Fireworks AI models & pricing
Fireworks AI hosts 342 models (318 with public pricing) covering 5 modalities. Fast inference for Llama, Qwen, DeepSeek, Mixtral and 200+ open-source models. Cheapest input starts at $0.008000/M tokens; the most premium goes up to $4.50/M. Use Future AGI's Agent Command Center to route any Fireworks AI model with cost-optimized fallback and unified observability.
342
chat 315
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| Nemotron Lightning 3.5 30B A3B Deprecates in 3d | $0.0500/M | $0.200/M | $0.0875/M | 262,144 | tools · reasoning |
| Nemotron Lightning 3.5 30B A3B Deprecates in 3d | $0.0500/M | $0.200/M | $0.0875/M | 262,144 | tools · reasoning |
| gpt-oss 20B | $0.0700/M | $0.300/M | $0.128/M | 131,072 | tools · reasoning |
| gpt-oss 20B | $0.0700/M | $0.300/M | $0.128/M | 131,072 | tools · reasoning |
| Codegemma 2B | $0.1000/M | $0.1000/M | $0.1000/M | 8,192 | |
| Cogito V1 preview Llama 3B | $0.1000/M | $0.1000/M | $0.1000/M | 131,072 | |
| DeepSeek Coder 1B Base | $0.1000/M | $0.1000/M | $0.1000/M | 16,384 | |
| DeepSeek R1 Distill Qwen 1 5B | $0.1000/M | $0.1000/M | $0.1000/M | 131,072 | |
| Ernie 4.5 21B A3B Pt | $0.1000/M | $0.1000/M | $0.1000/M | 131,072 | |
| Ernie 4.5 300B A47B Pt | $0.1000/M | $0.1000/M | $0.1000/M | 131,072 | |
| Gemma 2B IT | $0.1000/M | $0.1000/M | $0.1000/M | 8,192 | |
| Llama Guard 3 1B | $0.1000/M | $0.1000/M | $0.1000/M | 131,072 | |
| Llama V2 70B | $0.1000/M | $0.1000/M | $0.1000/M | 4,096 | |
| Llama V3.1 405B Instruct Long | $0.1000/M | $0.1000/M | $0.1000/M | 4,096 | |
| Llama V3.1 70B Instruct 1B | $0.1000/M | $0.1000/M | $0.1000/M | 4,096 | |
| Llama V3.1 8B Instruct | $0.1000/M | $0.1000/M | $0.1000/M | 131,072 | |
| Llama V3.2 1B | $0.1000/M | $0.1000/M | $0.1000/M | 131,072 | |
| Llama V3.2 1B Instruct | $0.1000/M | $0.1000/M | $0.1000/M | 131,072 | |
| Llama V3.2 3B | $0.1000/M | $0.1000/M | $0.1000/M | 131,072 | |
| Llama V3.2 3B Instruct | $0.1000/M | $0.1000/M | $0.1000/M | 131,072 | |
| MiniMax M1 80K | $0.1000/M | $0.1000/M | $0.1000/M | 4,096 | |
| Ministral 3 3B Instruct 2512 | $0.1000/M | $0.1000/M | $0.1000/M | 256,000 | |
| Nemotron nano V2 12B VL | $0.1000/M | $0.1000/M | $0.1000/M | 131,072 | |
| Phi 2 3B | $0.1000/M | $0.1000/M | $0.1000/M | 2,048 | |
| Phi 3 mini 128K Instruct | $0.1000/M | $0.1000/M | $0.1000/M | 131,072 | |
| Qwen2 VL 2B Instruct | $0.1000/M | $0.1000/M | $0.1000/M | 32,768 | |
| Qwen2.5 0 5B Instruct | $0.1000/M | $0.1000/M | $0.1000/M | 32,768 | |
| Qwen2.5 1 5B Instruct | $0.1000/M | $0.1000/M | $0.1000/M | 32,768 | |
| Qwen2.5 Coder 0 5B | $0.1000/M | $0.1000/M | $0.1000/M | 32,768 | |
| Qwen2.5 Coder 0 5B Instruct | $0.1000/M | $0.1000/M | $0.1000/M | 32,768 | |
| Qwen2.5 Coder 1 5B | $0.1000/M | $0.1000/M | $0.1000/M | 32,768 | |
| Qwen2.5 Coder 1 5B Instruct | $0.1000/M | $0.1000/M | $0.1000/M | 32,768 | |
| Qwen2.5 Coder 3B | $0.1000/M | $0.1000/M | $0.1000/M | 32,768 | |
| Qwen2.5 Coder 3B Instruct | $0.1000/M | $0.1000/M | $0.1000/M | 32,768 | |
| Qwen3.0 6B | $0.1000/M | $0.1000/M | $0.1000/M | 40,960 | |
| Qwen3.1 7B | $0.1000/M | $0.1000/M | $0.1000/M | 131,072 | |
| Qwen3.1 7B FP8 Draft | $0.1000/M | $0.1000/M | $0.1000/M | 262,144 | |
| Qwen3.1 7B FP8 Draft 131072 | $0.1000/M | $0.1000/M | $0.1000/M | 131,072 | |
| Qwen3.1 7B FP8 Draft 40960 | $0.1000/M | $0.1000/M | $0.1000/M | 40,960 | |
| Stablecode 3B | $0.1000/M | $0.1000/M | $0.1000/M | 4,096 | |
