modelbenchmark.io
All hosts

fireworks_ai

249 models listed here. Prices are this host's, not the vendor list price.

ai-4-1b-to-16b—$0.20$0.20
ai-56b-to-176b—$1.20$1.20
ai-above-16b—$0.90$0.90
ai-default—freefree
ai-moe-up-to-56b—$0.50$0.50
ai-up-to-4b—$0.20$0.20
chronos-hermes-13b4K$0.20$0.20
code-llama-13b16K$0.20$0.20
code-llama-13b-instruct16K$0.20$0.20
code-llama-13b-python16K$0.20$0.20
code-llama-34b16K$0.90$0.90
code-llama-34b-instruct16K$0.90$0.90
code-llama-34b-python16K$0.90$0.90
code-llama-70b4K$0.90$0.90
code-llama-70b-instruct4K$0.90$0.90
code-llama-70b-python4K$0.90$0.90
code-llama-7b16K$0.20$0.20
code-llama-7b-instruct16K$0.20$0.20
code-llama-7b-python16K$0.20$0.20
code-qwen-1-5-7b66K$0.20$0.20
codegemma-2b8K$0.10$0.10
codegemma-7b8K$0.20$0.20
Cogito v1 Preview Qwen 32B131K$0.90$0.90
cogito-671b-v2-p1164K$1.20$1.20
cogito-v1-preview-llama-3b131K$0.10$0.10
cogito-v1-preview-llama-70b131K$0.90$0.90
cogito-v1-preview-llama-8b131K$0.20$0.20
cogito-v1-preview-qwen-14b131K$0.20$0.20
dbrx-instruct33K$1.20$1.20
DeepSeek R1 Distill Llama 8B131K$0.20$0.20
DeepSeek R1 Distill Qwen 1.5B131K$0.10$0.10
DeepSeek R1 Distill Qwen 14B131K$0.20$0.20
Deepseek R1 Distill Qwen 32B131K$0.90$0.90
DeepSeek R1 Distill Qwen 7B131K$0.20$0.20
DeepSeek V4 Flash1M$0.14$0.28
DeepSeek V4 Pro1M$1.74$3.48
deepseek-coder-1b-base16K$0.10$0.10
deepseek-coder-33b-instruct16K$0.90$0.90
deepseek-coder-7b-base4K$0.20$0.20
deepseek-coder-7b-instruct4K$0.20$0.20
deepseek-coder-v2-instruct66K$1.20$1.20
deepseek-coder-v2-lite-base164K$0.50$0.50
deepseek-coder-v2-lite-instruct164K$0.50$0.50
deepseek-prover164K$1.20$1.20
DeepSeek-R1128K$3.00$8.00
deepseek-r1-0528-distill-qwen3-8b131K$0.20$0.20
deepseek-r1-basic128K$0.55$2.19
deepseek-v2-lite-chat164K$0.50$0.50
DeepSeek/DeepSeek-V3.1-Terminus128K$0.56$1.68
DeepSeek/DeepSeek-V3.2-Exp128K$0.90$0.90
Devstral Small131K$0.90$0.90
dobby-mini-unhinged-plus-llama-3-1-8b131K$0.20$0.20
dobby-unhinged-llama-3-3-70b-new131K$0.90$0.90
dolphin-2-6-mixtral-8x7b33K$0.50$0.50
dolphin-2-9-2-qwen2-72b131K$0.90$0.90
ernie-4-5-21b-a3b-pt4K$0.10$0.10
ernie-4-5-300b-a47b-pt4K$0.10$0.10
fare-20b131K$0.90$0.90
firefunction8K$0.90$0.90
firellava-13b4K$0.20$0.20
firesearch-ocr8K$0.20$0.20
gemma-2b-it8K$0.10$0.10
gemma-3-27b-it131K$0.90$0.90
gemma-7b8K$0.20$0.20
gemma-7b-it8K$0.20$0.20
GLM 5.2 Fast1M$2.10$6.60
GLM-4.5128K$0.55$2.19
GLM-4.5-Air128K$0.22$0.88
GLM-4.5V131K$1.20$1.20
GLM-4.6203K$0.55$2.19
GLM-4.7203K$0.60$2.20
glm-5-1-fast203K$2.80$8.80
glm-5-2-fast-us1M$2.10$6.60
GLM-5.1203K$1.40$4.40
GLM-5.21M$1.40$4.40
GLM-5.31M$1.40$4.40
Google Gemma 28K$0.20$0.20
gpt-oss-120b131K$0.15$0.60
gpt-oss-20b131K$0.07$0.30
hermes-2-pro-mistral-7b33K$0.20$0.20
internvl3-38b16K$0.90$0.90
internvl3-78b16K$0.90$0.90
