Fireworks AI API Pricing 2026

Fireworks AI provides fast, cost-effective inference for open-source models with a focus on developer experience.

Showing 251 models from Fireworks AI. Prices are per 1 million tokens. Data sourced from official pricing pages via LiteLLM.

Models

251

Cheapest Input

$0.00

/1M tokens

Cheapest Output

$0.00

/1M tokens

Max Context

262K

tokens

251 models
Features
accounts/fireworks/models/flux-1-dev-controlnet-union$0.0010$0.00104.1K4.1K
fireworks-ai-embedding-up-to-150m$0.0080Free
fireworks-ai-embedding-150m-to-350m$0.016Free
accounts/fireworks/models/gpt-oss-20b$0.050$0.200131.1K131.1K
accounts/fireworks/models/codegemma-2b$0.100$0.1008.2K8.2K
accounts/fireworks/models/cogito-v1-preview-llama-3b$0.100$0.100131.1K131.1K
accounts/fireworks/models/deepseek-coder-1b-base$0.100$0.10016.4K16.4K
accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b$0.100$0.100131.1K131.1K
accounts/fireworks/models/ernie-4p5-21b-a3b-pt$0.100$0.1004.1K4.1K
accounts/fireworks/models/ernie-4p5-300b-a47b-pt$0.100$0.1004.1K4.1K
accounts/fireworks/models/flux-1-dev$0.100$0.1004.1K4.1K
accounts/fireworks/models/flux-1-schnell$0.100$0.1004.1K4.1K
accounts/fireworks/models/gemma-2b-it$0.100$0.1008.2K8.2K
accounts/fireworks/models/llama-guard-3-1b$0.100$0.100131.1K131.1K
accounts/fireworks/models/llama-v2-70b$0.100$0.1004.1K4.1K
accounts/fireworks/models/llama-v3p1-405b-instruct-long$0.100$0.1004.1K4.1K
accounts/fireworks/models/llama-v3p1-70b-instruct-1b$0.100$0.1004.1K4.1K
accounts/fireworks/models/llama-v3p1-8b-instruct$0.100$0.10016.4K16.4K
accounts/fireworks/models/llama-v3p2-1b$0.100$0.100131.1K131.1K
accounts/fireworks/models/llama-v3p2-1b-instruct$0.100$0.10016.4K16.4K
accounts/fireworks/models/llama-v3p2-3b$0.100$0.100131.1K131.1K
accounts/fireworks/models/llama-v3p2-3b-instruct$0.100$0.10016.4K16.4K
accounts/fireworks/models/minimax-m1-80k$0.100$0.1004.1K4.1K
accounts/fireworks/models/ministral-3-3b-instruct-2512$0.100$0.100256K256K
accounts/fireworks/models/nemotron-nano-v2-12b-vl$0.100$0.1004.1K4.1K
accounts/fireworks/models/phi-2-3b$0.100$0.1002.0K2.0K
accounts/fireworks/models/phi-3-mini-128k-instruct$0.100$0.100131.1K131.1K
accounts/fireworks/models/qwen2-vl-2b-instruct$0.100$0.10032.8K32.8K
accounts/fireworks/models/qwen2p5-0p5b-instruct$0.100$0.10032.8K32.8K
accounts/fireworks/models/qwen2p5-1p5b-instruct$0.100$0.10032.8K32.8K
accounts/fireworks/models/qwen2p5-coder-0p5b$0.100$0.10032.8K32.8K
accounts/fireworks/models/qwen2p5-coder-0p5b-instruct$0.100$0.10032.8K32.8K
accounts/fireworks/models/qwen2p5-coder-1p5b$0.100$0.10032.8K32.8K
accounts/fireworks/models/qwen2p5-coder-1p5b-instruct$0.100$0.10032.8K32.8K
accounts/fireworks/models/qwen2p5-coder-3b$0.100$0.10032.8K32.8K
accounts/fireworks/models/qwen2p5-coder-3b-instruct$0.100$0.10032.8K32.8K
accounts/fireworks/models/qwen3-0p6b$0.100$0.10041.0K41.0K
