{ "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 Tencent Hy4's 64 (B), and leads in 5 of 7 scored categories. Tencent Hy4 leads on agent ergonomics and maintenance \u0026 community.", "b": { "slug": "hy4", "name": "Tencent Hy4", "vendor": "Tencent (Hy team)", "vendorUrl": "https://aistudio.tencent.com", "kind": "model", "category": "inference", "summary": "Tencent Hy4 is Tencent's flagship language model, released on 4 November 2026 with image understanding and computer use, served on Tencent Cloud TokenHub as hy4 with a 1M-token context, at ¥6 input and ¥18 output per million tokens.", "url": "https://www.anchorterminal.com/tools/hy4", "markdownUrl": "https://www.anchorterminal.com/tools/hy4.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/hy4.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/hy4.json", "dns": "hy4.grade.anchorterminal.com", "license": "Hosted model under the Tencent Cloud TokenHub terms. Tencent says weights and a system card will follow; no licence is stated yet", "transports": [ "http" ], "packages": [], "auth": "api-key", "authNotes": "A TokenHub bearer key (or `x-api-key` on the Anthropic-style route) from a Tencent Cloud account with real-name verification, per the tencent-tokenhub listing. Keys can be limited by model, service, IP range and token quota.", "pricing": "usage", "pricingNotes": "¥6 input, ¥0.3 cached input and ¥18 output per million tokens on TokenHub, billed at 50% until 31 December 2026 (Beijing time), per the price page updated 9 November 2026. Tencent's release gives about US$0.90, US$0.045 and US$2.70. No free allowance named for hy4 on the price page.", "priceSummary": "Pay per use", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in Tencent's release or TokenHub's price page, 11 November 2026.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-11" }, "docsUrl": "https://cloud.tencent.com/document/product/1823/130051", "llmsTxt": "https://cloud.tencent.com/document/product/1823/llms.txt", "capabilities": [ "inference.llm" ], "tags": [ "official", "hosted", "model", "multimodal", "reasoning", "long-context", "tool-calling", "usage-priced", "openai-compatible", "anthropic-compatible", "chinese", "new" ], "lastRelease": "2026-11-04", "graded": true, "anchor": { "graded": true, "score": 64, "grade": "B", "agentReady": false, "rank": 595, "ranked": true, "rankOf": 1524, "categoryRank": 25, "methodology": "0.8", "run": "2026-10-01", "scores": { "ergonomics": 86, "maintenance": 73, "payments": 45, "reliability": 46, "schema": 73, "security": 71, "transparency": 52 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-11" }, "negative": 0, "verdict": "Tencent's flagship model is on TokenHub as hy4, with a 1M-token context, image understanding, function calling and caching, at ¥6 input and ¥18 output per million tokens, half price until the end of 2026. The weights it is called open source for aren't published yet, and every benchmark is Tencent's own.", "bestFor": "Long-context agent work, coding and office or finance tasks on a 1M-token context with images, for teams already on Tencent Cloud or happy to verify an account there.", "strengths": [ "1M-token context with 960K input and 64K output, per TokenHub's model list", "Image understanding, function calling, structured output, thinking and caching are marked for hy4", "Prices published: ¥6 input, ¥0.3 cached, ¥18 output per million tokens, billed at 50% until 31 December 2026", "OpenAI- and Anthropic-compatible endpoints on TokenHub, so existing SDKs work with a changed base URL", "Tencent says it's the same price as Hy4 preview despite the upgrade" ], "weaknesses": [ "Weights, licence and system card are promised but not published; tencent/Hy4 didn't answer on Hugging Face on 11 November", "Computer use, which Tencent's release names, isn't marked in TokenHub's model list", "TokenHub needs real-name verification, and the international site answers with a bot check", "No public status page for TokenHub", "Every benchmark in the release is Tencent's own or a partner's, several of them internal" ], "agentNotes": [ "Use model id hy4 on TokenHub's OpenAI- or Anthropic-compatible endpoints; hy4-preview is a separate, older model", "Keep input under 960K tokens and expect at most 64K output", "Reuse prompt prefixes: cached input is ¥0.3 against ¥6", "Check the price page for the end of the 50% discount on 31 December 2026 before budgeting", "Read rate limits from the console or DescribeModelQuota; the public docs don't give them for chat models" ], "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 } ], "editorialScores": { "ergonomics": 86, "maintenance": 73, "payments": 45, "reliability": 46, "schema": 73, "security": 71, "transparency": 55 }, "provenanceScore": 49, "checked": { "categories": { "ergonomics": "2026-11-11", "maintenance": "2026-11-11", "payments": "2026-11-11", "reliability": "2026-11-11", "schema": "2026-11-11", "security": "2026-11-11", "transparency": "2026-11-11" }, "last": "2026-11-11", "lastMoved": "2026-11-13", "oldest": "2026-11-11", "stale": false, "staleAfterDays": 90 } }, "connect": { "http": "curl https://tokenhub.tencentmaas.com/v1/chat/completions \\\n -H \"Authorization: Bearer $TOKENHUB_API_KEY\" -H \"content-type: application/json\" \\\n -d '{\"model\":\"hy4\",\"messages\":[{\"role\":\"user\",\"content\":\"hello\"}]}'" }, "letme": { "capability": "https://letme.dev/inference.llm", "tool": "https://letme.dev/hy4" }, "sameCompany": [ "hy-memory", "tencentdb-agent-memory", "hunyuanocr", "octop", "hy-memory-30b-a3b", "hy3", "wevisone-vl-2b", "wevisone-vl-4b" ], "sameModel": [ "tencent-tokenhub" ], "area": "models", "unitPrices": [ { "item": "Hy4 input", "unit": "1m-tokens", "usd": 0.9, "note": "¥6 list, about US$0.90 per Tencent; billed at 50% until 31 December 2026" }, { "item": "Hy4 cached input", "unit": "1m-tokens", "usd": 0.045, "note": "¥0.3 list" }, { "item": "Hy4 output", "unit": "1m-tokens", "usd": 2.7, "note": "¥18 list" } ], "provenance": { "legalEntity": "Tencent Cloud Computing (Beijing) Co., Ltd. (腾讯云计算（北京）有限责任公司)", "domain": "tencentmaas.com", "domainRegistered": "2026-03-13", "endpointOnVendorDomain": false, "terms": "https://cloud.tencent.com/document/product/301/129852", "privacy": "https://privacy.qq.com/document/preview/91d5fd3c98ce4468ae462ac59233bba2", "statusPage": "", "changelog": "https://cloud.tencent.com/document/product/1823/130675", "securityTxt": "none", "checked": "2026-11-11", "notes": [ "The TokenHub Terms of Service (effective 14 September 2026), the SLA (effective 23 April 2026) and the special note on third-party deployed models (effective 14 September 2026) name 腾讯云计算（北京）有限责任公司. The docs footer also names 深圳市腾讯计算机系统有限公司 as ICP licence holder.", "The TokenHub privacy policy is linked from the docs to privacy.qq.com, which renders only with JavaScript, so it was not read. privacy.qq.com has no robots.txt (404).", "No public status page was found. status.cloud.tencent.com did not answer, and the Tencent Cloud health dashboard documentation answered with a bot check.", "security.txt answered 404 on cloud.tencent.com, www.tencent.com and tokenhub.tencentmaas.com. Tencent's bug bounty policy at en.security.tencent.com lists Tencent Cloud in scope.", "RDAP at Verisign gives tencentmaas.com a registration date of 13 March 2026 with no registrant. The API answers at tokenhub.tencentmaas.com and tokenhub-intl.tencentmaas.com, named in Tencent Cloud's API usage page.", "cloud.tencent.com allows these docs in robots.txt. Its pages answered some requests with a JavaScript bot check, which was not passed. The pages were read when a later plain request returned them. www.tencentcloud.com answered robots.txt with a bot check, so the international site was not read." ], "score": 49 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/hy4.json", "live": { "slug": "hy4", "securityTxt": { "url": "https://tencentmaas.com/.well-known/security.txt", "state": "unknown", "checkedAt": "2026-11-13T16:16:35.489580858Z" }, "llmsTxt": { "url": "https://cloud.tencent.com/document/product/1823/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-13T15:54:34.939672287Z" }, "pages": [ { "url": "https://cloud.tencent.com/document/product/1823/130675", "kind": "changelog", "status": 200, "checkedAt": "2026-11-13T18:11:34.856577424Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e3b0c44298fc" }, { "url": "https://privacy.qq.com/document/preview/91d5fd3c98ce4468ae462ac59233bba2", "kind": "privacy", "status": 304, "checkedAt": "2026-11-13T18:28:00.062507799Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e3b0c44298fc" }, { "url": "https://cloud.tencent.com/document/product/301/129852", "kind": "terms", "status": 200, "checkedAt": "2026-11-13T18:11:36.909670614Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e3b0c44298fc" } ], "updatedAt": "2026-11-13T18:28:00.062507799Z" } }, "edges": [ { "by": 24, "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 hy4 on Tencent Cloud TokenHub. Platform facts are the tencent-tokenhub listing's (checked 1 November), carried over as RULES.md allows for a model on an already graded platform. No public status page (0) and so no incident record to read (5 of 30). Per-model rate limits only in the console and DescribeModelQuota (8 of 15). Six 429 codes, Retry-After and backoff advice (13 of 15). The TokenHub SLA promises 99.5% a month, and Hy4 is Tencent's own model, so the third-party exclusion doesn't apply (10). Released as hy4 on 4 November, a separate id from hy4-preview, with no preview label (10). 0 + 5 + 8 + 13 + 10 + 10 = 46." }, "scores": { "a": 70, "b": 46 } }, { "by": 20, "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 hy4 on Tencent Cloud TokenHub. Platform facts are the tencent-tokenhub listing's (checked 1 November), carried over as RULES.md allows for a model on an already graded platform. No OpenAPI file for inference; field pages for the OpenAI and Anthropic formats as TokenHub implements them (12 of 25). llms.txt with Markdown copies (10). The model list, updated 9 November, gives hy4's context, input and output limits and marks thinking, structured output, function calling, caching and image understanding; computer use, which Tencent's release names, isn't marked (13 of 20). Typed field pages (10 of 15). Examples in five languages and an error page of 30 codes (14 of 15). Dated release notes, with hy4 added on 4 November (14 of 15). 12 + 10 + 13 + 10 + 14 + 14 = 73." }, "scores": { "a": 93, "b": 73 } }, { "by": 17, "category": "transparency", "leads": "fireworks-inference", "name": "Transparency \u0026 trust", "reasons": { "a": "Proprietary service, Apache-2.0 Python SDK. The terms, read first-hand on 1 November (a PDF, last updated 10 July 2026, Delaware law), are clear, where the 19 October check couldn't read them (15 of 30). The data-handling page and section 3.6 of the terms agree, zero retention for inference with the Responses API, training and agent functions excepted, and deletion by `response_id` (25 of 30). Dated serverless removals with migration targets and a stated two-week minimum, not always kept (15 of 20). Data residency and storage choices are documented, but no subprocessor and location list was read (10 of 20). 