{"jtbd":{"id":"open-model-inference","slug":"open-model-inference","name":"Hosted open-weight model inference","shortName":"Hosted open-weight model inference","problemStatement":"Run Llama/Qwen/DeepSeek/etc. without owning GPUs, with production DX."},"pick":{"id":"fireworks","slug":"fireworks","name":"Fireworks AI","tagline":"Top pick for production open-model serving with real DX. Prefer over random GPU DIY when you want tokens not…","website":"https://fireworks.ai","overall":8.35,"scoreBand":{"low":7.7,"mid":8.3,"high":8.9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.7–8.9 (editorial prior)"},"scoreLayers":{"editorialPrior":8.35,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"Serverless per-token + on-demand GPU; day-0 OSS model support; post-training stack. Free credits often available.","scores":{"capabilityFit":8.6,"pricePerformance":8.8,"latencyReliability":8.4,"developerDx":9,"privacyPosture":7.5,"lockInRisk":3.5,"maturity":8,"overall":8.35,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},"runnersUp":[{"id":"together","slug":"together","name":"Together AI","tagline":"Best catalog breadth for OSS models. Watch minimums and lifetime spend gates before you design around a gated…","website":"https://www.together.ai","overall":8.2,"scoreBand":{"low":7.6,"mid":8.2,"high":8.8,"halfWidth":0.6,"basis":"editorial_prior","display":"7.6–8.8 (editorial prior)"},"scoreLayers":{"editorialPrior":8.2,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-09-14: Open-model inference + fine-tune on one OpenAI-compatible API; competitive per-token rates (often ~$0.15–$0.90/MTok class depending on model). Strong for Llama/Qwen/DeepSeek families; Dedicated endpoints available.","scores":{"capabilityFit":8.5,"pricePerformance":9,"latencyReliability":8,"developerDx":8.4,"privacyPosture":7.2,"lockInRisk":3.5,"maturity":8.2,"overall":8.2,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"groq","slug":"groq","name":"Groq","tagline":"Use when latency is the product. Do not build your whole company on one Groq model SKU — they rotate.","website":"https://groq.com","overall":7.95,"scoreBand":{"low":7.4,"mid":8,"high":8.6,"halfWidth":0.6,"basis":"editorial_prior","display":"7.4–8.6 (editorial prior)"},"scoreLayers":{"editorialPrior":7.95,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"Per-token with free tier; LPU inference; narrow production model set (Llama/Qwen/GPT-OSS etc.); batch discounts. Llama Guard 4 12B (model id meta-llama/llama-guard-4-12b) is still documented at console.groq.com/docs/model/meta-llama/llama-guard-4-12b as an open safety classifier; its per-token price figure was removed because it couldn't be re-sourced on 2026-10-21 (no price on that page or on console.groq.com/docs/models as of 2026-10-21). See the stored rows for sourced Groq prices, including the Llama Prompt Guard 2 classifiers.","scores":{"capabilityFit":7.8,"pricePerformance":9,"latencyReliability":8.2,"developerDx":8.8,"privacyPosture":7,"lockInRisk":5,"maturity":7.8,"overall":7.95,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"deepinfra","slug":"deepinfra","name":"DeepInfra","tagline":"Budget open-model workhorse and one of the cheapest large-catalog hosts. Great for evals and high-volume…","website":"https://deepinfra.com","overall":7.95,"scoreBand":{"low":7.4,"mid":8,"high":8.6,"halfWidth":0.6,"basis":"editorial_prior","display":"7.4–8.6 (editorial prior)"},"scoreLayers":{"editorialPrior":7.95,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-09-14: Broad OpenAI-compatible catalog with model-specific token rates (e.g. Llama-3.3-70B Turbo $0.10/$0.32 per 1M in/out; DeepSeek-V4-Flash input $0.09, cached input $0.018 and output $0.18 per 1M (deepinfra.com/pricing as of 2026-10-21; not stored as rows); embeddings from $0.005/MTok). Dedicated GPU rentals (deepinfra.com/pricing, re-checked 2026-10-20): A100 80GB $1.49/GPU-hr, H100 $2.90, H200 $3.49, B200 $4.89, B300 $5.89. Standard/Priority(1.5x)/Flex(0.8x) tiers. No long-term contracts.","scores":{"capabilityFit":8,"pricePerformance":9.4,"latencyReliability":7.5,"developerDx":8.5,"privacyPosture":6.5,"lockInRisk":3,"maturity":7.2,"overall":7.95,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"huggingface-inference","slug":"huggingface-inference","name":"Hugging Face Inference","tagline":"Perfect for Hub-native workflows and custom models. For hard production latency, graduate to…","website":"https://endpoints.huggingface.co","overall":7.95,"scoreBand":{"low":7.4,"mid":8,"high":8.6,"halfWidth":0.6,"basis":"editorial_prior","display":"7.4–8.6 (editorial prior)"},"scoreLayers":{"editorialPrior":7.95,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"Inference Providers (pay-as-you-go access to partner inference providers plus Hugging Face's own hf-inference provider) + dedicated Inference Endpoints ('Pay for what you use, per minute' per https://endpoints.huggingface.co, fetched 2026-10-25; instance rates are the price rows: single-GPU x1 rows per GPU-hour, multi-GPU x2/x4/x8 rows per instance-hour (usd_per_instance_hour since v0.12.138, re-checked 2026-10-27 on https://huggingface.co/docs/inference-endpoints/pricing), never divided per GPU). The 'Serverless Inference API' name is retired: https://huggingface.co/docs/inference-providers/pricing (fetched 2026-10-25) says hf-inference 'used to be called “Inference API (serverless)” prior to Inference Providers' and 'just pay for what you use, with no markup from Hugging Face.' Monthly credits: 'Free Users None - yes (credits purchase required)'; PRO users and Team/Enterprise organizations get included monthly credits. Hub-centric. No price changed here; any price change goes through the reviewed --catalog step.","scores":{"capabilityFit":8.4,"pricePerformance":7.2,"latencyReliability":7.4,"developerDx":8.6,"privacyPosture":7.8,"lockInRisk":3.5,"maturity":9.2,"overall":7.95,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"chutes","slug":"chutes","name":"Chutes","tagline":"Budget open-model overflow with a now-pinned public