accounts/fireworks/models/qwen3-1p7b$0.100$0.100131.1K131.1K
accounts/fireworks/models/qwen3-1p7b-fp8-draft$0.100$0.100262.1K262.1K
accounts/fireworks/models/qwen3-1p7b-fp8-draft-131072$0.100$0.100131.1K131.1K
accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960$0.100$0.10041.0K41.0K
accounts/fireworks/models/stablecode-3b$0.100$0.1004.1K4.1K
accounts/fireworks/models/starcoder2-3b$0.100$0.10016.4K16.4K
accounts/fireworks/models/gpt-oss-120b$0.150$0.600131.1K131.1K
accounts/fireworks/models/llama4-scout-instruct-basic$0.150$0.600131.1K131.1K
accounts/fireworks/models/qwen3-30b-a3b$0.150$0.600131.1K131.1K
accounts/fireworks/models/qwen3-coder-30b-a3b-instruct$0.150$0.600262.1K262.1K
accounts/fireworks/models/qwen3-vl-30b-a3b-instruct$0.150$0.600262.1K262.1K
accounts/fireworks/models/qwen3-vl-30b-a3b-thinking$0.150$0.600262.1K262.1K
accounts/fireworks/models/chronos-hermes-13b-v2$0.200$0.2004.1K4.1K
accounts/fireworks/models/code-llama-13b$0.200$0.20016.4K16.4K
accounts/fireworks/models/code-llama-13b-instruct$0.200$0.20016.4K16.4K
accounts/fireworks/models/code-llama-13b-python$0.200$0.20016.4K16.4K
accounts/fireworks/models/code-llama-7b$0.200$0.20016.4K16.4K
accounts/fireworks/models/code-llama-7b-instruct$0.200$0.20016.4K16.4K
accounts/fireworks/models/code-llama-7b-python$0.200$0.20016.4K16.4K
accounts/fireworks/models/code-qwen-1p5-7b$0.200$0.20065.5K65.5K
accounts/fireworks/models/codegemma-7b$0.200$0.2008.2K8.2K
accounts/fireworks/models/cogito-v1-preview-llama-8b$0.200$0.200131.1K131.1K
accounts/fireworks/models/cogito-v1-preview-qwen-14b$0.200$0.200131.1K131.1K
accounts/fireworks/models/deepseek-coder-7b-base$0.200$0.2004.1K4.1K
accounts/fireworks/models/deepseek-coder-7b-base-v1p5$0.200$0.2004.1K4.1K
accounts/fireworks/models/deepseek-coder-7b-instruct-v1p5$0.200$0.2004.1K4.1K
accounts/fireworks/models/deepseek-r1-0528-distill-qwen3-8b$0.200$0.200131.1K131.1K
accounts/fireworks/models/deepseek-r1-distill-llama-8b$0.200$0.200131.1K131.1K
accounts/fireworks/models/deepseek-r1-distill-qwen-14b$0.200$0.200131.1K131.1K
accounts/fireworks/models/deepseek-r1-distill-qwen-7b$0.200$0.200131.1K131.1K
accounts/fireworks/models/dobby-mini-unhinged-plus-llama-3-1-8b$0.200$0.200131.1K131.1K
accounts/fireworks/models/firellava-13b$0.200$0.2004.1K4.1K
accounts/fireworks/models/firesearch-ocr-v6$0.200$0.2008.2K8.2K
accounts/fireworks/models/gemma-7b$0.200$0.2008.2K8.2K
accounts/fireworks/models/gemma-7b-it$0.200$0.2008.2K8.2K
accounts/fireworks/models/gemma2-9b-it$0.200$0.2008.2K8.2K
accounts/fireworks/models/hermes-2-pro-mistral-7b$0.200$0.20032.8K32.8K
accounts/fireworks/models/internvl3-8b$0.200$0.20016.4K16.4K
accounts/fireworks/models/llama-guard-2-8b$0.200$0.2008.2K8.2K
accounts/fireworks/models/llama-guard-3-8b$0.200$0.200131.1K131.1K
accounts/fireworks/models/llama-v2-13b$0.200$0.2004.1K4.1K
accounts/fireworks/models/llama-v2-13b-chat$0.200$0.2004.1K4.1K
