{ "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": 69.3, "grade": "B", "agentReady": false, "rank": 252, "ranked": true, "rankOf": 1520, "categoryRank": 11, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 80, "maintenance": 65, "payments": 40, "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": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 69.3 } ], "editorialScores": { "ergonomics": 80, "maintenance": 65, "payments": 40, "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": "2026-11-01", "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": "2026-11-11T23:53:47.599294009Z", "lastOk": true, "lastStatus": 404, "lastMs": 8, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 9, "p95ms24h": 83, "samples24h": 245, "samples30d": 5816, "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 } ], "since": "2026-10-19T00:00:00Z" }, "vendorStatus": { "page": "https://status.fireworks.ai", "indicator": "minor", "summary": "Partial System Degradation", "checkedAt": "2026-11-11T23:51:38.694600027Z" }, "versions": [ { "registry": "github", "name": "fw-ai-external/python-sdk", "version": "v1.2.33", "released": "2026-11-08", "seenAt": "2026-11-11T05:57:29.50450028Z" }, { "registry": "pypi", "name": "fireworks-ai", "version": "1.2.33", "released": "2026-11-08", "seenAt": "2026-11-11T05:57:29.387985719Z" } ], "githubStars": 11, "pypiWeekly": 414848, "securityTxt": { "url": "https://fireworks.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-11T16:11:31.528144883Z" }, "llmsTxt": { "url": "https://docs.fireworks.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-11T15:46:52.885705436Z" }, "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": "2026-11-11T23:53:47.599294009Z" }, "streak": { "days": 24, "from": "2026-10-19", "sinceWatching": true, "best": 24 } }, "answer": "Fireworks AI Inference scores 69.3 (B) on agent readiness against Gemini 4 Carbon's 62.6 (B), and leads in 4 of 7 scored categories. Gemini 4 Carbon leads on agent ergonomics and maintenance \u0026 community.", "b": { "slug": "gemini-4-carbon", "name": "Gemini 4 Carbon", "vendor": "Google", "vendorUrl": "https://ai.google.dev", "kind": "model", "category": "inference", "summary": "Gemini 4 Carbon is Google's strongest Gemini model, for long agentic coding, cybersecurity and research work, on the paid 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-carbon", "markdownUrl": "https://www.anchorterminal.com/tools/gemini-4-carbon.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/gemini-4-carbon.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/gemini-4-carbon.json", "dns": "gemini-4-carbon.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 on a project with billing, since Carbon is on the paid tier only, per the Gemini API listing and Google's developer post. Google AI Ultra subscribers can also use it in AI Studio and Antigravity. The `gemini-4-carbon-cyber-permissive` variant needs a project approved through Google's Fairwind Program.", "pricing": "usage", "pricingNotes": "Google's announcement gives an introductory $2 per million input tokens and $10 output, cached input 95% off, then $4 and $20, with no end date for the introduction. Paid tier only, no free tier. Every processed token is billed, thinking included (checked 2026-11-10).", "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 2026-11-10).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-10" }, "docsUrl": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/guides/gemini-4-carbon", "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", "card-required", "closed-source", "llms-txt", "new" ], "lastRelease": "2026-11-10", "graded": true, "anchor": { "graded": true, "score": 62.6, "grade": "B", "agentReady": false, "rank": 555, "ranked": true, "rankOf": 1520, "categoryRank": 22, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 93, "maintenance": 83, "payments": 20, "reliability": 40, "schema": 85, "security": 55, "transparency": 72 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-10" }, "negative": 0, "verdict": "Google's strongest model on the same Gemini API as Argon, with a 1M-token budget, function calling and structured output, at an introductory $2 and $10 per million tokens. Paid tier only, sampling parameters are ignored or refused, its launch stage isn't stated, and the price rises to $4 and $20 at a date Google hasn't given.", "bestFor": "Agents on the hardest long tasks (multi-step debugging, large codebases, open-ended research, security work) that can pay frontier prices and already use the Gemini API.", "strengths": [ "Introductory price of $2 input and $10 output per million tokens, with cached input 95% off", "1,048,576 tokens shared between input and output, with long decodes for big outputs", "Function calling, structured output, Google Search grounding and background execution", "Thinking levels LOW, MEDIUM (default) and HIGH, and implicit caching on by default", "The same API, keys and SDKs as Gemini 4 Argon, so switching is a model ID" ], "weaknesses": [ "Paid tier only, with no free tier to try it on", "temperature, top_p and top_k are ignored, and thinking_budget, MINIMAL, penalties and extra candidates return a 400", "No explicit context caching, and prefilled model turns aren't accepted", "The price goes to $4 and $20 after an introduction with no end date given", "Benchmark figures are Google's own, and the launch stage isn't stated" ], "agentNotes": [ "Call generateContent at https://generativelanguage.googleapis.com/v1beta with model gemini-4-carbon and an x-goog-api-key on a billed project", "Set thinking_level (LOW, MEDIUM or HIGH) instead of thinking_budget, and don't send temperature, top_p or top_k", "Count output against the same 1,048,576-token limit as the input, and set max_output_tokens for long answers", "Put static prompt content first so implicit caching applies; explicit caches aren't supported", "Use gemini-4-argon for most coding and knowledge work, and Carbon for the hardest long tasks, as Google suggests" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 62.6 } ], "editorialScores": { "ergonomics": 93, "maintenance": 83, "payments": 20, "reliability": 40, "schema": 85, "security": 55, "transparency": 55 }, "provenanceScore": 89, "checked": { "categories": { "ergonomics": "2026-11-10", "maintenance": "2026-11-10", "payments": "2026-11-10", "reliability": "2026-11-10", "schema": "2026-11-10", "security": "2026-11-10", "transparency": "2026-11-10" }, "last": "2026-11-10", "oldest": "2026-11-10", "stale": false, "staleAfterDays": 90 } }, "connect": { "http": "curl \"https://generativelanguage.googleapis.com/v1beta/models/gemini-4-carbon: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-carbon" }, "sameCompany": [ "vertex-ai", "embeddinggemma-2", "embeddinggemma-300m", "gemini-embedding", "vertex-ai-tuning", "cloud-run-gpus", "google-model-armor", "shieldgemma", "google-imagen", "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", "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 Carbon input", "unit": "1m-tokens", "usd": 2, "note": "Introductory; $4 after, date not given" }, { "item": "Gemini 4 Carbon cached input", "unit": "1m-tokens", "usd": 0.1, "note": "95% off input" }, { "item": "Gemini 4 Carbon output", "unit": "1m-tokens", "usd": 10, "note": "Introductory; $20 after" } ], "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": "2026-11-10", "score": 89 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/gemini-4-carbon.json", "live": { "slug": "gemini-4-carbon", "probe": { "target": "https://generativelanguage.googleapis.com/v1beta", "method": "get", "lastAt": "2026-11-11T23:53:48.979836747Z", "lastOk": true, "lastStatus": 404, "lastMs": 179, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 38, "p95ms24h": 108, "samples24h": 245, "samples30d": 309, "days": [ { "date": "2026-11-10", "probes": 65, "ok": 65 }, { "date": "2026-11-11", "probes": 244, "ok": 244 } ], "since": "2026-11-10T17:42:25.910455739Z" }, "vendorStatus": { "page": "https://aistudio.google.com/status", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-11T18:03:50.810380783Z" }, "securityTxt": { "url": "https://google.com/.well-known/security.txt", "state": "valid", "expires": "2030-04-01T00:00:00z", "checkedAt": "2026-11-11T16:10:51.936418595Z" }, "llmsTxt": { "url": "https://ai.google.dev/gemini-api/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-11T15:46:54.612299471Z" }, "pages": [ { "url": "https://ai.google.dev/gemini-api/docs/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-11-11T16:50:14.1697556Z", "changedAt": "2026-11-11T16:50:14.1697556Z", "fingerprint": "8b141b7245be" }, { "url": "https://ai.google.dev/gemini-api/terms", "kind": "terms", "status": 200, "checkedAt": "2026-11-11T16:50:30.702791329Z", "changedAt": "2026-11-03T07:41:20.562939041Z", "fingerprint": "07b98470ed02" } ], "updatedAt": "2026-11-11T23:53:48.979836747Z" }, "streak": { "days": 2, "from": "2026-11-10", "sinceWatching": true, "best": 2 } }, "edges": [ { "by": 30, "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-carbon 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). Carbon's launch stage isn't stated in Google's developer post, the Antigravity post or the Cloud developer guide read on 10 November, and the model ID carries no preview label, so half (5 of 10, a judgement call; Argon's GA earned the platform 10). 