15+25+15+10 = 65.", "b": "Model reading for hy4 on Tencent Cloud TokenHub. Platform facts are the tencent-tokenhub listing's (checked 1 November), carried over as RULES.md allows for a model on an already graded platform. Closed service under the TokenHub terms, but Tencent's release headline calls Hy4 open source while the weights and system card are only promised 'in the coming days', with no licence stated, and tencent/Hy4 didn't answer on Hugging Face on 11 November (14 of 30). Terms and FAQ agree inputs aren't used for training; the privacy policy renders only with JavaScript and wasn't read (15 of 30). Dated retirement notices and shutdown fields (13 of 20). Processing generally in mainland China for the China site, Singapore for the international one (13 of 20). Every benchmark in the release is Tencent's own or a partner's. 14 + 15 + 13 + 13 = 55." }, "scores": { "a": 69, "b": 52 } }, { "by": 15, "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 hy4 on Tencent Cloud TokenHub. Platform facts are the tencent-tokenhub listing's (checked 1 November), carried over as RULES.md allows for a model on an already graded platform. No machine payment protocol (0). The price page, updated 9 November, lists ¥6 input, ¥0.3 cached and ¥18 output per million tokens, with Hy4 billed at 50% until 31 December 2026 (20). TokenHub's campaign of 1M free tokens per language model, read on 1 November, isn't confirmed for hy4 on the price page, so half (10 of 20, a judgement call). A person signs up with real-name verification (0). 0 + 20 + 10 + 0 = 30. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45." }, "scores": { "a": 60, "b": 45 } }, { "by": 8, "category": "maintenance", "leads": "hy4", "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 hy4 on Tencent Cloud TokenHub. Platform facts are the tencent-tokenhub listing's (checked 1 November), carried over as RULES.md allows for a model on an already graded platform. Added on 4 November 2026 per the release notes; the model list and price page were updated on 9 November (30). Retirement notices of 21 to 33 days, no minimum written (7 of 12). Heavy retirement churn on the platform (3 of 8). Dated release notes and announcements, round-the-clock support (13 of 15). CLI replies not sampled (3 of 10). Control-plane SDKs and CLI, no inference SDK of its own (12 of 15). CLI runtime stated, CI not checked (5 of 10). 30 + 7 + 3 + 13 + 3 + 12 + 5 = 73. The model is a week old, so these lines are TokenHub's habits more than Hy4's record." }, "scores": { "a": 65, "b": 73 } }, { "by": 6, "category": "ergonomics", "leads": "hy4", "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 hy4 on Tencent Cloud TokenHub. Platform facts are the tencent-tokenhub listing's (checked 1 November), carried over as RULES.md allows for a model on an already graded platform. Function calling is marked for hy4 in the model list (18 of 20). Structured output marked (13 of 15). Cache-hit price published, ¥0.3 against ¥6 input (14 of 15). 1M-token context with 960K input and 64K output (15). Batch at half price covered Hy3 and Hy4 preview on 1 November; whether it covers hy4 wasn't re-read (3 of 10). OpenAI and Anthropic SDKs with a changed base URL, plus Tencent Cloud's SDK and CLI for the control plane (8 of 10). Errors with code, messages, upstream status and request ID (15 of 15). 18 + 13 + 14 + 15 + 3 + 8 + 15 = 86." }, "scores": { "a": 80, "b": 86 } } ], "facts": [ { "a": "HTTP API", "b": "Model API", "name": "Kind" }, { "a": "Fireworks AI", "b": "Tencent (Hy team)", "name": "Vendor" }, { "a": "https://api.fireworks.ai/inference/v1", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "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": "Hosted model under the Tencent Cloud TokenHub terms. Tencent says weights and a system card will follow; no licence is stated yet", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-27", "b": "2026-11-04", "name": "Last release" }, { "a": "couldn't be read", "b": "couldn't be read", "name": "Terms last updated" }, { "a": "no date given", "b": "couldn't be read", "name": "Privacy policy last updated" }, { "a": "couldn't be read", "b": "couldn't be read", "name": "Customer content may train models" }, { "a": "couldn't be read", "b": "couldn't be read", "name": "Terms restrict automated access" }, { "a": "couldn't be read", "b": "couldn't be read", "name": "Terms restrict benchmarking" }, { "a": "couldn't be read", "b": "couldn't be read", "name": "Terms or service can change without notice" }, { "a": "couldn't be read", "b": "couldn't be read", "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 Tencent Hy4's 64 (B), and leads in 5 of 7 scored categories. Tencent Hy4 leads on agent ergonomics and maintenance \u0026 community.", "question": "Which is better for AI agents, Fireworks AI Inference or Tencent Hy4?" }, { "answer": "Both need an API key.", "question": "Do Fireworks AI Inference and Tencent Hy4 need an API key?" }, { "answer": "Fireworks AI Inference has a hosted endpoint at https://api.fireworks.ai/inference/v1. No hosted endpoint is listed for Tencent Hy4.", "question": "Can an agent call Fireworks AI Inference and Tencent Hy4 without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 70 against 46", "Schema \u0026 documentation, 93 against 73", "Security \u0026 auth, 77 against 71", "Payments \u0026 pricing, 60 against 45", "Transparency \u0026 trust, 69 against 52" ], "also": [ "Agent-ready, a grade of BB or better", "A hosted endpoint, with nothing to install" ], "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, 86 against 80", "Maintenance \u0026 community, 73 against 65" ], "also": [ "No incidents deducted, where Fireworks AI Inference loses 3 points for them" ], "goodFor": "Long-context agent work, coding and office or finance tasks on a 1M-token context with images, for teams already on Tencent Cloud or happy to verify an account there.", "slug": "hy4", "watchFor": "Weights, licence and system card are promised but not published; tencent/Hy4 didn't answer on Hugging Face on 11 November" } ], "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" } ], "hy4": [ { "causes": [ "method" ], "date": "2026-11-13", "delta": 1.8, "from": 62.2, "fromGrade": "B", "to": 64, "toGrade": "B" } ] }, "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-hy4.json", "title": "Amazon Bedrock vs Tencent Hy4", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-hy4" }, { "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-hy4.json", "title": "Claude API vs Tencent Hy4", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-hy4" }, { "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-hy4.json", "title": "Antseed vs Tencent Hy4", "url": "https://www.anchorterminal.com/compare/antseed-vs-hy4" }, { "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-hy4.json", "title": "Azure OpenAI in Foundry Models vs Tencent Hy4", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-hy4" }, { "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-hy4.json", "title": "BlockRun.AI vs Tencent Hy4", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-hy4" }, { "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-hy4.json", "title": "Cerebras Inference vs Tencent Hy4", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-hy4" }, { "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-hy4.json", "title": "Claude Fable 5.2 vs Tencent Hy4", "url": "https://www.anchorterminal.com/compare/claude-fable-5-2-vs-hy4" }, { "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-hy4.json", "title": "Claude Mythos 5.2 vs Tencent Hy4", "url": "https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-hy4" }, { "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-hy4.json", "title": "Cloudflare AI Gateway vs Tencent Hy4", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-hy4" }, { "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-hy4.json", "title": "Cloudflare Workers AI vs Tencent Hy4", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-hy4" }, { "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-hy4.json", "title": "Cohere Chat API (Command models) vs Tencent Hy4", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-hy4" }, { "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-hy4.json", "title": "DeepInfra vs Tencent Hy4", "url": "https://www.anchorterminal.com/compare/deepinfra-vs-hy4" }, { "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-hy4.json", "title": "DeepSeek API vs Tencent Hy4", "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-hy4" }, { "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-hy4.json", "title": "Eden AI vs Tencent Hy4", "url": "https://www.anchorterminal.com/compare/eden-ai-vs-hy4" }, { "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-hy4.json", "title": "Glimpse vs Tencent Hy4", "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-hy4" }, { "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-4-hydrogen.json", "title": "Fireworks AI Inference vs Gemini 4 Hydrogen", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-4-hydrogen" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-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-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-hy4.json", "title": "Gemini 4 Carbon vs Tencent Hy4", "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-hy4" }, { "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-api-vs-hy4.json", "title": "Gemini Developer API vs Tencent Hy4", "url": "https://www.anchorterminal.com/compare/gemini-api-vs-hy4" }, { "json": "https://www.anchorterminal.com/compare/groq-vs-hy4.json", "title": "GroqCloud vs Tencent Hy4", "url": "https://www.anchorterminal.com/compare/groq-vs-hy4" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-hy4.json", "title": "Hugging Face Inference Providers vs Tencent Hy4", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-hy4" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-jais-3.json", "title": "Tencent Hy4 vs Jais 3", "url": "https://www.anchorterminal.com/compare/hy4-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-meta-model-api.json", "title": "Tencent Hy4 vs Meta Model API", "url": "https://www.anchorterminal.com/compare/hy4-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-minimax-api.json", "title": "Tencent Hy4 vs MiniMax API", "url": "https://www.anchorterminal.com/compare/hy4-vs-minimax-api" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-mistral-api.json", "title": "Tencent Hy4 vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/hy4-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-muse-ember.json", "title": "Tencent Hy4 vs Muse Ember", "url": "https://www.anchorterminal.com/compare/hy4-vs-muse-ember" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-muse-spark-open.json", "title": "Tencent Hy4 vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/hy4-vs-muse-spark-open" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-nemotron-3-5-super-vl.json", "title": "Tencent