accounts/fireworks/models/llama-v2-7b$0.200$0.2004.1K4.1K
accounts/fireworks/models/llama-v2-7b-chat$0.200$0.2004.1K4.1K
accounts/fireworks/models/llama-v3-8b$0.200$0.2008.2K8.2K
accounts/fireworks/models/llama-v3-8b-instruct-hf$0.200$0.2008.2K8.2K
accounts/fireworks/models/llama-v3p2-11b-vision-instruct$0.200$0.20016.4K16.4K
accounts/fireworks/models/llamaguard-7b$0.200$0.2004.1K4.1K
accounts/fireworks/models/ministral-3-14b-instruct-2512$0.200$0.200256K256K
accounts/fireworks/models/ministral-3-8b-instruct-2512$0.200$0.200256K256K
accounts/fireworks/models/mistral-7b$0.200$0.20032.8K32.8K
accounts/fireworks/models/mistral-7b-instruct-4k$0.200$0.20032.8K32.8K
accounts/fireworks/models/mistral-7b-instruct-v0p2$0.200$0.20032.8K32.8K
accounts/fireworks/models/mistral-7b-instruct-v3$0.200$0.20032.8K32.8K
accounts/fireworks/models/mistral-7b-v0p2$0.200$0.20032.8K32.8K
accounts/fireworks/models/mistral-nemo-base-2407$0.200$0.200128K128K
accounts/fireworks/models/mistral-nemo-instruct-2407$0.200$0.200128K128K
accounts/fireworks/models/mythomax-l2-13b$0.200$0.2004.1K4.1K
accounts/fireworks/models/nous-capybara-7b-v1p9$0.200$0.20032.8K32.8K
accounts/fireworks/models/nous-hermes-llama2-13b$0.200$0.2004.1K4.1K
accounts/fireworks/models/nous-hermes-llama2-7b$0.200$0.2004.1K4.1K
accounts/fireworks/models/nvidia-nemotron-nano-12b-v2$0.200$0.200131.1K131.1K
accounts/fireworks/models/nvidia-nemotron-nano-9b-v2$0.200$0.200131.1K131.1K
accounts/fireworks/models/openchat-3p5-0106-7b$0.200$0.2008.2K8.2K
accounts/fireworks/models/openhermes-2-mistral-7b$0.200$0.20032.8K32.8K
accounts/fireworks/models/openhermes-2p5-mistral-7b$0.200$0.20032.8K32.8K
accounts/fireworks/models/openorca-7b$0.200$0.20032.8K32.8K
accounts/fireworks/models/phi-3-vision-128k-instruct$0.200$0.20032.1K32.1K
accounts/fireworks/models/pythia-12b$0.200$0.2002.0K2.0K
accounts/fireworks/models/qwen-v2p5-14b-instruct$0.200$0.20032.8K32.8K
accounts/fireworks/models/qwen-v2p5-7b$0.200$0.200131.1K131.1K
accounts/fireworks/models/qwen2-7b-instruct$0.200$0.20032.8K32.8K
accounts/fireworks/models/qwen2-vl-7b-instruct$0.200$0.20032.8K32.8K
accounts/fireworks/models/qwen2p5-14b$0.200$0.200131.1K131.1K
accounts/fireworks/models/qwen2p5-7b-instruct$0.200$0.20032.8K32.8K
accounts/fireworks/models/qwen2p5-coder-14b$0.200$0.20032.8K32.8K
accounts/fireworks/models/qwen2p5-coder-14b-instruct$0.200$0.20032.8K32.8K
accounts/fireworks/models/qwen2p5-coder-7b$0.200$0.20032.8K32.8K
accounts/fireworks/models/qwen2p5-coder-7b-instruct$0.200$0.20032.8K32.8K
accounts/fireworks/models/qwen2p5-vl-3b-instruct$0.200$0.200128K128K
accounts/fireworks/models/qwen2p5-vl-7b-instruct$0.200$0.200128K128K
accounts/fireworks/models/qwen3-14b$0.200$0.20041.0K41.0K
accounts/fireworks/models/qwen3-4b$0.200$0.20041.0K41.0K
accounts/fireworks/models/qwen3-4b-instruct-2507$0.200$0.200262.1K262.1K