10 + 5 + 5 + 15 + 0 + 5 = 40." }, "scores": { "a": 70, "b": 40 } }, { "by": 22, "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-carbon 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). Carbon is on the paid tier only, and Google's terms say paid-tier content isn't used to improve products; AI Studio use under a Google AI Ultra subscription falls under terms we didn't read, so 15 of 20 (a judgement call; the platform's 10 is for its free tier). Abuse retention with no number, and new paid projects store requests by default since 26 October (5 of 15). Request logs for billed projects (15). security.txt and a reward programme, no certification naming the API (5 of 20). 15 + 15 + 5 + 15 + 5 = 55." }, "scores": { "a": 77, "b": 55 } }, { "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).", "b": "Model reading for gemini-4-carbon 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). Introductory prices published in Google's 28 October announcement without a login, $2 and $10, then $4 and $20; the Gemini API pricing page as read on 10 November showed no Carbon row, so the figures rest on the announcement (20). No free tier: Google's developer post puts Carbon on the paid tier (0). A Google account and AI Studio for a key (0). 0 + 20 + 0 + 0 = 20." }, "scores": { "a": 40, "b": 20 } }, { "by": 18, "category": "maintenance", "leads": "gemini-4-carbon", "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-carbon 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 to developers on 10 November 2026, with the platform's changelog (30). Deprecations with earliest dates and no stated minimum notice (4 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 (15). Runtimes stated (10). 30 + 4 + 4 + 15 + 5 + 15 + 10 = 83." }, "scores": { "a": 65, "b": 83 } }, { "by": 13, "category": "ergonomics", "leads": "gemini-4-carbon", "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-carbon 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 (13 of 15). Implicit caching with durable caching on by default, cached input 95% off, explicit caches not supported, per the Cloud guide read on 10 November (15). 1,048,576 tokens shared between input and output (15). Batch at half price on the platform (10). Python and JavaScript SDKs (10). Error codes with backoff guidance (10 of 15). 20 + 13 + 15 + 15 + 10 + 10 + 10 = 93." }, "scores": { "a": 80, "b": 93 } }, { "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-carbon 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 Carbon takes and refuses, the parameters that return 400 or are ignored, and how to migrate (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": "2026-11-10", "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 69.3 (B) on agent readiness against Gemini 4 Carbon's 62.6 (B), and leads in 4 of 7 scored categories. Gemini 4 Carbon leads on agent ergonomics and maintenance \u0026 community.", "question": "Which is better for AI agents, Fireworks AI Inference or Gemini 4 Carbon?" }, { "answer": "Both need an API key.", "question": "Do Fireworks AI Inference and Gemini 4 Carbon need an API key?" }, { "answer": "Yes. Fireworks AI Inference has a hosted endpoint at https://api.fireworks.ai/inference/v1 and Gemini 4 Carbon at https://generativelanguage.googleapis.com/v1beta.", "question": "Can an agent call Fireworks AI Inference and Gemini 4 Carbon without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 70 against 40", "Schema \u0026 documentation, 93 against 85", "Security \u0026 auth, 77 against 55", "Payments \u0026 pricing, 40 against 20" ], "also": null, "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, 93 against 80", "Maintenance \u0026 community, 83 against 65" ], "also": [ "No incidents deducted, where Fireworks AI Inference loses 3 points for them" ], "goodFor": "Agents on the hardest long tasks (multi-step debugging, large codebases, open-ended research, security work) that can pay frontier prices and already use the Gemini API.", "slug": "gemini-4-carbon", "watchFor": "Paid tier only, with no free tier to try it on" } ], "history": { "fireworks-inference": [ { "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-carbon": 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-carbon.json", "title": "Amazon Bedrock vs Gemini 4 Carbon", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-gemini-4-carbon" }, { "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-carbon.json", "title": "Claude