Fireworks AI API Pricing
Complete pricing for all Fireworks AI models. Input/output costs per 1M tokens, context windows, and rate limits.
Billing terms: priced in USD per 1M tokens unless a row states otherwise; official direct rates are listed separately from third-party channels, and regional prices are kept distinct. Record updated 2026-10-11.
Fireworks AI API Pricing Calculator
Select a model to estimate monthly cost using its listed rates on each channel.
Workloads reusing system prompts, long documents, or conversation history hit more; channels without a cached rate are billed at the full input rate.
| Channel | Effective input | Output /1M | Est. / month |
|---|---|---|---|
| fireworks | $0.15(w/ cache) | $1.20 | $1.27 |
Formula: monthly cost = (input tokens × effective input rate + output tokens × output rate) ÷ 1,000,000 × calls. The effective input rate blends list and cached rates at your cache-hit share. Rates share the selected model and billing basis; your vendor bill is authoritative.
Currently available rates
DeepSeek Flash Latest
LLMfireworks-accounts-fireworks-routers-deepseek-flash-latestDeepSeek Pro Latest
LLMfireworks-accounts-fireworks-routers-deepseek-pro-latestDeepSeek R1
LLMfireworks-deepseek-r1DeepSeek V3
LLMfireworks-deepseek-v3DeepSeek V4 Flash 0731
LLMfireworks-accounts-fireworks-models-deepseek-v4-flash-0731DeepSeek V4 Flash Vision Exp
LLMfireworks-accounts-fireworks-models-deepseek-v4-flash-vision-expDeepSeek V4 Pro
LLMfireworks-accounts-fireworks-models-deepseek-v4-proDeepSeek V4 Pro 0813
LLMfireworks-accounts-fireworks-models-deepseek-v4-pro-0813DeepSeek V4.1 Flash
LLMfireworks-accounts-fireworks-models-deepseek-v4p1-flashEmber-1
LLMfireworks-accounts-fireworks-models-ember-1Ember-1
LLMfireworks-ember-1FLUX.1 [dev]
Image Genfireworks-flux-1-devGLM 5.2
LLMfireworks-accounts-fireworks-models-glm-5p2GLM 5.2 Fast
LLMfireworks-accounts-fireworks-routers-glm-5p2-fastGLM 5.3
LLMfireworks-accounts-fireworks-models-glm-5p3GLM 5.3 Fast
LLMfireworks-accounts-fireworks-routers-glm-5p3-fastGLM 5.3 Fast (Latest)
LLMfireworks-accounts-fireworks-routers-glm-fast-latestGLM 5.3 Flash
LLMfireworks-accounts-fireworks-models-glm-5p3-flashGLM Flash Latest (GLM 5.3 Flash)
LLMfireworks-accounts-fireworks-routers-glm-flash-latestGLM Latest
LLMfireworks-accounts-fireworks-routers-glm-latestGPT OSS 120B
LLMfireworks-accounts-fireworks-models-gpt-oss-120bInkling
LLMfireworks-accounts-fireworks-models-inklingKimi Fast Latest
LLMfireworks-accounts-fireworks-routers-kimi-fast-latestKimi K2.6
LLMfireworks-accounts-fireworks-models-kimi-k2p6Kimi K2.7 Code
LLMfireworks-accounts-fireworks-models-kimi-k2p7-codeKimi K3
LLMfireworks-accounts-fireworks-models-kimi-k3Kimi K3 Fast
LLMfireworks-accounts-fireworks-routers-kimi-k3-fastKimi Latest
LLMfireworks-accounts-fireworks-routers-kimi-latestLlama 3.3 70B
LLMfireworks-llama-3.3-70bMiniMax Latest
LLMfireworks-accounts-fireworks-routers-minimax-latestMiniMax-M2.7
LLMfireworks-accounts-fireworks-models-minimax-m2p7MiniMax-M3
LLMfireworks-accounts-fireworks-models-minimax-m3Mistral Large 3 675B Instruct 2512
LLMfireworks-accounts-fireworks-models-mistral-large-3-fp8Muse Glimmer 30B
LLMfireworks-accounts-fireworks-models-muse-glimmer-30bNemotron 3 Ultra 550B A55B
LLMfireworks-accounts-fireworks-models-nemotron-3-ultra-nvfp4Nemotron 3.5 Lightning 30B A3B
LLMfireworks-accounts-fireworks-models-nemotron-lightning-3p5-30b-a3bQwen 2.5 72B
LLMfireworks-qwen-2.5-72bQwen 3.7 Plus
LLMfireworks-accounts-fireworks-models-qwen3p7-plusQwen Max Latest (Qwen3.8 Max)
LLMfireworks-accounts-fireworks-routers-qwen-max-latestQwen3.8 2.4T A95B
LLMfireworks-accounts-fireworks-models-qwen3p8-2p4t-a95bQwen3.8 Max
LLMfireworks-accounts-fireworks-models-qwen3p8-maxDoes this change your best option?
Check your models and usage for free. See the relevant official changes, estimated cost, and a practical next step.