internvl3-8b16K$0.20$0.20
kat-coder262K$0.90$0.90
kat-dev-32b131K$0.90$0.90
kat-dev-72b131K$0.90$0.90
Kimi K2 0905131K$0.60$2.50
Kimi K2 Thinking262K$0.60$2.50
Kimi K2.5262K$0.60$3.00
Kimi K2.6262K$0.95$4.00
Kimi K2.6 Fast262K$2.00$8.00
Kimi K2.7 Code262K$0.95$4.00
Kimi K2.7 Code Fast262K$1.90$8.00
Kimi K31M$3.00$15.00
Kimi K3 Fast1M$4.50$22.50
kimi-k3-us1M$3.30$16.50
llama-v2-13b4K$0.20$0.20
llama-v2-13b-chat4K$0.20$0.20
llama-v2-70b4K$0.10$0.10
llama-v2-70b-chat2K$0.90$0.90
llama-v2-7b4K$0.20$0.20
llama-v2-7b-chat4K$0.20$0.20
llama-v3-1-405b-instruct128K$3.00$3.00
llama-v3-1-405b-instruct-long4K$0.10$0.10
llama-v3-1-70b-instruct131K$0.90$0.90
llama-v3-1-70b-instruct-1b4K$0.10$0.10
llama-v3-1-8b-instruct16K$0.10$0.10
llama-v3-1-nemotron-70b-instruct131K$0.90$0.90
llama-v3-2-11b-vision-instruct16K$0.20$0.20
llama-v3-2-1b131K$0.10$0.10
llama-v3-2-1b-instruct16K$0.10$0.10
llama-v3-2-3b131K$0.10$0.10
llama-v3-2-3b-instruct16K$0.10$0.10
llama-v3-2-90b-vision-instruct16K$0.90$0.90
llama-v3-3-70b-instruct131K$0.90$0.90
llama-v3-70b-instruct8K$0.90$0.90
llama-v3-70b-instruct-hf8K$0.90$0.90
llama-v3-8b8K$0.20$0.20
llama-v3-8b-instruct-hf8K$0.20$0.20
llama4-maverick-instruct-basic131K$0.22$0.88
llama4-scout-instruct-basic131K$0.15$0.60
llava-yi-34b4K$0.90$0.90
MiniMax M1 80K4K$0.10$0.10
MiniMax-M24K$0.30$1.20
MiniMax-M2.1205K$0.30$1.20
MiniMax-M2.7197K$0.30$1.20
MiniMax-M3512K$0.30$1.20
Ministral 3 14B Instruct256K$0.20$0.20
Ministral 3 3B256K$0.10$0.10
Ministral 3 8B256K$0.20$0.20
Mistral Nemo Instruct 2407128K$0.20$0.20
Mistral Small 333K$0.90$0.90
mistral-7b33K$0.20$0.20
mistral-7b-instruct-4k33K$0.20$0.20
Mistral-7B-Instruct-v0.333K$0.20$0.20
mistral-large-3-fp8256K$1.20$1.20
mistral-nemo-base128K$0.20$0.20
Mistral: Mixtral 8x22B Instruct66K$1.20$1.20
Mistral: Mixtral 8x7B Instruct33K$0.50$0.50
mixtral-8x22b66K$1.20$1.20
mixtral-8x22b-instruct-hf66K$1.20$1.20
mixtral-8x7b33K$0.50$0.50
mixtral-8x7b-instruct-hf33K$0.50$0.50
Muse Glimmer 30B131K$0.35$1.50
MythoMax 13B4K$0.20$0.20
nemotron-3-ultra-nvfp4262K$0.60$2.40
nemotron-lightning-3.5-30b-a3b262K$0.05$0.20
nemotron-nano-v2-12b-vl4K$0.10$0.10
nous-capybara-7b33K$0.20$0.20
nous-hermes-2-mixtral-8x7b-dpo33K$0.50$0.50
nous-hermes-2-yi-34b4K$0.90$0.90
nous-hermes-llama2-13b4K$0.20$0.20
nous-hermes-llama2-70b4K$0.90$0.90
nous-hermes-llama2-7b4K$0.20$0.20
nvidia-nemotron-nano-12b131K$0.20$0.20
nvidia-nemotron-nano-9b-v2131K$0.20$0.20
openchat-3-5-0106-7b8K$0.20$0.20
openhermes-2-5-mistral-7b33K$0.20$0.20
openhermes-2-mistral-7b33K$0.20$0.20
openorca-7b33K$0.20$0.20
phi-2-3b2K$0.10$0.10
phi-3-mini-128k-instruct131K$0.10$0.10
phi-3-vision-128k-instruct32K$0.20$0.20
phind-code-llama-34b16K$0.90$0.90
phind-code-llama-34b-python16K$0.90$0.90
pythia-12b2K$0.20$0.20
