Per MillionLLM API prices, tracked daily

Fireworks AI API Pricing (Oct 2026): All 298 Models per 1M Tokens

As of : 298 models tracked. The median price is $0.30 per 1M input tokens and $0.88 per 1M output tokens. Cheapest blended price: nemotron-lightning-3p5-30b-a3b (Fireworks AI, $0.05 per 1M input / $0.20 per 1M output).

API list prices for every Fireworks AI chat model we track.

Browse: All models · Cheapest · Price changes · Cost calculator · By provider · Deprecations · Free RSS alerts

Models

Sort:

Models. Source: the LiteLLM price list (MIT License)
ModelProviderInput / 1MOutput / 1MCached input / 1MContext
nemotron-lightning-3p5-30b-a3bFireworks AI$0.05$0.20$0.01262K
nemotron-lightning-3p5-30b-a3bFireworks AI$0.05$0.20$0.01262K
codegemma-2bFireworks AI$0.10$0.10—8K
cogito-v1-preview-llama-3bFireworks AI$0.10$0.10—131K
deepseek-coder-1b-baseFireworks AI$0.10$0.10—16K
deepseek-r1-distill-qwen-1p5bFireworks AI$0.10$0.10—131K
ernie-4p5-21b-a3b-ptFireworks AI$0.10$0.10—131K
ernie-4p5-300b-a47b-ptFireworks AI$0.10$0.10—131K
gemma-2b-itFireworks AI$0.10$0.10—8K
llama-v2-70bFireworks AI$0.10$0.10—4K
llama-v3p1-405b-instruct-longFireworks AI$0.10$0.10—4K
llama-v3p1-70b-instruct-1bFireworks AI$0.10$0.10—4K
llama-v3p1-8b-instructFireworks AI$0.10$0.10—131K
llama-v3p2-1bFireworks AI$0.10$0.10—131K
llama-v3p2-1b-instructFireworks AI$0.10$0.10—131K
llama-v3p2-3bFireworks AI$0.10$0.10—131K
llama-v3p2-3b-instructFireworks AI$0.10$0.10—131K
minimax-m1-80kFireworks AI$0.10$0.10—4K
ministral-3-3b-instruct-2512Fireworks AI$0.10$0.10—256K
nemotron-nano-v2-12b-vlFireworks AI$0.10$0.10—131K
phi-2-3bFireworks AI$0.10$0.10—2K
phi-3-mini-128k-instructFireworks AI$0.10$0.10—131K
qwen2-vl-2b-instructFireworks AI$0.10$0.10—33K
qwen2p5-0p5b-instructFireworks AI$0.10$0.10—33K
qwen2p5-1p5b-instructFireworks AI$0.10$0.10—33K
qwen2p5-coder-0p5bFireworks AI$0.10$0.10—33K
qwen2p5-coder-0p5b-instructFireworks AI$0.10$0.10—33K
qwen2p5-coder-1p5bFireworks AI$0.10$0.10—33K
qwen2p5-coder-1p5b-instructFireworks AI$0.10$0.10—33K
qwen2p5-coder-3bFireworks AI$0.10$0.10—33K
qwen2p5-coder-3b-instructFireworks AI$0.10$0.10—33K
qwen3-0p6bFireworks AI$0.10$0.10—41K
qwen3-1p7bFireworks AI$0.10$0.10—131K
qwen3-1p7b-fp8-draftFireworks AI$0.10$0.10—262K
qwen3-1p7b-fp8-draft-131072Fireworks AI$0.10$0.10—131K
qwen3-1p7b-fp8-draft-40960Fireworks AI$0.10$0.10—41K
stablecode-3bFireworks AI$0.10$0.10—4K
starcoder2-3bFireworks AI$0.10$0.10—16K
gpt-oss-20bFireworks AI$0.07$0.30$0.04131K
gpt-oss-20bFireworks AI$0.07$0.30$0.04131K