TEE matrix. Depot open-model production pick stays…","website":"https://chutes.ai","overall":7.29,"scoreBand":{"low":6.7,"mid":7.3,"high":7.9,"halfWidth":0.6,"basis":"editorial_prior","display":"6.7–7.9 (editorial prior)"},"scoreLayers":{"editorialPrior":7.29,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-10-27 (chutes.ai/pricing, fetched twice 2026-10-27): Public TEE inference PAYG per 1M tokens, input/output (the page says per-model rates are 'pulled live from our pricing API'): gemma-4-31B-turbo $0.12/$0.37; Qwen3.8-27B $0.039/$1.25; Qwen3.6-27B $0.25/$2.00; DeepSeek-V4-Flash-0731 $0.44/$1.32; Kimi K2.6 $0.39/$1.80; Qwen 3.5 (397B-A17B) $0.45/$3.00; DeepSeek-V3.2 $1.00/$1.00; GLM-5.1 $0.90/$2.90; GLM-5.2 $1.25/$3.95; Kimi-K3 $1.85/$9.50 (cached-input rates also on page, not stored). Mistral-Nemo, Nemotron-3-Nano-Omni-30B, Qwen3-32B and Qwen3-235B-A22B-Thinking-2507 are no longer on the page (re-checked 2026-10-27; stored rows kept at their 2026-10-03 amounts, marked unverified, never ranked). Private Chute self-serve TEE GPU RTX Pro 6000 96 GB $1.80/hr + one-time deploy fee 3× hourly ($5.40). Page FAQ: 'Monthly plans are no longer sold on chutes.ai' (stored Plus $10 and Pro $20 rows kept from 2026-10-03, marked unverified, never ranked); no free tier. Matrix moves — re-curl before commits.","scores":{"capabilityFit":7.4,"pricePerformance":9.2,"latencyReliability":6.8,"developerDx":7.6,"privacyPosture":5.8,"lockInRisk":4,"maturity":6.2,"overall":7.29,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"friendli","slug":"friendli","name":"FriendliAI","tagline":"Open-model production peer when latency/tool-calling matter. Fireworks remains depot open-model default…","website":"https://friendli.ai","overall":8.03,"scoreBand":{"low":7.4,"mid":8,"high":8.6,"halfWidth":0.6,"basis":"editorial_prior","display":"7.4–8.6 (editorial prior)"},"scoreLayers":{"editorialPrior":8.03,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-10-01","pricingNotes":"As of 2026-10-01 (friendli.ai/pricing live): Dedicated Endpoints on-demand step-up **is live** — A100 **$4.0**/hr, H100 **$5.0**/hr, H200 **$7.0**/hr, B200 **$9.0**/hr, B300 $12.0/hr (was through-Sep-30: A100 $2.9, H100 $3.9, H200 $4.5, B200 $8.9, B300 $12.0). Billed per second; no idle/startup charge. Model API token examples on page (GLM/DeepSeek/MiniMax/whisper). SOC2 + HIPAA.","scores":{"capabilityFit":8.4,"pricePerformance":8,"latencyReliability":8.4,"developerDx":8.2,"privacyPosture":8.2,"lockInRisk":4,"maturity":7.6,"overall":8.03,"kind":"curated_estimate","confidence":"high","asOf":"2026-10-01"}}],"scoreBand":{"low":7.7,"mid":8.3,"high":8.9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.7–8.9 (editorial prior)"},"scoreLayers":{"editorialPrior":8.35,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"whyPickOverHigherScore":{"pickId":"fireworks","pickName":"Fireworks AI","pickScore":8.35,"highestScoredCandidateId":"fireworks","highestScoredCandidateName":"Fireworks AI","highestScore":8.35,"pickHasLowerCompositeScore":false,"delta":0,"pickLeadsOnDimensions":[],"explanation":"Fireworks AI (8.35) holds both the highest composite score among ranked candidates and the editorial pick for Hosted open-weight model inference: Catalog freshness, tokens/sec, OpenAI-compat DX, and pricePerf."},"cheapest":{"providerId":"chutes","providerName":"Chutes","skuId":"chutes-qwen3-8-27b-qwen-qwen3-8-27b-tee-in","item":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE)","plan":"Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE) — Public TEE inference, USD per 1M tokens","unit":"usd_per_million_input_tokens","amountUsd":0.039,"isFloorPrice":true,"floorWarning":"Provider-wide floor SKU; may not be the flagship model scored for this JTBD.","skuCountInUnit":10,"isDepotPick":false,"sourceUrl":"https://chutes.ai/pricing","asOf":"2026-10-27","verifiedAsOf":"2026-10-27"},"recommendedWorkloadQuote":{"providerId":"fireworks","providerName":"Fireworks AI","skuId":"fireworks-embed-to-150m","item":"Embeddings up to 150M params","plan":"Embeddings up to 150M params — parameter-count bucket, not a named chat model","unit":"usd_per_million_input_tokens","amountUsd":0.008,"outputSkuId":null,"outputItem":null,"outputAmountUsd":null,"outputUnit":null,"sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-03","pricingLastVerifiedAt":"2026-10-03","isFlagshipForJob":false,"differsFromFloorCheapest":false,"representativeQuote":{"skuId":"fireworks-embed-to-150m","item":"Embeddings up to 150M params","plan":"Embeddings up to 150M params — parameter-count bucket, not a named chat model","amountUsd":0.008,"inputOrUnitUsd":0.008,"unit":"usd_per_million_input_tokens","outputUsd":null,"outputUnit":null,"sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-03"},"estimatedTaskCost":{"tasks":1000,"retryAndToolOverheadMultiplier":1.15,"retryToolOverheadMultiplier":1.15,"inputTokensPerTask":4000,"outputTokensPerTask":0,"baseCostPer1kTasksUsd":0.032,"totalUsd":0.0368,"estimatedTotalUsd":0.0368,"perTaskUsd":0.000037,"estimatedCostPerTaskUsd":0.000037,"formula":"((4,000 tokens * $0.008/1M) * 1,000 tasks) * 1.15 overhead","assumptions":"1,000 agent tasks @ 4k input + 1k output tokens/task with 1.15x retry/tool-call overhead."}},"representativeQuote":{"skuId":"fireworks-embed-to-150m","item":"Embeddings up to 150M params","plan":"Embeddings up to 150M params — parameter-count bucket, not a named chat model","amountUsd":0.008,"inputOrUnitUsd":0.008,"unit":"usd_per_million_input_tokens","outputUsd":null,"outputUnit":null,"sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-03"},"estimatedTaskCost":{"tasks":1000,"retryAndToolOverheadMultiplier":1.15,"retryToolOverheadMultiplier":1.15,"inputTokensPerTask":4000,"outputTokensPerTask":0,"baseCostPer1kTasksUsd":0.032,"totalUsd":0.0368,"estimatedTotalUsd":0.0368,"perTaskUsd":0.000037,"estimatedCostPerTaskUsd":0.000037,"formula":"((4,000 tokens * $0.008/1M) * 1,000 tasks) * 1.15 overhead","assumptions":"1,000 agent tasks @ 4k input + 1k output tokens/task with 1.15x retry/tool-call overhead."