API vs Gemini 4 Carbon", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-gemini-4-carbon" }, { "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-carbon.json", "title": "Antseed vs Gemini 4 Carbon", "url": "https://www.anchorterminal.com/compare/antseed-vs-gemini-4-carbon" }, { "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-carbon.json", "title": "Azure OpenAI in Foundry Models vs Gemini 4 Carbon", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-gemini-4-carbon" }, { "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-carbon.json", "title": "BlockRun.AI vs Gemini 4 Carbon", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-gemini-4-carbon" }, { "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-carbon.json", "title": "Cerebras Inference vs Gemini 4 Carbon", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-gemini-4-carbon" }, { "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-carbon.json", "title": "Claude Fable 5.2 vs Gemini 4 Carbon", "url": "https://www.anchorterminal.com/compare/claude-fable-5-2-vs-gemini-4-carbon" }, { "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-carbon.json", "title": "Claude Mythos 5.2 vs Gemini 4 Carbon", "url": "https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-gemini-4-carbon" }, { "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-carbon.json", "title": "Cloudflare AI Gateway vs Gemini 4 Carbon", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-gemini-4-carbon" }, { "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-carbon.json", "title": "Cloudflare Workers AI vs Gemini 4 Carbon", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-gemini-4-carbon" }, { "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-carbon.json", "title": "Cohere Chat API (Command models) vs Gemini 4 Carbon", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-gemini-4-carbon" }, { "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-carbon.json", "title": "DeepInfra vs Gemini 4 Carbon", "url": "https://www.anchorterminal.com/compare/deepinfra-vs-gemini-4-carbon" }, { "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-carbon.json", "title": "DeepSeek API vs Gemini 4 Carbon", "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-gemini-4-carbon" }, { "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-carbon.json", "title": "Eden AI vs Gemini 4 Carbon", "url": "https://www.anchorterminal.com/compare/eden-ai-vs-gemini-4-carbon" }, { "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-carbon.json", "title": "Glimpse vs Gemini 4 Carbon", "url": "https://www.anchorterminal.com/compare/elorian-glimpse-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-inkling-2-small.json", "title": "Fireworks AI Inference vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-inkling-2-small" }, { "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-api.json", "title": "Gemini 4 Carbon vs Gemini Developer API", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-gemini-api" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-groq.json", "title": "Gemini 4 Carbon vs GroqCloud", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-groq" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-hugging-face-inference-providers.json", "title": "Gemini 4 Carbon vs Hugging Face Inference Providers", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-hugging-face-inference-providers" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-inkling-2-small.json", "title": "Gemini 4 Carbon vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-jais-3.json", "title": "Gemini 4 Carbon vs Jais 3", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-meta-model-api.json", "title": "Gemini 4 Carbon vs Meta Model API", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-minimax-api.json", "title": "Gemini 4 Carbon vs MiniMax API", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-minimax-api" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-mistral-api.json", "title": "Gemini 4 Carbon vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-muse-ember.json", "title": "Gemini 4 Carbon vs Muse Ember", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-muse-spark-open.json", "title": "Gemini 4 Carbon vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-muse-spark-open" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-nemotron-3-5-super-vl.json", "title": "Gemini 4 Carbon vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-novita-ai.json", "title": "Gemini 4 Carbon vs Novita