deepseek-v4-flashFireworks AI$0.14$0.28$0.031.04858M
deepseek-v4-flashFireworks AI$0.14$0.28$0.031.04858M
chronos-hermes-13b-v2Fireworks AI$0.20$0.20—4K
code-llama-13bFireworks AI$0.20$0.20—16K
code-llama-13b-instructFireworks AI$0.20$0.20—16K
code-llama-13b-pythonFireworks AI$0.20$0.20—16K
code-llama-7bFireworks AI$0.20$0.20—16K
code-llama-7b-instructFireworks AI$0.20$0.20—16K
code-llama-7b-pythonFireworks AI$0.20$0.20—16K
code-qwen-1p5-7bFireworks AI$0.20$0.20—66K
codegemma-7bFireworks AI$0.20$0.20—8K
cogito-v1-preview-llama-8bFireworks AI$0.20$0.20—131K
cogito-v1-preview-qwen-14bFireworks AI$0.20$0.20—131K
deepseek-coder-7b-baseFireworks AI$0.20$0.20—4K
deepseek-coder-7b-base-v1p5Fireworks AI$0.20$0.20—4K
deepseek-coder-7b-instruct-v1p5Fireworks AI$0.20$0.20—4K
deepseek-r1-0528-distill-qwen3-8bFireworks AI$0.20$0.20—131K
deepseek-r1-distill-llama-8bFireworks AI$0.20$0.20—131K
deepseek-r1-distill-qwen-14bFireworks AI$0.20$0.20—131K
deepseek-r1-distill-qwen-7bFireworks AI$0.20$0.20—131K
dobby-mini-unhinged-plus-llama-3-1-8bFireworks AI$0.20$0.20—131K
firellava-13bFireworks AI$0.20$0.20—4K
firesearch-ocr-v6Fireworks AI$0.20$0.20—8K
gemma-7bFireworks AI$0.20$0.20—8K
gemma-7b-itFireworks AI$0.20$0.20—8K
gemma2-9b-itFireworks AI$0.20$0.20—8K
hermes-2-pro-mistral-7bFireworks AI$0.20$0.20—33K
internvl3-8bFireworks AI$0.20$0.20—16K
llama-v2-13bFireworks AI$0.20$0.20—4K
llama-v2-13b-chatFireworks AI$0.20$0.20—4K
llama-v2-7bFireworks AI$0.20$0.20—4K
llama-v2-7b-chatFireworks AI$0.20$0.20—4K
llama-v3-8bFireworks AI$0.20$0.20—8K
llama-v3-8b-instruct-hfFireworks AI$0.20$0.20—8K
llama-v3p2-11b-vision-instructFireworks AI$0.20$0.20—131K
ministral-3-14b-instruct-2512Fireworks AI$0.20$0.20—256K
ministral-3-8b-instruct-2512Fireworks AI$0.20$0.20—256K
mistral-7bFireworks AI$0.20$0.20—33K
mistral-7b-instruct-4kFireworks AI$0.20$0.20—33K
mistral-7b-instruct-v0p2Fireworks AI$0.20$0.20—33K
mistral-7b-instruct-v3Fireworks AI$0.20$0.20—33K
mistral-7b-v0p2Fireworks AI$0.20$0.20—33K
mistral-nemo-base-2407Fireworks AI$0.20$0.20—128K
mistral-nemo-instruct-2407Fireworks AI$0.20$0.20—128K
mythomax-l2-13bFireworks AI$0.20$0.20—4K
nous-capybara-7b-v1p9Fireworks AI$0.20$0.20—33K
nous-hermes-llama2-13bFireworks AI$0.20$0.20—4K
nous-hermes-llama2-7bFireworks AI$0.20$0.20—4K
nvidia-nemotron-nano-12b-v2Fireworks AI$0.20$0.20—128K
nvidia-nemotron-nano-9b-v2Fireworks AI$0.20$0.20—128K
openchat-3p5-0106-7bFireworks AI$0.20$0.20—8K
openhermes-2-mistral-7bFireworks AI$0.20$0.20—33K
openhermes-2p5-mistral-7bFireworks AI$0.20$0.20—33K