},"freeAlternatives":[{"id":"deepseek-r1-weights","name":"DeepSeek-R1 weights","kind":"open_weights","jtbdIds":["open-model-inference"],"whatYouGet":"Downloadable DeepSeek-R1 weights.","cost":"oss","license":"MIT","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-R1/raw/main/LICENSE","notes":"LICENSE file fetched 2026-10-03 is the MIT License. This is DeepSeek-R1, not DeepSeek-V3. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical): 'MIT License'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"open_weights","substitutable":true},{"id":"deepseek-v3.2-weights","name":"DeepSeek-V3.2 weights","kind":"open_weights","jtbdIds":["open-model-inference","budget-open-inference"],"whatYouGet":"Downloadable DeepSeek-V3.2 weights from the Hugging Face repo whose LICENSE file is MIT.","cost":"oss","license":"MIT","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2/raw/main/LICENSE","notes":"This is DeepSeek-V3.2, not DeepSeek-V3. V3 used a separate LICENSE-MODEL and is not indexed here. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical): 'MIT License'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"open_weights","substitutable":true},{"id":"exo","name":"exo","kind":"local_runtime","jtbdIds":["open-model-inference","on-device-edge-batch"],"whatYouGet":"Open-source runtime for running models across your own machines.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://raw.githubusercontent.com/exo-explore/exo/main/LICENSE","notes":"LICENSE fetched 2026-10-03 is Apache License 2.0. Re-fetched twice 2026-10-25 (~10 s apart, plain curl, no login): HTTP 200, byte-identical: 'Apache License Version 2.0, January 2004'. License unchanged.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"local_runtime","substitutable":true},{"id":"gemma-terms-of-use","name":"Gemma models under the Gemma Terms of Use","kind":"open_weights","providerId":"google-ai","jtbdIds":["open-model-inference","wasm-edge-small-models"],"whatYouGet":"Gemma models listed in the Appendix of the Gemma Terms of Use page (for example Gemma 1, 1.1, 2, 3 and 3n, FunctionGemma, EmbeddingGemma, PaliGemma, ShieldGemma, CodeGemma, RecurrentGemma, T5Gemma, VaultGemma and TranslateGemma), usable under that license with its Section 3.2 use restrictions. Gemma 4 is not covered by these terms.","cost":"free","license":"Gemma Terms of Use","sourceUrl":"https://ai.google.dev/gemma/terms","notes":"Terms page fetched twice 2026-10-24 (identical text; 'Last modified: April 1, 2026', footer 'Last updated 2026-04-01 UTC'): 'The terms below apply to Gemma models listed in the Appendix at bottom of this page.' and 'For Gemma 4 terms, see the Gemma 4 license'. That link points to https://ai.google.dev/gemma/apache_2, a page titled 'Apache License 2.0' (fetched twice 2026-10-24); Gemma 4 is not indexed in this row. Section 3.2: 'You must not use any of the Gemma Services: for the restricted uses set forth in the Gemma Prohibited Use Policy'. The page now also says 'This documentation is deprecated. Please visit the new documentation at gemma.ai'; the terms are still served at this URL (HTTP 200, no redirect). Download path is https://ai.google.dev/gemma/docs/get_started: 'You can download official Google Gemma model variants and community-created variants from Kaggle Models and Hugging Face'. Re-checked 2026-10-26 (v0.12.131): stored quotes still match. https://ai.google.dev/gemma/terms, https://ai.google.dev/gemma/apache_2 and https://ai.google.dev/gemma/docs/get_started were each fetched twice (~10 s apart, plain curl, no login, following redirects): HTTP 200, no redirect, HTML differs only inside inline scripts, tag-stripped text identical; the terms page still reads 'Last modified: April 1, 2026' and 'Last updated 2026-04-01 UTC'. Every quote above string-matched the whitespace-normalized text; license and values unchanged (Depot data decision to re-date only, approvalRef 'Ethan delegation 2026-10-21 19:41 ET t55u', decidedBy Agent Depo).","limits":null,"asOf":"2026-10-26","freeType":"open_weights","substitutable":true},{"id":"glm-4-9b-chat","name":"GLM-4-9B-Chat","kind":"open_weights","jtbdIds":["open-model-inference"],"whatYouGet":"Downloadable GLM-4-9B-Chat weights under the glm-4-9b license. Academic use is stated as free. Commercial use requires registration.","cost":"free","license":"glm-4-9b License","sourceUrl":"https://huggingface.co/zai-org/glm-4-9b-chat/raw/main/LICENSE","notes":"LICENSE fetched 2026-10-03 grants royalty-free academic research and says commercial use requires registration at open.bigmodel.cn, after which commercial use is described as free. Not Apache. Military and illegal uses are prohibited in the same text. Re-fetched twice 2026-10-25: https://huggingface.co/THUDM/glm-4-9b-chat/raw/main/LICENSE now answers HTTP 307 to /zai-org/glm-4-9b-chat/raw/main/LICENSE (HTTP 200, byte-identical), so sourceUrl moved to the redirect target. Text still says 'The glm-4-9b License', 'For users who wish to use the models for commercial purposes, please do so [here](https://open.bigmodel.cn/mla/form)' and 'Registered users are free to use this model for commercial activities'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"open_weights","substitutable":true},{"id":"gpt-oss-20b","name":"gpt-oss-20b","kind":"open_weights","jtbdIds":["open-model-inference","budget-open-inference"],"whatYouGet":"Downloadable OpenAI gpt-oss-20b weights.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://huggingface.co/openai/gpt-oss-20b/raw/main/LICENSE","notes":"LICENSE file fetched 2026-10-03 is Apache License 2.0. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical): 'Apache License Version 2.0, January 2004'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"open_weights","substitutable":true},{"id":"granite-3-1-8b-instruct","name":"Granite-3.1-8B-Instruct","kind":"open_weights","jtbdIds":["open-model-inference"],"whatYouGet":"Downloadable IBM Granite 3.1 8B Instruct weights.