AI", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-novita-ai" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-openai-api.json", "title": "Gemini 4 Carbon vs OpenAI API", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-openai-api" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-openrouter.json", "title": "Gemini 4 Carbon vs OpenRouter", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-openrouter" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-prism-inference.json", "title": "Gemini 4 Carbon vs Prism Inference", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-ramp-router.json", "title": "Gemini 4 Carbon vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-reflection-beam.json", "title": "Gemini 4 Carbon vs Beam 1.0", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-reflection-beam" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-routerplus.json", "title": "Gemini 4 Carbon vs RouterPlus", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-routerplus" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-sambanova.json", "title": "Gemini 4 Carbon vs SambaCloud", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-sambanova" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-siliconflow.json", "title": "Gemini 4 Carbon vs SiliconFlow", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-siliconflow" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-simplismart.json", "title": "Gemini 4 Carbon vs Simplismart", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-simplismart" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-stepfun-api.json", "title": "Gemini 4 Carbon vs StepFun API", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-stepfun-api" }, { "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-carbon-vs-tencent-tokenhub.json", "title": "Gemini 4 Carbon vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-together-inference.json", "title": "Gemini 4 Carbon vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-together-inference" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-vercel-ai-gateway.json", "title": "Gemini 4 Carbon vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-vertex-ai.json", "title": "Gemini 4 Carbon vs Vertex AI (Gemini Enterprise Agent Platform)", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-vertex-ai" }, { "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-xai-api.json", "title": "Gemini 4 Carbon vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-xai-api" } ], "panel": null, "scores": [ { "by": 30, "edge": "fireworks-inference", "fireworks-inference": 70, "gemini-4-carbon": 40, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 8, "edge": "fireworks-inference", "fireworks-inference": 93, "gemini-4-carbon": 85, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 13, "edge": "gemini-4-carbon", "fireworks-inference": 80, "gemini-4-carbon": 93, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 22, "edge": "fireworks-inference", "fireworks-inference": 77, "gemini-4-carbon": 55, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 20, "edge": "fireworks-inference", "fireworks-inference": 40, "gemini-4-carbon": 20, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 18, "edge": "gemini-4-carbon", "fireworks-inference": 65, "gemini-4-carbon": 83, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 3, "edge": "gemini-4-carbon", "fireworks-inference": 69, "gemini-4-carbon": 72, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Fireworks AI Inference scores 69.3 (B) on agent readiness against Gemini 4 Carbon's 62.6 (B), and leads in 4 of 7 scored categories. Gemini 4 Carbon 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-carbon": "Google's strongest model on the same Gemini API as Argon, with a 1M-token budget, function calling and structured output, at an introductory $2 and $10 per million tokens. Paid tier only, sampling parameters are ignored or refused, its launch stage isn't stated, and the price rises to $4 and $20 at a date Google hasn't given." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-4-carbon", "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-4-carbon.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-4-carbon.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-4-carbon.min.md" }, "markdown": "Fireworks AI Inference scores 69.3 (B) on agent readiness against Gemini 4 Carbon's 62.6 (B), and leads in 4 of 7 scored categories. Gemini 4 Carbon leads on agent ergonomics and maintenance \u0026 community. Both do llm inference.