openorca-7bFireworks AI$0.20$0.20—33K
phi-3-vision-128k-instructFireworks AI$0.20$0.20—32K
pythia-12bFireworks AI$0.20$0.20—2K
qwen-v2p5-14b-instructFireworks AI$0.20$0.20—33K
qwen-v2p5-7bFireworks AI$0.20$0.20—131K
qwen2-7b-instructFireworks AI$0.20$0.20—33K
qwen2-vl-7b-instructFireworks AI$0.20$0.20—33K
qwen2p5-14bFireworks AI$0.20$0.20—131K
qwen2p5-7b-instructFireworks AI$0.20$0.20—33K
qwen2p5-coder-14bFireworks AI$0.20$0.20—33K
qwen2p5-coder-14b-instructFireworks AI$0.20$0.20—33K
qwen2p5-coder-7bFireworks AI$0.20$0.20—33K
qwen2p5-coder-7b-instructFireworks AI$0.20$0.20—33K
qwen2p5-vl-3b-instructFireworks AI$0.20$0.20—128K
qwen2p5-vl-7b-instructFireworks AI$0.20$0.20—128K
qwen3-14bFireworks AI$0.20$0.20—41K
qwen3-4bFireworks AI$0.20$0.20—41K
qwen3-4b-instruct-2507Fireworks AI$0.20$0.20—262K
qwen3-8bFireworks AI$0.20$0.20—41K
qwen3-vl-8b-instructFireworks AI$0.20$0.20—262K
rolm-ocrFireworks AI$0.20$0.20—128K
snorkel-mistral-7b-pairrm-dpoFireworks AI$0.20$0.20—33K
starcoder-16bFireworks AI$0.20$0.20—8K
starcoder-7bFireworks AI$0.20$0.20—8K
starcoder2-15bFireworks AI$0.20$0.20—16K
starcoder2-7bFireworks AI$0.20$0.20—16K
toppy-m-7bFireworks AI$0.20$0.20—33K
yi-6bFireworks AI$0.20$0.20—4K
zephyr-7b-betaFireworks AI$0.20$0.20—33K
glm-5p3-flashFireworks AI$0.15$0.50$0.031.04858M
glm-5p3-flashFireworks AI$0.15$0.50$0.031.04858M
gpt-oss-120bFireworks AI$0.15$0.60$0.01131K
llama4-scout-instruct-basicFireworks AI$0.15$0.60—131K
minimax-m3p1-flashFireworks AI$0.15$0.60$0.011.04858M
qwen3-30b-a3bFireworks AI$0.15$0.60—131K
qwen3-coder-30b-a3b-instructFireworks AI$0.15$0.60—262K
qwen3-vl-30b-a3b-instructFireworks AI$0.15$0.60—262K
qwen3-vl-30b-a3b-thinkingFireworks AI$0.15$0.60—262K
gpt-oss-120bFireworks AI$0.15$0.60$0.01131K
deepseek-v4-flash-0731Fireworks AI$0.22$0.66$0.0071.04858M
deepseek-v4-flash-vision-expFireworks AI$0.22$0.66$0.0071.04858M
deepseek-v4-flash-0731Fireworks AI$0.22$0.66$0.0071.04858M
deepseek-v4-flash-vision-expFireworks AI$0.22$0.66$0.0071.04858M
glm-5p3-flash-usFireworks AI$0.23$0.75$0.041.04858M
glm-5p3-flash-usFireworks AI$0.23$0.75$0.041.04858M
glm-4p5-airFireworks AI$0.22$0.88—131K
llama4-maverick-instruct-basicFireworks AI$0.22$0.88—131K
qwen3-235b-a22bFireworks AI$0.22$0.88—131K
qwen3-235b-a22b-instruct-2507Fireworks AI$0.22$0.88—262K
qwen3-235b-a22b-thinking-2507Fireworks AI$0.22$0.88—262K
qwen3-vl-235b-a22b-instructFireworks AI$0.22$0.88—262K
qwen3-vl-235b-a22b-thinkingFireworks AI$0.22$0.88—262K
deepseek-coder-v2-lite-baseFireworks AI$0.50$0.50—164K
deepseek-coder-v2-lite-instructFireworks AI$0.50$0.50—164K