Hy4 vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/hy4-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-novita-ai.json", "title": "Tencent Hy4 vs Novita AI", "url": "https://www.anchorterminal.com/compare/hy4-vs-novita-ai" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-openai-api.json", "title": "Tencent Hy4 vs OpenAI API", "url": "https://www.anchorterminal.com/compare/hy4-vs-openai-api" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-openrouter.json", "title": "Tencent Hy4 vs OpenRouter", "url": "https://www.anchorterminal.com/compare/hy4-vs-openrouter" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-prism-inference.json", "title": "Tencent Hy4 vs Prism Inference", "url": "https://www.anchorterminal.com/compare/hy4-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-ramp-router.json", "title": "Tencent Hy4 vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/hy4-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-reflection-beam.json", "title": "Tencent Hy4 vs Beam 1.0", "url": "https://www.anchorterminal.com/compare/hy4-vs-reflection-beam" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-routerplus.json", "title": "Tencent Hy4 vs RouterPlus", "url": "https://www.anchorterminal.com/compare/hy4-vs-routerplus" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-sambanova.json", "title": "Tencent Hy4 vs SambaCloud", "url": "https://www.anchorterminal.com/compare/hy4-vs-sambanova" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-siliconflow.json", "title": "Tencent Hy4 vs SiliconFlow", "url": "https://www.anchorterminal.com/compare/hy4-vs-siliconflow" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-simplismart.json", "title": "Tencent Hy4 vs Simplismart", "url": "https://www.anchorterminal.com/compare/hy4-vs-simplismart" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-stepfun-api.json", "title": "Tencent Hy4 vs StepFun API", "url": "https://www.anchorterminal.com/compare/hy4-vs-stepfun-api" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-swe-2-flash.json", "title": "Tencent Hy4 vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/hy4-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-tencent-tokenhub.json", "title": "Tencent Hy4 vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/hy4-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-together-inference.json", "title": "Tencent Hy4 vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/hy4-vs-together-inference" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-vercel-ai-gateway.json", "title": "Tencent Hy4 vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/hy4-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-vertex-ai.json", "title": "Tencent Hy4 vs Vertex AI (Gemini Enterprise Agent Platform)", "url": "https://www.anchorterminal.com/compare/hy4-vs-vertex-ai" }, { "json": "https://www.anchorterminal.com/compare/hy4-vs-xai-api.json", "title": "Tencent Hy4 vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/hy4-vs-xai-api" } ], "panel": null, "scores": [ { "by": 24, "edge": "fireworks-inference", "fireworks-inference": 70, "hy4": 46, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 20, "edge": "fireworks-inference", "fireworks-inference": 93, "hy4": 73, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 6, "edge": "hy4", "fireworks-inference": 80, "hy4": 86, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 6, "edge": "fireworks-inference", "fireworks-inference": 77, "hy4": 71, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 15, "edge": "fireworks-inference", "fireworks-inference": 60, "hy4": 45, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 8, "edge": "hy4", "fireworks-inference": 65, "hy4": 73, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 17, "edge": "fireworks-inference", "fireworks-inference": 69, "hy4": 52, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Fireworks AI Inference scores 71.8 (BB) on agent readiness against Tencent Hy4's 64 (B), and leads in 5 of 7 scored categories. Tencent Hy4 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.", "hy4": "Tencent's flagship model is on TokenHub as hy4, with a 1M-token context, image understanding, function calling and caching, at ¥6 input and ¥18 output per million tokens, half price until the end of 2026. The weights it is called open source for aren't published yet, and every benchmark is Tencent's own." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/fireworks-inference-vs-hy4", "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-hy4.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/fireworks-inference-vs-hy4.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/fireworks-inference-vs-hy4.min.md" }, "markdown": "Fireworks AI Inference scores 71.8 (BB) on agent readiness against Tencent Hy4's 64 (B), and leads in 5 of 7 scored categories. Tencent Hy4 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- Tencent Hy4: grade B, 64/100, rank #595 of 1524. Markdown https://www.anchorterminal.com/tools/hy4.md · JSON https://www.anchorterminal.com/api/v1/tools/hy4.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 46\n- Schema \u0026 documentation, 93 against 73\n- Security \u0026 auth, 77 against 71\n- Payments \u0026 pricing, 60 against 45\n- Transparency \u0026 trust, 69 against 52\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- A hosted endpoint, with nothing to install\n\nWatch for: Cloud provider outages on 11 August and 14 October hit many serverless models for hours\n\n### Tencent Hy4 (B)\n\nGood for: Long-context agent work, coding and office or finance tasks on a 1M-token context with images, for teams already on Tencent Cloud or happy to verify an account there.