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://huggingface.co/ibm-granite/granite-3.1-8b-instruct/raw/main/README.md","notes":"Model card fetched 2026-10-03 says license: apache-2.0 and links the Apache 2.0 text. A separate LICENSE file was 404. README re-fetched twice 2026-10-25 (HTTP 200, byte-identical): front matter 'license: apache-2.0' and '- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)'; raw/main/LICENSE still 404 (twice).","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"open_weights","substitutable":true},{"id":"groq-free-plan-chat","name":"Groq Free Plan chat models","kind":"free_inference","providerId":"groq","jtbdIds":["cheap-volume-llm","ultra-low-latency","open-model-inference"],"whatYouGet":"Organization-level Free Plan rate limits for the chat and classifier model ids in the page payload key freeRows. Not the Developer plan table.","cost":"free","limits":{"scope":"organization","models":{"openai/gpt-oss-120b":{"rpm":30,"rpd":1000,"tpm":8000,"tpd":200000},"openai/gpt-oss-20b":{"rpm":30,"rpd":1000,"tpm":8000,"tpd":200000},"openai/gpt-oss-safeguard-20b":{"rpm":3,"rpd":1000,"tpm":2000,"tpd":200000},"qwen/qwen3.8-27b":{"rpm":30,"rpd":1000,"tpm":8000,"tpd":200000},"meta-llama/llama-prompt-guard-2-22m":{"rpm":30,"rpd":14400,"tpm":15000,"tpd":500000},"meta-llama/llama-prompt-guard-2-86m":{"rpm":30,"rpd":14400,"tpm":15000,"tpd":500000}}},"sourceUrl":"https://console.groq.com/docs/rate-limits","notes":"Rate-limits page fetched twice 2026-10-24 about 10 s apart (identical HTML; the page shows no last-updated date). Parsed from the HTML payload key freeRows (the 'Free Plan Limits' tab), which is separate from devRows (Developer plan, not stored). K suffixes expanded (1K=1000, 2K=2000, 14.4K=14400). The page says: 'The following is a high level summary and there may be exceptions to these limits.' and 'You can view the current, exact rate limits for your organization on the limits page in your account settings.' 'Rate limits apply at the organization level, not individual users.' 'Cached tokens do not count towards your rate limits.' The page also says 'some organizations are also subject to separate per-minute limits on input tokens (ITPM) and output tokens (OTPM)'; no ITPM/OTPM values are published, so none are stored. Change on 2026-10-24: freeRows now reads 'openai/gpt-oss-safeguard-20b 3 1K 2K 200K' (RPM 3, TPM 2K); before 0.12.98 this row stored RPM 30 and TPM 8000 for it. The other five model ids and their values are unchanged. No Llama chat model is in freeRows.","license":null,"asOf":"2026-10-24","freeType":"free_inference","substitutable":true},{"id":"huggingface-transformers","name":"Hugging Face Transformers","kind":"dev_tool","jtbdIds":["open-model-inference","finetune"],"whatYouGet":"Model loading and training library. Weights keep their own licenses.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://github.com/huggingface/transformers/blob/main/LICENSE","notes":"Re-fetched twice 2026-10-25 (~10 s apart, plain curl, no login): GitHub blob page HTTP 200, no redirect (page chrome differs between fetches); raw LICENSE fetched twice too, HTTP 200, byte-identical: 'Copyright 2018- The Hugging Face team. All rights reserved.' / 'Apache License Version 2.0, January 2004'. License unchanged.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"dev_tool","substitutable":true},{"id":"llama-cpp","name":"llama.cpp","kind":"local_runtime","jtbdIds":["open-model-inference","budget-open-inference","edge-llm-inference"],"whatYouGet":"C/C++ GGUF inference CLI and server. Weights are not included.","cost":"oss","license":"MIT","sourceUrl":"https://github.com/ggml-org/llama.cpp/blob/master/LICENSE","notes":"LICENSE fetched 2026-10-03, copyright 2023-2026 The ggml authors. Re-fetched twice 2026-10-25 (~10 s apart, plain curl, no login): the GitHub blob page answered HTTP 200 both times (page chrome differs between fetches), so the raw file https://raw.githubusercontent.com/ggml-org/llama.cpp/master/LICENSE was also fetched twice (HTTP 200, byte-identical): 'MIT License' / 'Copyright (c) 2023-2026 The ggml authors'. License unchanged.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"local_runtime","substitutable":true},{"id":"llamafile","name":"llamafile","kind":"local_runtime","jtbdIds":["open-model-inference","on-device-edge-batch"],"whatYouGet":"Mozilla's open-source single-file local LLM runtime.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://raw.githubusercontent.com/Mozilla-Ocho/llamafile/main/LICENSE","notes":"LICENSE fetched 2026-10-03 is Apache License 2.0, copyright 2023 Mozilla Foundation. Re-fetched twice 2026-10-25 (~10 s apart, plain curl, no login): HTTP 200, byte-identical: 'The Apache 2.0 License' / 'Copyright 2023 Mozilla Foundation'. License unchanged.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"local_runtime","substitutable":true},{"id":"mistral-7b-instruct-v0-3","name":"Mistral-7B-Instruct-v0.3","kind":"open_weights","jtbdIds":["open-model-inference","budget-open-inference"],"whatYouGet":"Downloadable Mistral-7B-Instruct-v0.3 weights.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3/raw/main/README.md","notes":"Model card front matter fetched 2026-10-03 says license: apache-2.0. A separate LICENSE file was 404. README re-fetched twice 2026-10-25 (HTTP 200, byte-identical): front matter 'license: apache-2.0'; raw/main/LICENSE still 404 (twice).","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"open_weights","substitutable":true},{"id":"mlx","name":"MLX","kind":"local_runtime","jtbdIds":["on-device-edge-batch","open-model-inference"],"whatYouGet":"Apple's open-source array framework for on-device model inference.","cost":"oss","license":"MIT","sourceUrl":"https://raw.githubusercontent.com/ml-explore/mlx/main/LICENSE","notes":"LICENSE fetched 2026-10-03 is MIT, copyright 2023 Apple Inc. Re-fetched twice 2026-10-25 (~10 s apart, plain curl, no login): HTTP 200, byte-identical: 'MIT License' / 'Copyright © 2023 Apple Inc.'. License unchanged.