\n\n- Fireworks AI Inference: grade B, 69.3/100, rank #252 of 1520. Markdown https://www.anchorterminal.com/tools/fireworks-inference.md · JSON https://www.anchorterminal.com/api/v1/tools/fireworks-inference.json\n- Gemini 4 Carbon: grade B, 62.6/100, rank #555 of 1520. Markdown https://www.anchorterminal.com/tools/gemini-4-carbon.md · JSON https://www.anchorterminal.com/api/v1/tools/gemini-4-carbon.json\n- Best model APIs and inference for AI agents: https://www.anchorterminal.com/best/inference/index.md\n- All 999 models comparisons: https://www.anchorterminal.com/compare/inference/index.md\n\n## Which one, for what\n\n### Fireworks AI Inference (B)\n\nGood for: Fireworks AI Inference runs open models through OpenAI-compatible chat and completion APIs.\n\nAhead on:\n- Reliability, 70 against 40\n- Schema \u0026 documentation, 93 against 85\n- Security \u0026 auth, 77 against 55\n- Payments \u0026 pricing, 40 against 20\n\nWatch for: Cloud provider outages on 11 August and 14 October hit many serverless models for hours\n\n### Gemini 4 Carbon (B)\n\nGood for: Agents on the hardest long tasks (multi-step debugging, large codebases, open-ended research, security work) that can pay frontier prices and already use the Gemini API.\n\nAhead on:\n- Agent ergonomics, 93 against 80\n- Maintenance \u0026 community, 83 against 65\n\nAlso in its favour:\n- No incidents deducted, where Fireworks AI Inference loses 3 points for them\n\nWatch for: Paid tier only, with no free tier to try it on\n\n\n## Why the edge\n\n### Reliability: Fireworks AI Inference +30\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 Carbon (40): Model reading for gemini-4-carbon 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). Carbon's launch stage isn't stated in Google's developer post, the Antigravity post or the Cloud developer guide read on 10 November, and the model ID carries no preview label, so half (5 of 10, a judgement call; Argon's GA earned the platform 10). 10 + 5 + 5 + 15 + 0 + 5 = 40.\n\n### Security \u0026 auth: Fireworks AI Inference +22\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 Carbon (55): Model reading for gemini-4-carbon 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). Carbon is on the paid tier only, and Google's terms say paid-tier content isn't used to improve products; AI Studio use under a Google AI Ultra subscription falls under terms we didn't read, so 15 of 20 (a judgement call; the platform's 10 is for its free tier). Abuse retention with no number, and new paid projects store requests by default since 26 October (5 of 15). Request logs for billed projects (15). security.txt and a reward programme, no certification naming the API (5 of 20). 15 + 15 + 5 + 15 + 5 = 55.\n\n### Payments \u0026 pricing: Fireworks AI Inference +20\n\n- Fireworks AI Inference (40): 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).\n- Gemini 4 Carbon (20): Model reading for gemini-4-carbon 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). Introductory prices published in Google's 28 October announcement without a login, $2 and $10, then $4 and $20; the Gemini API pricing page as read on 10 November showed no Carbon row, so the figures rest on the announcement (20). No free tier: Google's developer post puts Carbon on the paid tier (0). A Google account and AI Studio for a key (0). 0 + 20 + 0 + 0 = 20.\n\n### Maintenance \u0026 community: Gemini 4 Carbon +18\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 Carbon (83): Model reading for gemini-4-carbon 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 to developers on 10 November 2026, with the platform's changelog (30). Deprecations with earliest dates and no stated minimum notice (4 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 (15). Runtimes stated (10). 30 + 4 + 4 + 15 + 5 + 15 + 10 = 83.\n\n### Agent ergonomics: Gemini 4 Carbon +13\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 Carbon (93): Model reading for gemini-4-carbon 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 (13 of 15). Implicit caching with durable caching on by default, cached input 95% off, explicit caches not supported, per the Cloud guide read on 10 November (15). 1,048,576 tokens shared between input and output (15). Batch at half price on the platform (10). Python and JavaScript SDKs (10). Error codes with backoff guidance (10 of 15). 20 + 13 + 15 + 15 + 10 + 10 + 10 = 93.