deepseek-v2-lite-chatFireworks AI$0.50$0.50—164K
dolphin-2p6-mixtral-8x7bFireworks AI$0.50$0.50—33K
firefunction-v1Fireworks AI$0.50$0.50—33K
mixtral-8x7bFireworks AI$0.50$0.50—33K
mixtral-8x7b-instructFireworks AI$0.50$0.50—33K
mixtral-8x7b-instruct-hfFireworks AI$0.50$0.50—33K
nous-hermes-2-mixtral-8x7b-dpoFireworks AI$0.50$0.50—33K
qwen3-30b-a3b-instruct-2507Fireworks AI$0.50$0.50—262K
deepseek-v4p1-flashFireworks AI$0.30$1.20$0.0061.04858M
minimax-m2Fireworks AI$0.30$1.20—197K
minimax-m2p1Fireworks AI$0.30$1.20$0.03197K
minimax-m3Fireworks AI$0.30$1.20$0.06512K
deepseek-v4p1-flashFireworks AI$0.30$1.20$0.0061.04858M
minimax-m2p1Fireworks AI$0.30$1.20$0.03197K
minimax-m3Fireworks AI$0.30$1.20$0.06512K
muse-glimmer-30bFireworks AI$0.35$1.50$0.04131K
muse-glimmer-30bFireworks AI$0.35$1.50$0.04131K
qwen3p7-plusFireworks AI$0.40$1.60$0.08262K
qwen3p7-plusFireworks AI$0.40$1.60$0.08262K
deepseek-v4p1-flash-1017-usFireworks AI$0.45$1.80$0.0091.04858M
qwen3-coder-480b-a35b-instructFireworks AI$0.45$1.80—262K
deepseek-v4p1-flash-usFireworks AI$0.45$1.80$0.0091.04858M
deepseek-v4p1-flash-usFireworks AI$0.45$1.80$0.0091.04858M
deepseek-v3p1Fireworks AI$0.56$1.68—128K
deepseek-v3p1-terminusFireworks AI$0.56$1.68—128K
deepseek-v3p2Fireworks AI$0.56$1.68—164K
code-llama-34bFireworks AI$0.90$0.90—16K
code-llama-34b-instructFireworks AI$0.90$0.90—16K
code-llama-34b-pythonFireworks AI$0.90$0.90—16K
code-llama-70bFireworks AI$0.90$0.90—4K
code-llama-70b-instructFireworks AI$0.90$0.90—4K
code-llama-70b-pythonFireworks AI$0.90$0.90—4K
cogito-v1-preview-llama-70bFireworks AI$0.90$0.90—131K
cogito-v1-preview-qwen-32bFireworks AI$0.90$0.90—131K
deepseek-coder-33b-instructFireworks AI$0.90$0.90—16K
deepseek-r1-distill-llama-70bFireworks AI$0.90$0.90—131K
deepseek-r1-distill-qwen-32bFireworks AI$0.90$0.90—131K
deepseek-v3Fireworks AI$0.90$0.90—131K
devstral-small-2505Fireworks AI$0.90$0.90—131K
dobby-unhinged-llama-3-3-70b-newFireworks AI$0.90$0.90—131K
dolphin-2-9-2-qwen2-72bFireworks AI$0.90$0.90—131K
fare-20bFireworks AI$0.90$0.90—131K
firefunction-v2Fireworks AI$0.90$0.90—8K
gemma-3-27b-itFireworks AI$0.90$0.90—131K
internvl3-38bFireworks AI$0.90$0.90—16K
internvl3-78bFireworks AI$0.90$0.90—16K
kat-coderFireworks AI$0.90$0.90—262K
kat-dev-32bFireworks AI$0.90$0.90—131K
kat-dev-72b-expFireworks AI$0.90$0.90—131K
llama-v2-70b-chatFireworks AI$0.90$0.90—2K
llama-v3-70b-instructFireworks AI$0.90$0.90—8K
llama-v3-70b-instruct-hfFireworks AI$0.90$0.90—8K
llama-v3p1-70b-instructFireworks AI$0.90$0.90—131K