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"local_runtime","substitutable":true},{"id":"ollama","name":"Ollama","kind":"local_runtime","jtbdIds":["open-model-inference","budget-open-inference"],"whatYouGet":"Local model runner and OpenAI-compatible server. You still supply weights and your own hardware.","cost":"oss","license":"MIT","sourceUrl":"https://github.com/ollama/ollama/blob/main/LICENSE","notes":"Re-fetched twice 2026-10-25 (~10 s apart, plain curl, no login): the GitHub blob page answered HTTP 200 both times (page chrome differs between fetches), so the raw file https://raw.githubusercontent.com/ollama/ollama/main/LICENSE was also fetched twice (HTTP 200, byte-identical): 'MIT License' / 'Copyright (c) Ollama'. License unchanged.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"local_runtime","substitutable":true},{"id":"olmo-2-1124-7b-instruct","name":"OLMo-2-1124-7B-Instruct","kind":"open_weights","jtbdIds":["open-model-inference"],"whatYouGet":"Downloadable Allen Institute OLMo-2 7B Instruct weights.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://huggingface.co/allenai/OLMo-2-1124-7B-Instruct/raw/main/README.md","notes":"Model card front matter fetched 2026-10-03 says license: apache-2.0. A separate LICENSE file was 404. README re-fetched twice 2026-10-25 (HTTP 200, byte-identical): front matter 'license: apache-2.0'; raw/main/LICENSE still 404 (twice).","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"open_weights","substitutable":true},{"id":"phi-4","name":"Phi-4","kind":"open_weights","jtbdIds":["open-model-inference","budget-open-inference"],"whatYouGet":"Downloadable Microsoft Phi-4 weights.","cost":"oss","license":"MIT","sourceUrl":"https://huggingface.co/microsoft/phi-4/raw/main/LICENSE","notes":"LICENSE file fetched 2026-10-03 is the MIT License. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical): 'MIT License'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"open_weights","substitutable":true},{"id":"qwen2-5-coder-7b-instruct","name":"Qwen2.5-Coder-7B-Instruct","kind":"open_weights","jtbdIds":["coding-agent","open-model-inference"],"whatYouGet":"Downloadable Qwen2.5-Coder 7B Instruct weights. This checkpoint only.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct/raw/main/LICENSE","notes":"LICENSE file fetched 2026-10-03 is Apache License 2.0. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical): 'Apache License Version 2.0, January 2004'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"open_weights","substitutable":true},{"id":"qwen2-5-vl-7b-instruct","name":"Qwen2.5-VL-7B-Instruct","kind":"open_weights","jtbdIds":["multimodal","open-model-inference"],"whatYouGet":"Downloadable Qwen2.5-VL 7B Instruct weights for image-text tasks.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct/raw/main/README.md","notes":"Model card front matter fetched 2026-10-03 says license: apache-2.0. The 3B checkpoint uses a different Qwen Research LICENSE and is not this row. README re-fetched twice 2026-10-25 (HTTP 200, byte-identical): front matter 'license: apache-2.0'; raw/main/LICENSE 404 (twice). The 3B README fetched the same day says 'license_name: qwen-research'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"open_weights","substitutable":true},{"id":"qwen3-0.6b-base","name":"Qwen3-0.6B-Base","kind":"open_weights","jtbdIds":["open-model-inference","budget-open-inference"],"whatYouGet":"Downloadable Qwen3 0.6B base weights. This row is this checkpoint only, not every Qwen model.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://huggingface.co/Qwen/Qwen3-0.6B-Base/raw/main/LICENSE","notes":"LICENSE file fetched 2026-10-03 is Apache License 2.0. Weights are the model repo, not this license URL. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical): 'Apache License Version 2.0, January 2004'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"open_weights","substitutable":true},{"id":"qwen3-8b","name":"Qwen3-8B","kind":"open_weights","jtbdIds":["open-model-inference","budget-open-inference"],"whatYouGet":"Downloadable Qwen3-8B weights.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://huggingface.co/Qwen/Qwen3-8B/raw/main/LICENSE","notes":"LICENSE file fetched 2026-10-03 is Apache License 2.0. Not a claim about every Qwen3 checkpoint. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical): 'Apache License Version 2.0, January 2004'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"open_weights","substitutable":true},{"id":"sglang","name":"SGLang","kind":"local_runtime","jtbdIds":["open-model-inference","budget-open-inference"],"whatYouGet":"Open-source serving runtime for LLMs.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://raw.githubusercontent.com/sgl-project/sglang/main/LICENSE","notes":"LICENSE fetched 2026-10-03 is Apache License 2.0. Re-fetched twice 2026-10-25 (~10 s apart, plain curl, no login): HTTP 200, byte-identical: 'Apache License Version 2.0, January 2004'. License unchanged.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"local_runtime","substitutable":true},{"id":"smollm2-1-7b-instruct","name":"SmolLM2-1.7B-Instruct","kind":"open_weights","jtbdIds":["open-model-inference","budget-open-inference","on-device-edge-batch"],"whatYouGet":"Downloadable SmolLM2 1.7B Instruct weights.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct/raw/main/README.md","notes":"Model card front matter fetched 2026-10-03 says license: apache-2.0. A separate LICENSE file was not in the repo (404). README re-fetched twice 2026-10-25 (HTTP 200, byte-identical): front matter 'license: apache-2.0'; raw/main/LICENSE still 404 (twice).","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"open_weights","substitutable":true},{"id":"vllm","name":"vLLM","kind":"local_runtime","jtbdIds":["production-inference-fleet","open-model-inference"],"whatYouGet":"Self-hosted GPU inference server with an OpenAI-compatible API. GPU time is your own.