accounts/fireworks/models/qwen3-8b$0.200$0.20041.0K41.0K
accounts/fireworks/models/qwen3-vl-8b-instruct$0.200$0.2004.1K4.1K
accounts/fireworks/models/rolm-ocr$0.200$0.200128K128K
accounts/fireworks/models/snorkel-mistral-7b-pairrm-dpo$0.200$0.20032.8K32.8K
accounts/fireworks/models/starcoder-16b$0.200$0.2008.2K8.2K
accounts/fireworks/models/starcoder-7b$0.200$0.2008.2K8.2K
accounts/fireworks/models/starcoder2-15b$0.200$0.20016.4K16.4K
accounts/fireworks/models/starcoder2-7b$0.200$0.20016.4K16.4K
accounts/fireworks/models/toppy-m-7b$0.200$0.20032.8K32.8K
accounts/fireworks/models/yi-6b$0.200$0.2004.1K4.1K
accounts/fireworks/models/zephyr-7b-beta$0.200$0.20032.8K32.8K
fireworks-ai-4.1b-to-16b$0.200$0.200
fireworks-ai-up-to-4b$0.200$0.200
accounts/fireworks/models/glm-4p5-air$0.220$0.880128K96K
accounts/fireworks/models/llama4-maverick-instruct-basic$0.220$0.880131.1K131.1K
accounts/fireworks/models/qwen3-235b-a22b$0.220$0.880131.1K131.1K
accounts/fireworks/models/qwen3-235b-a22b-instruct-2507$0.220$0.880262.1K262.1K
accounts/fireworks/models/qwen3-235b-a22b-thinking-2507$0.220$0.880262.1K262.1K
accounts/fireworks/models/qwen3-vl-235b-a22b-instruct$0.220$0.880262.1K262.1K
accounts/fireworks/models/qwen3-vl-235b-a22b-thinking$0.220$0.880262.1K262.1K
accounts/fireworks/models/minimax-m2$0.300$1.204.1K4.1K
accounts/fireworks/models/minimax-m2p1$0.300$1.20204.8K204.8K
minimax-m2p1$0.300$1.20204.8K204.8K
accounts/fireworks/models/qwen3-coder-480b-a35b-instruct$0.450$1.80262.1K262.1K
accounts/fireworks/models/deepseek-coder-v2-lite-base$0.500$0.500163.8K163.8K
accounts/fireworks/models/deepseek-coder-v2-lite-instruct$0.500$0.500163.8K163.8K
accounts/fireworks/models/deepseek-v2-lite-chat$0.500$0.500163.8K163.8K
accounts/fireworks/models/dolphin-2p6-mixtral-8x7b$0.500$0.50032.8K32.8K
accounts/fireworks/models/firefunction-v1$0.500$0.50032.8K32.8K
accounts/fireworks/models/gpt-oss-safeguard-20b$0.500$0.500131.1K131.1K
accounts/fireworks/models/mixtral-8x7b$0.500$0.50032.8K32.8K
accounts/fireworks/models/mixtral-8x7b-instruct$0.500$0.50032.8K32.8K
accounts/fireworks/models/mixtral-8x7b-instruct-hf$0.500$0.50032.8K32.8K
accounts/fireworks/models/nous-hermes-2-mixtral-8x7b-dpo$0.500$0.50032.8K32.8K
accounts/fireworks/models/qwen3-30b-a3b-instruct-2507$0.500$0.500262.1K262.1K
fireworks-ai-moe-up-to-56b$0.500$0.500
accounts/fireworks/models/deepseek-r1-basic$0.550$2.19128K20.5K
accounts/fireworks/models/glm-4p5$0.550$2.19128K96K
accounts/fireworks/models/glm-4p6$0.550$2.19202.8K202.8K
accounts/fireworks/models/deepseek-v3p1$0.560$1.68128K8.2K
accounts/fireworks/models/deepseek-v3p1-terminus$0.560$1.68128K8.2K
accounts/fireworks/models/deepseek-v3p2$0.560$1.68163.8K163.8K
accounts/fireworks/models/glm-4p7$0.600$2.20202.8K202.8K
accounts/fireworks/models/kimi-k2-instruct$0.600$2.50131.1K16.4K
accounts/fireworks/models/kimi-k2-instruct-0905$0.600$2.50262.1K32.8K