llama-v3p1-nemotron-70b-instructFireworks AI$0.90$0.90—131K
llama-v3p2-90b-vision-instructFireworks AI$0.90$0.90—131K
llama-v3p3-70b-instructFireworks AI$0.90$0.90—131K
llava-yi-34bFireworks AI$0.90$0.90—4K
mistral-small-24b-instruct-2501Fireworks AI$0.90$0.90—33K
nous-hermes-2-yi-34bFireworks AI$0.90$0.90—4K
nous-hermes-llama2-70bFireworks AI$0.90$0.90—4K
phind-code-llama-34b-python-v1Fireworks AI$0.90$0.90—16K
phind-code-llama-34b-v1Fireworks AI$0.90$0.90—16K
phind-code-llama-34b-v2Fireworks AI$0.90$0.90—16K
qwen-qwq-32b-previewFireworks AI$0.90$0.90—33K
qwen1p5-72b-chatFireworks AI$0.90$0.90—33K
qwen2-72b-instructFireworks AI$0.90$0.90—33K
qwen2-vl-72b-instructFireworks AI$0.90$0.90—33K
qwen2p5-32bFireworks AI$0.90$0.90—131K
qwen2p5-32b-instructFireworks AI$0.90$0.90—33K
qwen2p5-72bFireworks AI$0.90$0.90—131K
qwen2p5-72b-instructFireworks AI$0.90$0.90—33K
qwen2p5-coder-32bFireworks AI$0.90$0.90—33K
qwen2p5-coder-32b-instructFireworks AI$0.90$0.90—4K
qwen2p5-coder-32b-instruct-128kFireworks AI$0.90$0.90—131K
qwen2p5-coder-32b-instruct-32k-ropeFireworks AI$0.90$0.90—33K
qwen2p5-coder-32b-instruct-64kFireworks AI$0.90$0.90—66K
qwen2p5-math-72b-instructFireworks AI$0.90$0.90—4K
qwen2p5-vl-32b-instructFireworks AI$0.90$0.90—128K
qwen2p5-vl-72b-instructFireworks AI$0.90$0.90—128K
qwen3-30b-a3b-thinking-2507Fireworks AI$0.90$0.90—262K
qwen3-32bFireworks AI$0.90$0.90—131K
qwen3-coder-480b-instruct-bf16Fireworks AI$0.90$0.90—262K
qwen3-next-80b-a3b-instructFireworks AI$0.90$0.90—4K
qwen3-next-80b-a3b-thinkingFireworks AI$0.90$0.90—4K
qwen3-vl-32b-instructFireworks AI$0.90$0.90—4K
qwq-32bFireworks AI$0.90$0.90—131K
yi-34bFireworks AI$0.90$0.90—4K
yi-34b-200k-capybaraFireworks AI$0.90$0.90—200K
yi-34b-chatFireworks AI$0.90$0.90—4K
deepseek-r1-basicFireworks AI$0.55$2.19—164K
glm-4p5Fireworks AI$0.55$2.19—131K
glm-4p6Fireworks AI$0.55$2.19—203K
glm-4p7Fireworks AI$0.60$2.20$0.30203K
glm-4p7Fireworks AI$0.60$2.20$0.30203K
nemotron-3-ultra-nvfp4Fireworks AI$0.60$2.40$0.12262K
nemotron-3-ultra-nvfp4Fireworks AI$0.60$2.40$0.12262K
kimi-k2-instructFireworks AI$0.60$2.50—131K
kimi-k2-thinkingFireworks AI$0.60$2.50—262K
cogito-671b-v2-p1Fireworks AI$1.20$1.20—164K
dbrx-instructFireworks AI$1.20$1.20—33K
deepseek-coder-v2-instructFireworks AI$1.20$1.20—66K
deepseek-prover-v2Fireworks AI$1.20$1.20—164K
deepseek-v2p5Fireworks AI$1.20$1.20—33K
deepseek-v4-proFireworks AI$1.20$1.20$0.601.04858M
glm-4p5vFireworks AI$1.20$1.20—131K
kimi-k2p5Fireworks AI$0.60$3.00$0.10262K
mistral-large-3-fp8Fireworks AI$1.20$1.20—256K