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://github.com/vllm-project/vllm/blob/main/LICENSE","notes":"Re-fetched twice 2026-10-25 (~10 s apart, plain curl, no login): the GitHub blob page answered HTTP 200 both times (page chrome differs between fetches), so the raw file https://raw.githubusercontent.com/vllm-project/vllm/main/LICENSE was also fetched twice (HTTP 200, byte-identical): 'Apache License Version 2.0, January 2004'. License unchanged.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"local_runtime","substitutable":true}],"referenceDocs":[],"falsification":{"jtbdId":"open-model-inference","jtbdName":"Hosted open-weight model inference","currentPickId":"fireworks","currentPickScore":8.35,"challengerId":"together","challengerScore":8.2,"currentScoreGap":0.15,"minVerifiedOutcomes":10,"requiredOutcomeMargin":0.3,"requiredSuccessRateDelta":0.15,"maxPickPriceIncreasePct":25,"whatWouldChangePick":["Together AI (together) outperforms Fireworks AI (fireworks) by >= 0.3 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on Fireworks AI's representative SKU for open-model-inference without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=fireworks) or sustained >= 30% degraded/failed rate in verified production outcomes."],"frozenHoldoutPolicy":{"holdoutSplit":"20% frozen benchmark holdout tasks + 80% live production outcome receipts","requireCountersignReceipt":true,"requiredEvidenceTiers":["outcome_verified","reference_checked"],"minDistinctContributors":2,"antiGamingRule":"Unverified self-reports and seed/editorial rows never mutate picks or scores."},"triggers":[{"kind":"verified_outcomes_outperformance","challengerId":"together","minVerifiedOutcomes":10,"requiredOutcomeMargin":0.3,"requiredWorkedRateDelta":0.15},{"kind":"verified_price_increase","providerId":"fireworks","maxPriceIncreasePct":25},{"kind":"live_rail_exhaustion_or_degradation","providerId":"fireworks","immediateOverrideUrl":"/api/decide?jtbd=open-model-inference&exhausted=fireworks"}],"submissionSpec":{"falsifyEndpoint":"/api/falsify?jtbd=open-model-inference","outcomesEndpoint":"POST /api/feedback","correctionsEndpoint":"POST /api/corrections","payloadTemplate":{"agentIdentity":"agent:<your-agent-id>","jtbdId":"open-model-inference","providerId":"together","outcome":"worked","detail":"Comparative production evaluation on open-model-inference (n>=10 tasks) with Countersign receipt.","confidence":"high","receipt":{"countersign":{"claim_id":"cs-00000000","status":"verified","evidence_tier":"outcome_verified","counts_as_verified":true}}}}},"whatWouldChangePick":["Together AI (together) outperforms Fireworks AI (fireworks) by >= 0.3 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on Fireworks AI's representative SKU for open-model-inference without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=fireworks) or sustained >= 30% degraded/failed rate in verified production outcomes."],"routePlan":{"jtbdId":"open-model-inference","primary":{"providerId":"fireworks","name":"Fireworks AI","overall":8.35,"scoreBand":{"low":7.7,"mid":8.3,"high":8.9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.7–8.9 (editorial prior)"},"scoreLayers":{"editorialPrior":8.35,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"primary","reason":"Editorial Depot Pick for Hosted open-weight model inference; healthy/eligible under caller constraints."},"fallback":[{"providerId":"together","name":"Together AI","overall":8.2,"scoreBand":{"low":7.6,"mid":8.2,"high":8.8,"halfWidth":0.6,"basis":"editorial_prior","display":"7.6–8.8 (editorial prior)"},"scoreLayers":{"editorialPrior":8.2,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Hosted open-weight model inference."},{"providerId":"groq","name":"Groq","overall":7.95,"scoreBand":{"low":7.4,"mid":8,"high":8.6,"halfWidth":0.6,"basis":"editorial_prior","display":"7.4–8.6 (editorial prior)"},"scoreLayers":{"editorialPrior":7.95,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Hosted open-weight model inference."},{"providerId":"deepinfra","name":"DeepInfra","overall":7.95,"scoreBand":{"low":7.4,"mid":8,"high":8.6,"halfWidth":0.6,"basis":"editorial_prior","display":"7.4–8.6 (editorial prior)"},"scoreLayers":{"editorialPrior":7.95,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Hosted open-weight model inference."},{"providerId":"huggingface-inference","name":"Hugging Face Inference","overall":7.95,"scoreBand":{"low":7.4,"mid":8,"high":8.6,"halfWidth":0.6,"basis":"editorial_prior","display":"7.4–8.6 (editorial prior)"},"scoreLayers":{"editorialPrior":7.95,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Hosted open-weight model inference."},{"providerId":"chutes","name":"Chutes","overall":7.29,"scoreBand":{"low":6.7,"mid":7.3,"high":7.9,"halfWidth":0.6,"basis":"editorial_prior","display":"6.7–7.9 (editorial prior)"},"scoreLayers":{"editorialPrior":7.29,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Hosted open-weight model inference."},{"providerId":"friendli","name":"FriendliAI","overall":8.03,"scoreBand":{"low":7.4,"mid":8,"high":8.6,"halfWidth":0.6,"basis":"editorial_prior","display":"7.4–8.6 (editorial prior)"},"scoreLayers":{"editorialPrior":8.03,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-10-01","role":"fallback","reason":"Ranked fallback route for Hosted open-weight model inference."}],"disqualified":[],"expectedRegret":{"scoreDeltaVsUnconstrainedPick":0,"unconstrainedPickId":"fireworks","activePrimaryId":"fireworks","summary":"0.00 score regret: unconstrained editorial pick satisfies all caller constraints."