\n\nAhead on:\n- Agent ergonomics, 86 against 80\n- Maintenance \u0026 community, 73 against 65\n\nAlso in its favour:\n- No incidents deducted, where Fireworks AI Inference loses 3 points for them\n\nWatch for: Weights, licence and system card are promised but not published; tencent/Hy4 didn't answer on Hugging Face on 11 November\n\n\n## Why the edge\n\n### Reliability: Fireworks AI Inference +24\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- Tencent Hy4 (46): Model reading for hy4 on Tencent Cloud TokenHub. Platform facts are the tencent-tokenhub listing's (checked 1 November), carried over as RULES.md allows for a model on an already graded platform. No public status page (0) and so no incident record to read (5 of 30). Per-model rate limits only in the console and DescribeModelQuota (8 of 15). Six 429 codes, Retry-After and backoff advice (13 of 15). The TokenHub SLA promises 99.5% a month, and Hy4 is Tencent's own model, so the third-party exclusion doesn't apply (10). Released as hy4 on 4 November, a separate id from hy4-preview, with no preview label (10). 0 + 5 + 8 + 13 + 10 + 10 = 46.\n\n### Schema \u0026 documentation: Fireworks AI Inference +20\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- Tencent Hy4 (73): Model reading for hy4 on Tencent Cloud TokenHub. Platform facts are the tencent-tokenhub listing's (checked 1 November), carried over as RULES.md allows for a model on an already graded platform. No OpenAPI file for inference; field pages for the OpenAI and Anthropic formats as TokenHub implements them (12 of 25). llms.txt with Markdown copies (10). The model list, updated 9 November, gives hy4's context, input and output limits and marks thinking, structured output, function calling, caching and image understanding; computer use, which Tencent's release names, isn't marked (13 of 20). Typed field pages (10 of 15). Examples in five languages and an error page of 30 codes (14 of 15). Dated release notes, with hy4 added on 4 November (14 of 15). 12 + 10 + 13 + 10 + 14 + 14 = 73.\n\n### Transparency \u0026 trust: Fireworks AI Inference +17\n\n- Fireworks AI Inference (69): Proprietary service, Apache-2.0 Python SDK. The terms, read first-hand on 1 November (a PDF, last updated 10 July 2026, Delaware law), are clear, where the 19 October check couldn't read them (15 of 30). The data-handling page and section 3.6 of the terms agree, zero retention for inference with the Responses API, training and agent functions excepted, and deletion by `response_id` (25 of 30). Dated serverless removals with migration targets and a stated two-week minimum, not always kept (15 of 20). Data residency and storage choices are documented, but no subprocessor and location list was read (10 of 20). 15+25+15+10 = 65.\n- Tencent Hy4 (52): Model reading for hy4 on Tencent Cloud TokenHub. Platform facts are the tencent-tokenhub listing's (checked 1 November), carried over as RULES.md allows for a model on an already graded platform. Closed service under the TokenHub terms, but Tencent's release headline calls Hy4 open source while the weights and system card are only promised 'in the coming days', with no licence stated, and tencent/Hy4 didn't answer on Hugging Face on 11 November (14 of 30). Terms and FAQ agree inputs aren't used for training; the privacy policy renders only with JavaScript and wasn't read (15 of 30). Dated retirement notices and shutdown fields (13 of 20). Processing generally in mainland China for the China site, Singapore for the international one (13 of 20). Every benchmark in the release is Tencent's own or a partner's. 14 + 15 + 13 + 13 = 55.\n\n### Payments \u0026 pricing: Fireworks AI Inference +15\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- Tencent Hy4 (45): Model reading for hy4 on Tencent Cloud TokenHub. Platform facts are the tencent-tokenhub listing's (checked 1 November), carried over as RULES.md allows for a model on an already graded platform. No machine payment protocol (0). The price page, updated 9 November, lists ¥6 input, ¥0.3 cached and ¥18 output per million tokens, with Hy4 billed at 50% until 31 December 2026 (20). TokenHub's campaign of 1M free tokens per language model, read on 1 November, isn't confirmed for hy4 on the price page, so half (10 of 20, a judgement call). A person signs up with real-name verification (0). 0 + 20 + 10 + 0 = 30. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.\n\n### Maintenance \u0026 community: Tencent Hy4 +8\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- Tencent Hy4 (73): Model reading for hy4 on Tencent Cloud TokenHub. Platform facts are the tencent-tokenhub listing's (checked 1 November), carried over as RULES.md allows for a model on an already graded platform. Added on 4 November 2026 per the release notes; the model list and price page were updated on 9 November (30). Retirement notices of 21 to 33 days, no minimum written (7 of 12). Heavy retirement churn on the platform (3 of 8). Dated release notes and announcements, round-the-clock support (13 of 15). CLI replies not sampled (3 of 10). Control-plane SDKs and CLI, no inference SDK of its own (12 of 15). CLI runtime stated, CI not checked (5 of 10). 30 + 7 + 3 + 13 + 3 + 12 + 5 = 73. The model is a week old, so these lines are TokenHub's habits more than Hy4's record.