mixtral-8x22bFireworks AI$1.20$1.20—66K
mixtral-8x22b-instructFireworks AI$1.20$1.20—66K
mixtral-8x22b-instruct-hfFireworks AI$1.20$1.20—66K
kimi-k2p5Fireworks AI$0.60$3.00$0.10262K
kimi-k2p6Fireworks AI$0.95$4.00$0.16262K
kimi-k2p7-codeFireworks AI$0.95$4.00$0.19262K
kimi-k2p6Fireworks AI$0.95$4.00$0.16262K
kimi-k2p7-codeFireworks AI$0.95$4.00$0.19262K
inklingFireworks AI$1.00$4.05$0.171.04858M
deepseek-v4-pro-0813Fireworks AI$1.32$3.96$0.041.04858M
deepseek-v4-pro-0813Fireworks AI$1.32$3.96$0.041.04858M
muse-spark-openFireworks AI$1.25$4.25$0.151.04858M
glm-5p1Fireworks AI$1.40$4.40$0.26203K
glm-5p2Fireworks AI$1.40$4.40$0.141.04858M
glm-5p3Fireworks AI$1.40$4.40$0.261.04858M
glm-5p1Fireworks AI$1.40$4.40$0.26203K
glm-5p2Fireworks AI$1.40$4.40$0.141.04858M
glm-5p3Fireworks AI$1.40$4.40$0.261.04858M
llama-v3p1-405b-instructFireworks AI$3.00$3.00—131K
qwen3p8-maxFireworks AI$2.00$6.00$0.25262K
yi-largeFireworks AI$3.00$3.00—33K
qwen3p8-maxFireworks AI$2.00$6.00$0.25262K
glm-5p2-fastFireworks AI$2.10$6.60$0.211.04858M
glm-5p2-fast-usFireworks AI$2.10$6.60$0.211.04858M
glm-5p3-fastFireworks AI$2.10$6.60$0.391.04858M
glm-5p3-usFireworks AI$2.10$6.60$0.391.04858M
glm-5p2-fastFireworks AI$2.10$6.60$0.211.04858M
glm-5p2-fast-usFireworks AI$2.10$6.60$0.211.04858M
glm-5p3-fastFireworks AI$2.10$6.60$0.391.04858M
glm-5p3-usFireworks AI$2.10$6.60$0.391.04858M
kimi-k2p7-code-fastFireworks AI$1.90$8.00$0.38262K
kimi-k2p7-code-fastFireworks AI$1.90$8.00$0.38262K
kimi-k2p6-fastFireworks AI$2.00$8.00$0.30262K
kimi-k2p6-fastFireworks AI$2.00$8.00$0.30262K
deepseek-r1Fireworks AI$3.00$8.00—164K
glm-5p1-fastFireworks AI$2.80$8.80$0.52203K
glm-5p1-fastFireworks AI$2.80$8.80$0.52203K
ember-1Fireworks AI$3.00$15.00$0.301.04858M
kimi-k3Fireworks AI$3.00$15.00$0.301.04858M
kimi-k3Fireworks AI$3.00$15.00$0.301.04858M
kimi-k3-fastFireworks AI$4.50$22.50$0.451.04858M
kimi-k3-usFireworks AI$4.50$22.50$0.451.04858M
kimi-k3-fastFireworks AI$4.50$22.50$0.451.04858M
kimi-k3-usFireworks AI$4.50$22.50$0.451.04858M

FAQ

How are prices shown?

In US dollars per 1 million tokens, as listed for each model's API. 'Blended' assumes 3 input tokens for every output token.

Which model is cheapest here?

nemotron-lightning-3p5-30b-a3b from Fireworks AI, at $0.05 per 1M input and $0.20 per 1M output tokens (as of ).

How current are these prices?

We copy the open-source LiteLLM price list once a day and record every change. Providers can change prices at any time, so confirm on the official pricing page linked from each model.