qwen-qwq-32b33K$0.90$0.90
qwen-v2-5-14b-instruct33K$0.20$0.20
qwen-v2-5-7b131K$0.20$0.20
qwen1-5-72b-chat33K$0.90$0.90
qwen2-5-0-5b-instruct33K$0.10$0.10
qwen2-5-1-5b-instruct33K$0.10$0.10
qwen2-5-14b131K$0.20$0.20
qwen2-5-32b131K$0.90$0.90
qwen2-5-72b131K$0.90$0.90
qwen2-5-coder-0-5b-instruct33K$0.10$0.10
qwen2-5-coder-1-5b33K$0.10$0.10
qwen2-5-coder-1-5b-instruct33K$0.10$0.10
qwen2-5-coder-14b33K$0.20$0.20
qwen2-5-coder-14b-instruct33K$0.20$0.20
qwen2-5-coder-32b33K$0.90$0.90
qwen2-5-coder-32b-instruct-128k131K$0.90$0.90
qwen2-5-coder-32b-instruct-32k-rope33K$0.90$0.90
qwen2-5-coder-32b-instruct-64k66K$0.90$0.90
qwen2-5-coder-3b33K$0.10$0.10
qwen2-5-coder-3b-instruct33K$0.10$0.10
qwen2-5-coder-7b33K$0.20$0.20
qwen2-5-vl-3b-instruct128K$0.20$0.20
qwen2-72b-instruct33K$0.90$0.90
qwen2-7b-instruct33K$0.20$0.20
qwen2-vl-2b-instruct33K$0.10$0.10
qwen2-vl-72b-instruct33K$0.90$0.90
qwen2-vl-7b-instruct33K$0.20$0.20
Qwen2.5 32B Instruct33K$0.90$0.90
Qwen2.5 72B Instruct33K$0.90$0.90
Qwen2.5 7B Instruct33K$0.20$0.20
Qwen2.5 VL 32B Instruct128K$0.90$0.90
Qwen2.5-Coder 32B Instruct4K$0.90$0.90
Qwen2.5-Coder 7B Instruct33K$0.20$0.20
Qwen2.5-Coder-0.5B33K$0.10$0.10
Qwen2.5-Math 72B Instruct4K$0.90$0.90
Qwen2.5-VL 72B Instruct128K$0.90$0.90
Qwen2.5-VL 7B Instruct128K$0.20$0.20
Qwen3 14B41K$0.20$0.20
Qwen3 235b A22B Instruct 2507262K$0.22$0.88
Qwen3 235B A22B Thinking 2507262K$0.22$0.88
Qwen3 235B-A22B131K$0.22$0.88
Qwen3 30B A3B131K$0.15$0.60
Qwen3 30b A3b Instruct 2507262K$0.50$0.50
Qwen3 30b A3b Thinking 2507262K$0.90$0.90
Qwen3 32B131K$0.90$0.90
Qwen3 4B Instruct262K$0.20$0.20
Qwen3 8B41K$0.20$0.20
Qwen3 VL 235B A22B Instruct262K$0.22$0.88
Qwen3 VL 235B A22B Thinking262K$0.22$0.88
Qwen3 VL 30B A3B Instruct262K$0.15$0.60
Qwen3 VL 32B Instruct4K$0.90$0.90
Qwen3 VL 8B Instruct4K$0.20$0.20
qwen3-0-6b41K$0.10$0.10
qwen3-1-7b131K$0.10$0.10
qwen3-1-7b-fp8-draft262K$0.10$0.10
qwen3-1-7b-fp8-draft-131072131K$0.10$0.10
qwen3-1-7b-fp8-draft-4096041K$0.10$0.10
qwen3-4b41K$0.20$0.20
Qwen3-Coder 30B-A3B Instruct262K$0.15$0.60
Qwen3-Coder 480B-A35B Instruct262K$0.45$1.80
qwen3-coder-480b-instruct-bf164K$0.90$0.90
Qwen3-Next 80B-A3B (Thinking)4K$0.90$0.90
Qwen3-Next 80B-A3B Instruct4K$0.90$0.90
Qwen3-Vl 30b A3b Thinking262K$0.15$0.60
Qwen3.7 Plus262K$0.40$1.60
Qwen3.8 Max262K$2.00$6.00
QwQ 32B131K$0.90$0.90
R1 Distill Llama 70B131K$0.90$0.90
rolm-ocr128K$0.20$0.20
snorkel-mistral-7b-pairrm-dpo33K$0.20$0.20
stablecode-3b4K$0.10$0.10
starcoder-16b8K$0.20$0.20
starcoder-7b8K$0.20$0.20
starcoder2-15b16K$0.20$0.20
starcoder2-3b16K$0.10$0.10
starcoder2-7b16K$0.20$0.20
toppy-m-7b33K$0.20$0.20
Yi Large33K$3.00$3.00
yi-34b4K$0.90$0.90
yi-34b-200k-capybara200K$0.90$0.90
yi-34b-chat4K$0.90$0.90
yi-6b4K$0.20$0.20
zephyr-7b33K$0.20$0.20