\n\n### Agent ergonomics: Tencent Hy4 +6\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- Tencent Hy4 (86): Model reading for hy4 on Tencent Cloud TokenHub. Platform facts are the tencent-tokenhub listing's (checked 1 November), carried over as RULES.md allows for a model on an already graded platform. Function calling is marked for hy4 in the model list (18 of 20). Structured output marked (13 of 15). Cache-hit price published, ¥0.3 against ¥6 input (14 of 15). 1M-token context with 960K input and 64K output (15). Batch at half price covered Hy3 and Hy4 preview on 1 November; whether it covers hy4 wasn't re-read (3 of 10). OpenAI and Anthropic SDKs with a changed base URL, plus Tencent Cloud's SDK and CLI for the control plane (8 of 10). Errors with code, messages, upstream status and request ID (15 of 15). 18 + 13 + 14 + 15 + 3 + 8 + 15 = 86.\n\n## Score by category\n\n| Category | Weight | Fireworks AI Inference | Tencent Hy4 | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 70 | 46 | Fireworks AI Inference +24 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 93 | 73 | Fireworks AI Inference +20 |\n| Agent ergonomics | 13% (16.2 this run) | 80 | 86 | Tencent Hy4 +6 |\n| Security \u0026 auth | 14% (17.5 this run) | 77 | 71 | Fireworks AI Inference +6 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 45 | Fireworks AI Inference +15 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 65 | 73 | Tencent Hy4 +8 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 69 | 52 | Fireworks AI Inference +17 |\n| Negative events | ≤15 | -3 | 0 | |\n| **Total** | | **71.8 · BB** | **64 · B** | |\n\n## Facts side by side\n\n| Fact | Fireworks AI Inference | Tencent Hy4 |\n| --- | --- | --- |\n| Kind | HTTP API | Model API |\n| Vendor | Fireworks AI | Tencent (Hy team) |\n| Hosted endpoint | `https://api.fireworks.ai/inference/v1` | no (local only) |\n| Transports | HTTP | 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. | Hosted model under the Tencent Cloud TokenHub terms. Tencent says weights and a system card will follow; no licence is stated yet |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-27 | 2026-11-04 |\n| Terms last updated | couldn't be read | couldn't be read |\n| Privacy policy last updated | no date given | couldn't be read |\n| Customer content may train models | couldn't be read | couldn't be read |\n| Terms restrict automated access | couldn't be read | couldn't be read |\n| Terms restrict benchmarking | couldn't be read | couldn't be read |\n| Terms or service can change without notice | couldn't be read | couldn't be read |\n| Arbitration or class-action waiver | couldn't be read | couldn't be read |\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### Tencent Hy4\n\n- +1.8 on 13 November 2026: checklist\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**Tencent Hy4.** Tencent's flagship model is on TokenHub as hy4, with a 1M-token context, image understanding, function calling and caching, at ¥6 input and ¥18 output per million tokens, half price until the end of 2026. The weights it is called open source for aren't published yet, and every benchmark is Tencent's own.\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### Tencent Hy4\n\n1. Use model id hy4 on TokenHub's OpenAI- or Anthropic-compatible endpoints; hy4-preview is a separate, older model\n2. Keep input under 960K tokens and expect at most 64K output\n3. Reuse prompt prefixes: cached input is ¥0.3 against ¥6\n4. Check the price page for the end of the 50% discount on 31 December 2026 before budgeting\n5. Read rate limits from the console or DescribeModelQuota; the public docs don't give them for chat models\n\n## Questions\n\n### Which is better for AI agents, Fireworks AI Inference or Tencent Hy4?\n\nFireworks AI Inference scores 71.8 (BB) on agent readiness against Tencent Hy4's 64 (B), and leads in 5 of 7 scored categories. Tencent Hy4 leads on agent ergonomics and maintenance \u0026 community.\n\n### Do Fireworks AI Inference and Tencent Hy4 need an API key?\n\nBoth need an API key.\n\n### Can an agent call Fireworks AI Inference and Tencent Hy4 without installing anything?\n\nFireworks AI Inference has a hosted endpoint at https://api.fireworks.ai/inference/v1. No hosted endpoint is listed for Tencent Hy4.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/fireworks-inference-vs-hy4.json, and with the fewest tokens: https://www.anchorterminal.com/compare/fireworks-inference-vs-hy4.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"fireworks-inference\", \"b\": \"hy4\"}`. From a terminal: `anchor compare fireworks-inference hy4`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/fireworks-inference.json and https://www.anchorterminal.com/api/v1/tools/hy4.json\n\n## Other comparisons with Fireworks AI Inference or Tencent Hy4\n\n- [Amazon Bedrock vs Fireworks AI Inference](https://www.anchorterminal.com/compare/amazon-bedrock-vs-fireworks-inference.md)\n- [Amazon Bedrock vs Tencent Hy4](https://www.anchorterminal.com/compare/amazon-bedrock-vs-hy4.md)\n- [Claude API vs Fireworks AI Inference](https://www.anchorterminal.com/compare/anthropic-api-vs-fireworks-inference.md)\n- [Claude API vs Tencent Hy4](https://www.anchorterminal.com/compare/anthropic-api-vs-hy4.md)\n- [Antseed vs Fireworks AI Inference](https://www.anchorterminal.com/compare/antseed-vs-fireworks-inference.md)\n- [Antseed vs Tencent Hy4](https://www.anchorterminal.com/compare/antseed-vs-hy4.