accounts/fireworks/models/kimi-k2-thinking$0.600$2.50262.1K262.1K
accounts/fireworks/models/kimi-k2p5$0.600$3.00262.1K262.1K
glm-4p7$0.600$2.20202.8K202.8K
kimi-k2p5$0.600$3.00262.1K262.1K
accounts/fireworks/models/code-llama-34b$0.900$0.90016.4K16.4K
accounts/fireworks/models/code-llama-34b-instruct$0.900$0.90016.4K16.4K
accounts/fireworks/models/code-llama-34b-python$0.900$0.90016.4K16.4K
accounts/fireworks/models/code-llama-70b$0.900$0.9004.1K4.1K
accounts/fireworks/models/code-llama-70b-instruct$0.900$0.9004.1K4.1K
accounts/fireworks/models/code-llama-70b-python$0.900$0.9004.1K4.1K
accounts/fireworks/models/cogito-v1-preview-llama-70b$0.900$0.900131.1K131.1K
accounts/fireworks/models/cogito-v1-preview-qwen-32b$0.900$0.900131.1K131.1K
accounts/fireworks/models/deepseek-coder-33b-instruct$0.900$0.90016.4K16.4K
accounts/fireworks/models/deepseek-r1-distill-llama-70b$0.900$0.900131.1K131.1K
accounts/fireworks/models/deepseek-r1-distill-qwen-32b$0.900$0.900131.1K131.1K
accounts/fireworks/models/deepseek-v3$0.900$0.900128K8.2K
accounts/fireworks/models/deepseek-v3-0324$0.900$0.900163.8K163.8K
accounts/fireworks/models/devstral-small-2505$0.900$0.900131.1K131.1K
accounts/fireworks/models/dobby-unhinged-llama-3-3-70b-new$0.900$0.900131.1K131.1K
accounts/fireworks/models/dolphin-2-9-2-qwen2-72b$0.900$0.900131.1K131.1K
accounts/fireworks/models/fare-20b$0.900$0.900131.1K131.1K
accounts/fireworks/models/firefunction-v2$0.900$0.9008.2K8.2K
accounts/fireworks/models/gemma-3-27b-it$0.900$0.900131.1K131.1K
accounts/fireworks/models/internvl3-38b$0.900$0.90016.4K16.4K
accounts/fireworks/models/internvl3-78b$0.900$0.90016.4K16.4K
accounts/fireworks/models/kat-coder$0.900$0.900262.1K262.1K
accounts/fireworks/models/kat-dev-32b$0.900$0.900131.1K131.1K
accounts/fireworks/models/kat-dev-72b-exp$0.900$0.900131.1K131.1K
accounts/fireworks/models/llama-v2-70b-chat$0.900$0.9002.0K2.0K
accounts/fireworks/models/llama-v3-70b-instruct$0.900$0.9008.2K8.2K
accounts/fireworks/models/llama-v3-70b-instruct-hf$0.900$0.9008.2K8.2K
accounts/fireworks/models/llama-v3p1-70b-instruct$0.900$0.900131.1K131.1K
accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct$0.900$0.900131.1K131.1K
accounts/fireworks/models/llama-v3p2-90b-vision-instruct$0.900$0.90016.4K16.4K
accounts/fireworks/models/llama-v3p3-70b-instruct$0.900$0.900131.1K131.1K
accounts/fireworks/models/llava-yi-34b$0.900$0.9004.1K4.1K
accounts/fireworks/models/mistral-small-24b-instruct-2501$0.900$0.90032.8K32.8K
accounts/fireworks/models/nous-hermes-2-yi-34b$0.900$0.9004.1K4.1K
accounts/fireworks/models/nous-hermes-llama2-70b$0.900$0.9004.1K4.1K
accounts/fireworks/models/phind-code-llama-34b-python-v1$0.900$0.90016.4K16.4K
accounts/fireworks/models/phind-code-llama-34b-v1$0.900$0.90016.4K16.4K
accounts/fireworks/models/phind-code-llama-34b-v2$0.900$0.90016.4K16.4K
accounts/fireworks/models/qwen-qwq-32b-preview$0.900$0.90032.8K32.8K