},"evidenceAgeDays":{"editorialScoreAgeDays":43,"pricingVerifiedAgeDays":0,"editorialPriorAsOf":"2026-09-14","pricingLastVerifiedAt":"2026-10-27"},"confidenceBand":{"low":7.7,"mid":8.3,"high":8.9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.7–8.9 (editorial prior)"},"constraintsApplied":false,"constraintBundle":{"task":null,"jtbd":"open-model-inference","quotaExhausted":[],"degraded":[],"healthy":[],"budgetUsd":null,"maxLatencyMs":null,"region":null,"privacy":null,"exit":[],"existing":[]}},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","tie":false,"scoreGap":0.15,"decidingFactor":null,"tieNote":null,"rationale":"Catalog freshness, tokens/sec, OpenAI-compat DX, and pricePerf.","whenNotTopPick":"Need Hub-native custom model endpoints (HF) or ultra-low latency on narrow SKUs (Groq).","skipTopPick":false,"skipReason":null,"matchedConstraints":[],"pricingSummary":"Serverless per-token + on-demand GPU; day-0 OSS model support; post-training stack. Free credits often available.","cite":"Depot Pick for open-model-inference: fireworks (asOf 2026-09-14). See GET /api/jtbds/open-model-inference + GET /api/methodology.","nextActions":[{"step":1,"title":"Inspect full JTBD + embeds","href":"/api/jtbds/open-model-inference?embed=providers","why":"Confirm pick, runners-up, and methodology notes."},{"step":2,"title":"Quote sourced SKUs","href":"/api/quote?jtbd=open-model-inference","why":"Depot Pick SKUs plus the cheapest sourced SKU whose unit matches this job. Does not change the pick. Does not blend input and output or borrow a chat rate for a non-chat job."},{"step":3,"title":"Open provider detail","href":"/api/providers/fireworks","why":"Scores, pricingNotes, strengths/weaknesses, communitySignals (claims only)."},{"step":4,"title":"Cite methodology","href":"/api/methodology","why":"Required when publishing a Depot Pick citation."},{"step":5,"title":"Grab badge SVG","href":"/api/badge?type=depot-pick&jtbd=open-model-inference","why":"Embed in README / agent passport."},{"step":6,"title":"Post production insight","method":"POST","href":"/api/insights","why":"Unverified until curated; never auto-mutates official scores."}],"honesty":["Do not invent scores or benches.","Insights are claims until curated/reviewed; they never silently mutate official scores.","lockInRisk higher = more lock-in (worse).","normalizedUsdPerMillionTokens is set only for a single sourced token row. Otherwise null, with a machine-readable reason. Do not coerce GPU, minute, or per-1k search units.","Runners-up are not Depot Picks.","Depot overall is editorial_weighted, not Arena Elo and not an Artificial Analysis index."],"asOf":"2026-09-14","depth":{"whenNotToUse":{"text":"Need Hub-native custom model endpoints (HF) or ultra-low latency on narrow SKUs (Groq).","source":"editorial `whenNotTopPick` (data/jtbds.json)"},"whenNotToUseReason":null,"runnerUp":{"providerId":"together","name":"Together AI","overallForJob":8.2,"pickOverallForJob":8.35,"beatsPickOn":["pricePerformance","maturity"],"source":"first resolvable entry of the job's editorially ranked `runnersUpIds`; scores are stored job-weighted scores"},"runnerUpReason":null,"lockIn":{"pickLockInRisk":3.5,"runnerUpLockInRisk":3.5,"scale":"0–10 stored curated estimate; higher = more lock-in (worse)","pickExitSignals":["serves open-weight models (provider tag `open-models`)"],"runnerUpExitSignals":["serves open-weight models (provider tag `open-models`)"],"pickNotes":[],"selfHostFallback":[{"id":"qwen3-0.6b-base","name":"Qwen3-0.6B-Base","license":"Apache-2.0","sourceUrl":"https://huggingface.co/Qwen/Qwen3-0.6B-Base/raw/main/LICENSE"},{"id":"deepseek-v3.2-weights","name":"DeepSeek-V3.2 weights","license":"MIT","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2/raw/main/LICENSE"},{"id":"gemma-terms-of-use","name":"Gemma models under the Gemma Terms of Use","license":"Gemma Terms of Use","sourceUrl":"https://ai.google.dev/gemma/terms"}],"migration":"Pick exit signals: serves open-weight models (provider tag `open-models`). Self-host fallback listed for this job: Qwen3-0.6B-Base, DeepSeek-V3.2 weights, Gemma models under the Gemma Terms of Use.","migrationReason":null,"derivedFrom":"stored lockInRisk scores, provider tags (oss, self-host, openai-compat, open-models), free rows that list this job, and verbatim provider notes. No migration guide was invented."}},"citation":{"text":"Agent Provider Depot (v0.12.150), Depot Pick for open-model-inference: fireworks, scores as of 2026-09-14, retrieved 2026-10-27. https://getagentdepot.com/jtbds/open-model-inference","markdown":"[Agent Provider Depot](https://getagentdepot.com/jtbds/open-model-inference) (v0.12.150) — Depot Pick for `open-model-inference`: **fireworks** (scores as of 2026-09-14, retrieved 2026-10-27)","fields":{"publisher":"Agent Provider Depot","version":"0.12.150","role":"depot_pick","jtbdId":"open-model-inference","providerId":"fireworks","scoreAsOf":"2026-09-14","retrievedOn":"2026-10-27","page":"https://getagentdepot.com/jtbds/open-model-inference","api":"https://getagentdepot.com/api/decide?jtbd=open-model-inference"},"howToCite":"Cite Depot as an editorial, dated recommendation, not a benchmark: name the job, the Depot Pick (or runner-up), the score asOf date and the day you retrieved it, and link the job page. Format: “Agent Provider Depot (v{version}), Depot Pick for {jobId}: {providerId}, scores as of {scoreAsOf}, retrieved {retrievedOn}. {baseUrl}/jtbds/{jobId}”. Quote prices only with their own sourceUrl and asOf. If the pick's score is stale (freshness.pick.score.stale), say so."},"freshness":{"pick":{"score":{"asOf":"2026-09-14","ageDays":43,"stale":true,"staleAfterDays":30,"reason":null},"lastReviewed":{"asOf":"2026-09-14","ageDays":43,"stale":true,"staleAfterDays":30,"reason":null},"sourceCheck":{"checkedAt":"2026-10-27","sourceUrls":2,"sourcesReachable":2,"pricingRows":10,"pricingRowsReconfirmed":6,"note":"A source re-check confirms the page is reachable and, for pricing rows, that the stored amount and SKU name appear on it. It does not re-derive or change the score.","reason":null}},"scoreAsOf":"2026-09-14","editorialPriorAsOf":"2026-09-14","pricingLastVerifiedAt":"2026-10-27","pickLastReviewed":"2026-09-14","runnersUpScoreAsOf":["2026-09-14","2026-09-14","2026-09-14","2026-09-14","2026-09-14","2026-10-01"],"contractAsOf":"2026-10-03","pricingShape":"sourced_rows","normalizedUsdPerMillionTokens":null,"normalizationStatus":"ambiguous","normalizationReason":"multiple_sourced_token_skus"},"pricingContract":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"ambiguous","normalizationReason":"multiple_sourced_token_skus","shape":"sourced_rows","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[{"id":"fireworks-embed-to-150m","providerId":"fireworks","sku":"Embeddings