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 Tencent Hy4](https://www.anchorterminal.com/compare/azure-openai-vs-hy4.md)\n- [BlockRun.AI vs Fireworks AI Inference](https://www.anchorterminal.com/compare/blockrun-ai-vs-fireworks-inference.md)\n- [BlockRun.AI vs Tencent Hy4](https://www.anchorterminal.com/compare/blockrun-ai-vs-hy4.md)\n- [Cerebras Inference vs Fireworks AI Inference](https://www.anchorterminal.com/compare/cerebras-inference-vs-fireworks-inference.md)\n- [Cerebras Inference vs Tencent Hy4](https://www.anchorterminal.com/compare/cerebras-inference-vs-hy4.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 Tencent Hy4](https://www.anchorterminal.com/compare/claude-fable-5-2-vs-hy4.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 Tencent Hy4](https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-hy4.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 Tencent Hy4](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-hy4.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 Tencent Hy4](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-hy4.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 Tencent Hy4](https://www.anchorterminal.com/compare/cohere-chat-vs-hy4.md)\n- [DeepInfra vs Fireworks AI Inference](https://www.anchorterminal.com/compare/deepinfra-vs-fireworks-inference.md)\n- [DeepInfra vs Tencent Hy4](https://www.anchorterminal.com/compare/deepinfra-vs-hy4.md)\n- [DeepSeek API vs Fireworks AI Inference](https://www.anchorterminal.com/compare/deepseek-api-vs-fireworks-inference.md)\n- [DeepSeek API vs Tencent Hy4](https://www.anchorterminal.com/compare/deepseek-api-vs-hy4.md)\n- [Eden AI vs Fireworks AI Inference](https://www.anchorterminal.com/compare/eden-ai-vs-fireworks-inference.md)\n- [Eden AI vs Tencent Hy4](https://www.anchorterminal.com/compare/eden-ai-vs-hy4.md)\n- [Glimpse vs Fireworks AI Inference](https://www.anchorterminal.com/compare/elorian-glimpse-vs-fireworks-inference.md)\n- [Glimpse vs Tencent Hy4](https://www.anchorterminal.com/compare/elorian-glimpse-vs-hy4.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 4 Hydrogen](https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-4-hydrogen.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 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 Tencent Hy4](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-hy4.md)\n- [Gemini 4 Hydrogen vs Tencent Hy4](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-hy4.md)\n- [Gemini Developer API vs Tencent Hy4](https://www.anchorterminal.com/compare/gemini-api-vs-hy4.md)\n- [GroqCloud vs Tencent Hy4](https://www.anchorterminal.com/compare/groq-vs-hy4.md)\n- [Hugging Face Inference Providers vs Tencent Hy4](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-hy4.md)\n- [Tencent Hy4 vs Jais 3](https://www.anchorterminal.com/compare/hy4-vs-jais-3.md)\n- [Tencent Hy4 vs Meta Model API](https://www.anchorterminal.com/compare/hy4-vs-meta-model-api.md)\n- [Tencent Hy4 vs MiniMax API](https://www.anchorterminal.com/compare/hy4-vs-minimax-api.md)\n- [Tencent Hy4 vs Mistral AI API](https://www.anchorterminal.com/compare/hy4-vs-mistral-api.md)\n- [Tencent Hy4 vs Muse Ember](https://www.anchorterminal.com/compare/hy4-vs-muse-ember.md)\n- [Tencent Hy4 vs Muse Spark Open](https://www.anchorterminal.com/compare/hy4-vs-muse-spark-open.md)\n- [Tencent Hy4 vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/hy4-vs-nemotron-3-5-super-vl.md)\n- [Tencent Hy4 vs Novita AI](https://www.anchorterminal.com/compare/hy4-vs-novita-ai.md)\n- [Tencent Hy4 vs OpenAI API](https://www.anchorterminal.com/compare/hy4-vs-openai-api.md)\n- [Tencent Hy4 vs OpenRouter](https://www.anchorterminal.com/compare/hy4-vs-openrouter.md)\n- [Tencent Hy4 vs Prism Inference](https://www.anchorterminal.com/compare/hy4-vs-prism-inference.md)\n- [Tencent Hy4 vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/hy4-vs-ramp-router.md)\n- [Tencent Hy4 vs Beam 1.0](https://www.anchorterminal.com/compare/hy4-vs-reflection-beam.md)\n- [Tencent Hy4 vs RouterPlus](https://www.anchorterminal.com/compare/hy4-vs-routerplus.md)\n- [Tencent Hy4 vs SambaCloud](https://www.anchorterminal.com/compare/hy4-vs-sambanova.md)\n- [Tencent Hy4 vs SiliconFlow](https://www.anchorterminal.com/compare/hy4-vs-siliconflow.md)\n- [Tencent Hy4 vs Simplismart](https://www.anchorterminal.com/compare/hy4-vs-simplismart.md)\n- [Tencent Hy4 vs StepFun API](https://www.anchorterminal.com/compare/hy4-vs-stepfun-api.md)\n- [Tencent Hy4 vs SWE-2 Flash](https://www.anchorterminal.com/compare/hy4-vs-swe-2-flash.md)\n- [Tencent Hy4 vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/hy4-vs-tencent-tokenhub.md)\n- [Tencent Hy4 vs Together AI Inference](https://www.anchorterminal.com/compare/hy4-vs-together-inference.md)\n- [Tencent Hy4 vs Vercel AI Gateway](https://www.anchorterminal.com/compare/hy4-vs-vercel-ai-gateway.md)\n- [Tencent Hy4 vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/hy4-vs-vertex-ai.md)\n- [Tencent Hy4 vs xAI API (Grok)](https://www.anchorterminal.com/compare/hy4-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 Tencent Hy4", "url": "" } ], "description": "Fireworks AI Inference scores 71.8 (BB) to Tencent Hy4's 64 (B) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Fireworks AI Inference BB 71.8", "Tencent Hy4 B 64", "scores" ], "h1": "Fireworks AI Inference vs Tencent Hy4", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/fireworks-inference-vs-hy4", "published": "2026-10-01", "section": "tools", "title": "Fireworks AI Inference vs Tencent Hy4 for AI agents (2026)", "toc": null, "updated": "2026-11-13", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-hy4" }, "tokens": { "markdown": 6900, "slim": 1030 }, "version": 1 }