\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 Carbon (85): Model reading for gemini-4-carbon 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 Carbon takes and refuses, the parameters that return 400 or are ignored, and how to migrate (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 Carbon | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 70 | 40 | Fireworks AI Inference +30 |\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 | 93 | Gemini 4 Carbon +13 |\n| Security \u0026 auth | 14% (17.5 this run) | 77 | 55 | Fireworks AI Inference +22 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 20 | 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 | 83 | Gemini 4 Carbon +18 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 69 | 72 | Gemini 4 Carbon +3 |\n| Negative events | ≤15 | -3 | 0 | |\n| **Total** | | **69.3 · B** | **62.6 · B** | |\n\n## Facts side by side\n\n| Fact | Fireworks AI Inference | Gemini 4 Carbon |\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 | 2026-11-10 |\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- -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 Carbon\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 Carbon.** Google's strongest model on the same Gemini API as Argon, with a 1M-token budget, function calling and structured output, at an introductory $2 and $10 per million tokens. Paid tier only, sampling parameters are ignored or refused, its launch stage isn't stated, and the price rises to $4 and $20 at a date Google hasn't given.\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 Carbon\n\n1. Call generateContent at https://generativelanguage.googleapis.com/v1beta with model gemini-4-carbon and an x-goog-api-key on a billed project\n2. Set thinking_level (LOW, MEDIUM or HIGH) instead of thinking_budget, and don't send temperature, top_p or top_k\n3. Count output against the same 1,048,576-token limit as the input, and set max_output_tokens for long answers\n4. Put static prompt content first so implicit caching applies; explicit caches aren't supported\n5. Use gemini-4-argon for most coding and knowledge work, and Carbon for the hardest long tasks, as Google suggests\n\n## Questions\n\n### Which is better for AI agents, Fireworks AI Inference or Gemini 4 Carbon?\n\nFireworks AI Inference scores 69.3 (B) on agent readiness against Gemini 4 Carbon's 62.6 (B), and leads in 4 of 7 scored categories. Gemini 4 Carbon leads on agent ergonomics and maintenance \u0026 community.\n\n### Do Fireworks AI Inference and Gemini 4 Carbon need an API key?\n\nBoth need an API key.\n\n### Can an agent call Fireworks AI Inference and Gemini 4 Carbon without installing anything?\n\nYes. Fireworks AI Inference has a hosted endpoint at https://api.fireworks.ai/inference/v1 and Gemini 4 Carbon 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-carbon.json, and with the fewest tokens: https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-4-carbon.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"fireworks-inference\", \"b\": \"gemini-4-carbon\"}`. From a terminal: `anchor compare fireworks-inference gemini-4-carbon`\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-carbon.json\n\n## Other comparisons with Fireworks AI Inference or Gemini 4 Carbon\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 Carbon](https://www.anchorterminal.com/compare/amazon-bedrock-vs-gemini-4-carbon.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 Carbon](https://www.anchorterminal.com/compare/anthropic-api-vs-gemini-4-carbon.md)\n- [Antseed vs Fireworks AI Inference](https://www.anchorterminal.com/compare/antseed-vs-fireworks-inference.md)\n- [Antseed vs Gemini 4 Carbon](https://www.anchorterminal.com/compare/antseed-vs-gemini-4-carbon.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 Carbon](https://www.anchorterminal.com/compare/azure-openai-vs-gemini-4-carbon.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 Carbon](https://www.anchorterminal.com/compare/blockrun-ai-vs-gemini-4-carbon.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 Carbon](https://www.anchorterminal.com/compare/cerebras-inference-vs-gemini-4-carbon.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 Carbon](https://www.anchorterminal.com/compare/claude-fable-5-2-vs-gemini-4-carbon.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 Carbon](https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-gemini-4-carbon.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 Carbon](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-gemini-4-carbon.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 Carbon](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-gemini-4-carbon.