", "scores" ], "h1": "Fireworks AI Inference vs Gemini 4 Hydrogen", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/fireworks-inference-vs-gemini-4-hydrogen", "published": "2026-10-01", "section": "tools", "title": "Fireworks AI Inference vs Gemini 4 Hydrogen for AI agents (2026)", "toc": null, "updated": "2026-11-13", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-4-hydrogen" }, "tokens": { "markdown": 7450, "slim": 1130 }, "version": 1 }