up to 150M params","unit":"usd_per_million_input_tokens","amountUsd":0.008,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.008,"normalizationReason":"embedding_sku_excluded_from_provider_sort","priceSortEligible":false,"qualifier":"parameter-count bucket, not a named chat model"},{"id":"fireworks-embed-150-350m","providerId":"fireworks","sku":"Embeddings 150M-350M params","unit":"usd_per_million_input_tokens","amountUsd":0.016,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.016,"normalizationReason":"embedding_sku_excluded_from_provider_sort","priceSortEligible":false,"qualifier":"parameter-count bucket"},{"id":"fireworks-embed-qwen3-8b","providerId":"fireworks","sku":"Qwen3 8B","unit":"usd_per_million_input_tokens","amountUsd":0.1,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.1,"normalizationReason":"embedding_sku_excluded_from_provider_sort","priceSortEligible":false,"qualifier":"listed in the embeddings section after the parameter buckets"},{"id":"fireworks-train-lora-sft-to-16b","providerId":"fireworks","sku":"Managed training LoRA SFT up to 16B","unit":"usd_per_million_train_tokens","amountUsd":0.5,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.5,"normalizationReason":"training_token_price_not_inference","priceSortEligible":false,"qualifier":"per 1M training tokens"},{"id":"fireworks-gpu-h100","providerId":"fireworks","sku":"H100 80 GB","unit":"usd_per_gpu_hour","amountUsd":8,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"on-demand deployments; per-minute column also shown and not converted; reconfirmed 2026-10-27 (v0.12.139): page says 'Region-restricted deployments are priced at a 1.5x premium' (not stored as a separate row)"},{"id":"fireworks-gpu-h200","providerId":"fireworks","sku":"H200 141 GB","unit":"usd_per_gpu_hour","amountUsd":8,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"on-demand deployments; per-minute column also shown and not converted; reconfirmed 2026-10-27 (v0.12.139): page says 'Region-restricted deployments are priced at a 1.5x premium' (not stored as a separate row)"},{"id":"fireworks-gpu-b200","providerId":"fireworks","sku":"B200 180 GB","unit":"usd_per_gpu_hour","amountUsd":13,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"on-demand deployments; per-minute column also shown and not converted; reconfirmed 2026-10-27 (v0.12.139): page says 'Region-restricted deployments are priced at a 1.5x premium' (not stored as a separate row)"},{"id":"fireworks-gpu-b300","providerId":"fireworks","sku":"B300 288 GB","unit":"usd_per_gpu_hour","amountUsd":15,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"on-demand deployments; per-minute column also shown and not converted; reconfirmed 2026-10-27 (v0.12.139): page says 'Region-restricted deployments are priced at a 1.5x premium' (not stored as a separate row)"},{"id":"fireworks-gpu-gb300","providerId":"fireworks","sku":"GB300 288 GB","unit":"usd_per_gpu_hour","amountUsd":20,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"on-demand deployments; per-minute column also shown and not converted; reconfirmed 2026-10-27 (v0.12.139): page says 'Region-restricted deployments are priced at a 1.5x premium' (not stored as a separate row)"},{"id":"fireworks-serverless-chat-unavailable","providerId":"fireworks","sku":"serverless chat models","unit":"usd_per_million_input_tokens","amountUsd":null,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-03","normalizationStatus":"ambiguous","normalizedUsdPerMillionTokens":null,"normalizationReason":"page_points_elsewhere_for_serverless_chat_matrix","priceSortEligible":false,"qualifier":"fireworks.ai/pricing says to visit full pricing documentation for Standard/Priority/Fast serverless token rates. Those figures were not on this page and were not guessed."}],"notesExcerpt":"Serverless per-token + on-demand GPU; day-0 OSS model support; post-training stack. Free credits often available.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://fireworks.ai","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"Partial coverage. Providers without a fetched SKU are omitted. See GET /api/pricing."},"links":{"jtbd":"/jtbds/open-model-inference","jtbdApi":"/api/jtbds/open-model-inference","leaderboard":"/api/leaderboards?jtbd=open-model-inference","methodology":"/api/methodology","badge":"/api/badge?type=depot-pick&jtbd=open-model-inference","decide":"/api/decide?jtbd=open-model-inference","humanPage":"/jtbds/open-model-inference","alternatives":"/api/alternatives?provider=fireworks","canonical":"/api/canonical","quote":"/api/quote?jtbd=open-model-inference","falsify":"/api/falsify?jtbd=open-model-inference"},"constraintBundle":{"task":null,"jtbd":"open-model-inference","quotaExhausted":[],"degraded":[],"healthy":[],"budgetUsd":null,"maxLatencyMs":null,"region":null,"privacy":null,"exit":[],"existing":[]},"stackContext":{"host":null,"framework":null,"repo":null,"lang":null,"existing":[],"volume":null,"sender":null,"detectedFromTask":[]},"keep":null,"contextAdvice":null,"communityFeedback":{"pickOnThisJob":{"failed":0,"degraded":0,"worked":0,"insights":0,"withVerifiedReceipt":0,"failureModes":{},"latestAt":null,"note":"Agent-reported claims (unverified unless a receipt is verified by Depot's re-check). They never change scores or picks."},"outcomes":{"job":{"n":0,"worked":0,"degraded":0,"failed":0,"failureModes":{},"verifiedReports":0,"contributors":0,"excluded":{"seed_editorial":0,"test":0,"notFeedback":0},"reason":"no_submitted_outcome_reports_yet"},"pick":{"providerId":"fireworks","n":0,"worked":0,"degraded":0,"failed":0,"failureModes":{},"evidenceTiers":{"agent_claim":0,"self_declared":0,"reference_checked":0,"outcome_verified":0},"reason":"no_submitted_outcome_reports_yet"},"scoresMutated":false,"more":"/api/outcomes?jtbd=open-model-inference"},"report":"POST /api/feedback {agentIdentity, outcome: failed|degraded|worked, detail, providerId, jtbdId, failureModeId?, receipt?}"}}