accounts/fireworks/models/qwen1p5-72b-chat$0.900$0.90032.8K32.8K
accounts/fireworks/models/qwen2-72b-instruct$0.900$0.90032.8K32.8K
accounts/fireworks/models/qwen2-vl-72b-instruct$0.900$0.90032.8K32.8K
accounts/fireworks/models/qwen2p5-32b$0.900$0.900131.1K131.1K
accounts/fireworks/models/qwen2p5-32b-instruct$0.900$0.90032.8K32.8K
accounts/fireworks/models/qwen2p5-72b$0.900$0.900131.1K131.1K
accounts/fireworks/models/qwen2p5-72b-instruct$0.900$0.90032.8K32.8K
accounts/fireworks/models/qwen2p5-coder-32b$0.900$0.90032.8K32.8K
accounts/fireworks/models/qwen2p5-coder-32b-instruct$0.900$0.9004.1K4.1K
accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k$0.900$0.900131.1K131.1K
accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope$0.900$0.90032.8K32.8K
accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k$0.900$0.90065.5K65.5K
accounts/fireworks/models/qwen2p5-math-72b-instruct$0.900$0.9004.1K4.1K
accounts/fireworks/models/qwen2p5-vl-32b-instruct$0.900$0.900128K128K
accounts/fireworks/models/qwen2p5-vl-72b-instruct$0.900$0.900128K128K
accounts/fireworks/models/qwen3-30b-a3b-thinking-2507$0.900$0.900262.1K262.1K
accounts/fireworks/models/qwen3-32b$0.900$0.900131.1K131.1K
accounts/fireworks/models/qwen3-coder-480b-instruct-bf16$0.900$0.9004.1K4.1K
accounts/fireworks/models/qwen3-next-80b-a3b-instruct$0.900$0.9004.1K4.1K
accounts/fireworks/models/qwen3-next-80b-a3b-thinking$0.900$0.9004.1K4.1K
accounts/fireworks/models/qwen3-vl-32b-instruct$0.900$0.9004.1K4.1K
accounts/fireworks/models/qwq-32b$0.900$0.900131.1K131.1K
accounts/fireworks/models/yi-34b$0.900$0.9004.1K4.1K
accounts/fireworks/models/yi-34b-200k-capybara$0.900$0.900200K200K
accounts/fireworks/models/yi-34b-chat$0.900$0.9004.1K4.1K
fireworks-ai-above-16b$0.900$0.900
accounts/fireworks/models/cogito-671b-v2-p1$1.20$1.20163.8K163.8K
accounts/fireworks/models/dbrx-instruct$1.20$1.2032.8K32.8K
accounts/fireworks/models/deepseek-coder-v2-instruct$1.20$1.2065.5K65.5K
accounts/fireworks/models/deepseek-prover-v2$1.20$1.20163.8K163.8K
accounts/fireworks/models/deepseek-v2p5$1.20$1.2032.8K32.8K
accounts/fireworks/models/glm-4p5v$1.20$1.20131.1K131.1K
accounts/fireworks/models/gpt-oss-safeguard-120b$1.20$1.20131.1K131.1K
accounts/fireworks/models/mistral-large-3-fp8$1.20$1.20256K256K
accounts/fireworks/models/mixtral-8x22b$1.20$1.2065.5K65.5K
accounts/fireworks/models/mixtral-8x22b-instruct$1.20$1.2065.5K65.5K
accounts/fireworks/models/mixtral-8x22b-instruct-hf$1.20$1.2065.5K65.5K
fireworks-ai-56b-to-176b$1.20$1.20
accounts/fireworks/models/deepseek-r1$3.00$8.00128K20.5K
accounts/fireworks/models/deepseek-r1-0528$3.00$8.00160K160K
accounts/fireworks/models/llama-v3p1-405b-instruct$3.00$3.00128K16.4K
accounts/fireworks/models/yi-large$3.00$3.0032.8K32.8K

อัปเดตราคา LLM รายสัปดาห์

รับแจ้งเตือนเมื่อราคา AI model เปลี่ยน ฟรี ไม่สแปม ยกเลิกได้ตลอด