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 Carbon](https://www.anchorterminal.com/compare/cohere-chat-vs-gemini-4-carbon.md)\n- [DeepInfra vs Fireworks AI Inference](https://www.anchorterminal.com/compare/deepinfra-vs-fireworks-inference.md)\n- [DeepInfra vs Gemini 4 Carbon](https://www.anchorterminal.com/compare/deepinfra-vs-gemini-4-carbon.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 Carbon](https://www.anchorterminal.com/compare/deepseek-api-vs-gemini-4-carbon.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 Carbon](https://www.anchorterminal.com/compare/eden-ai-vs-gemini-4-carbon.md)\n- [Glimpse vs Fireworks AI Inference](https://www.anchorterminal.com/compare/elorian-glimpse-vs-fireworks-inference.md)\n- [Glimpse vs Gemini 4 Carbon](https://www.anchorterminal.com/compare/elorian-glimpse-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 Inkling 2 Small](https://www.anchorterminal.com/compare/fireworks-inference-vs-inkling-2-small.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 Developer API](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-gemini-api.md)\n- [Gemini 4 Carbon vs GroqCloud](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-groq.md)\n- [Gemini 4 Carbon vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-hugging-face-inference-providers.md)\n- [Gemini 4 Carbon vs Inkling 2 Small](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-inkling-2-small.md)\n- [Gemini 4 Carbon vs Jais 3](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-jais-3.md)\n- [Gemini 4 Carbon vs Meta Model API](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-meta-model-api.md)\n- [Gemini 4 Carbon vs MiniMax API](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-minimax-api.md)\n- [Gemini 4 Carbon vs Mistral AI API](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-mistral-api.md)\n- [Gemini 4 Carbon vs Muse Ember](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-muse-ember.md)\n- [Gemini 4 Carbon vs Muse Spark Open](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-muse-spark-open.md)\n- [Gemini 4 Carbon vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-nemotron-3-5-super-vl.md)\n- [Gemini 4 Carbon vs Novita AI](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-novita-ai.md)\n- [Gemini 4 Carbon vs OpenAI API](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-openai-api.md)\n- [Gemini 4 Carbon vs OpenRouter](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-openrouter.md)\n- [Gemini 4 Carbon vs Prism Inference](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-prism-inference.md)\n- [Gemini 4 Carbon vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-ramp-router.md)\n- [Gemini 4 Carbon vs Beam 1.0](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-reflection-beam.md)\n- [Gemini 4 Carbon vs RouterPlus](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-routerplus.md)\n- [Gemini 4 Carbon vs SambaCloud](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-sambanova.md)\n- [Gemini 4 Carbon vs SiliconFlow](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-siliconflow.md)\n- [Gemini 4 Carbon vs Simplismart](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-simplismart.md)\n- [Gemini 4 Carbon vs StepFun API](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-stepfun-api.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 Carbon vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-tencent-tokenhub.md)\n- [Gemini 4 Carbon vs Together AI Inference](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-together-inference.md)\n- [Gemini 4 Carbon vs Vercel AI Gateway](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-vercel-ai-gateway.md)\n- [Gemini 4 Carbon vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-vertex-ai.md)\n- [Gemini 4 Carbon vs xAI API (Grok)](https://www.anchorterminal.com/compare/gemini-4-carbon-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": "2026-11-12", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Fireworks AI Inference vs Gemini 4 Carbon", "url": "" } ], "description": "Fireworks AI Inference scores 69.3 (B) to Gemini 4 Carbon's 62.6 (B) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Fireworks AI Inference B 69.3", "Gemini 4 Carbon B 62.6", "scores" ], "h1": "Fireworks AI Inference vs Gemini 4 Carbon", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/fireworks-inference-vs-gemini-4-carbon", "published": "2026-10-01", "section": "tools", "title": "Fireworks AI Inference vs Gemini 4 Carbon for AI agents (2026)", "toc": null, "updated": "2026-11-11", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-4-carbon" }, "tokens": { "markdown": 7050, "slim": 1130 }, "version": 1 }