| Starcoder2 3B | $0.1000/M | $0.1000/M | $0.1000/M | 16,384 | |
| DeepSeek V4 Flash | $0.140/M | $0.280/M | $0.175/M | 1,048,576 | tools · reasoning |
| DeepSeek V4 Flash | $0.140/M | $0.280/M | $0.175/M | 1,048,576 | tools · reasoning |
| GLM 5.3 Flash | $0.150/M | $0.500/M | $0.238/M | 1,048,576 | tools · vision |
| gpt-oss 120B Deprecates in 3d | $0.150/M | $0.600/M | $0.262/M | 131,072 | tools · reasoning |
| Llama 4 Scout Instruct Basic | $0.150/M | $0.600/M | $0.262/M | 131,072 | |
| MiniMax M3.1 Flash | $0.150/M | $0.600/M | $0.262/M | 1,048,576 | tools · vision · reasoning |
| Qwen3 30B A3B | $0.150/M | $0.600/M | $0.262/M | 131,072 | |
| Qwen3 Coder 30B A3B Instruct | $0.150/M | $0.600/M | $0.262/M | 262,144 | |
| Qwen3 VL 30B A3B Instruct | $0.150/M | $0.600/M | $0.262/M | 262,144 | |
| Qwen3 VL 30B A3B Thinking | $0.150/M | $0.600/M | $0.262/M | 262,144 | |
| GLM 5.3 Flash | $0.150/M | $0.500/M | $0.238/M | 1,048,576 | tools · vision |
| gpt-oss 120B Deprecates in 3d | $0.150/M | $0.600/M | $0.262/M | 131,072 | tools · reasoning |
| Chronos Hermes 13B v2 | $0.200/M | $0.200/M | $0.200/M | 4,096 | |
| Code Llama 13B | $0.200/M | $0.200/M | $0.200/M | 16,384 | |
| Code Llama 13B Instruct | $0.200/M | $0.200/M | $0.200/M | 16,384 | |
| Code Llama 13B Python | $0.200/M | $0.200/M | $0.200/M | 16,384 | |
| Code Llama 7B | $0.200/M | $0.200/M | $0.200/M | 16,384 | |
| Code Llama 7B Instruct | $0.200/M | $0.200/M | $0.200/M | 16,384 | |
| Code Llama 7B Python | $0.200/M | $0.200/M | $0.200/M | 16,384 | |
| Code Qwen 1.5 7B | $0.200/M | $0.200/M | $0.200/M | 65,536 | |
| Codegemma 7B | $0.200/M | $0.200/M | $0.200/M | 8,192 | |
| Cogito V1 preview Llama 8B | $0.200/M | $0.200/M | $0.200/M | 131,072 | |
| Cogito V1 preview Qwen 14B | $0.200/M | $0.200/M | $0.200/M | 131,072 | |
| DeepSeek Coder 7B Base | $0.200/M | $0.200/M | $0.200/M | 4,096 | |
| DeepSeek Coder 7B Base v1.5 | $0.200/M | $0.200/M | $0.200/M | 4,096 | |
| DeepSeek Coder 7B Instruct v1.5 | $0.200/M | $0.200/M | $0.200/M | 4,096 | |
| DeepSeek R1 0528 Distill Qwen3 8B | $0.200/M | $0.200/M | $0.200/M | 131,072 | |
| DeepSeek R1 Distill Llama 8B | $0.200/M | $0.200/M | $0.200/M | 131,072 | |
| DeepSeek R1 Distill Qwen 14B | $0.200/M | $0.200/M | $0.200/M | 131,072 | |
| DeepSeek R1 Distill Qwen 7B | $0.200/M | $0.200/M | $0.200/M | 131,072 | |
| Dobby mini Unhinged Plus Llama 3.1 8B | $0.200/M | $0.200/M | $0.200/M | 131,072 | |
| Firellava 13B | $0.200/M | $0.200/M | $0.200/M | 4,096 | |
| Firesearch OCR v6 | $0.200/M | $0.200/M | $0.200/M | 8,192 | |
| Gemma 7B | $0.200/M | $0.200/M | $0.200/M | 8,192 | |
| Gemma 7B IT | $0.200/M | $0.200/M | $0.200/M | 8,192 | |
| Gemma2 9B IT | $0.200/M | $0.200/M | $0.200/M | 8,192 | |
| Hermes 2 Pro Mistral 7B | $0.200/M | $0.200/M | $0.200/M | 32,768 | |
| Internvl3 8B | $0.200/M | $0.200/M | $0.200/M | 16,384 | |
| Llama Guard 2 8B | $0.200/M | $0.200/M | $0.200/M | 8,192 | |
| Llama Guard 3 8B | $0.200/M | $0.200/M | $0.200/M | 131,072 | |
| Llama V2 13B | $0.200/M | $0.200/M | $0.200/M | 4,096 | |
| Llama V2 13B Chat | $0.200/M | $0.200/M | $0.200/M | 4,096 | |
| Llama V2 7B | $0.200/M | $0.200/M | $0.200/M | 4,096 | |
| Llama V2 7B Chat | $0.200/M | $0.200/M | $0.200/M | 4,096 | |
| Llama V3 8B | $0.200/M | $0.200/M | $0.200/M | 8,192 | |
| Llama V3 8B Instruct Hf | $0.200/M | $0.200/M | $0.200/M | 8,192 | |
| Llama V3.2 11B Vision Instruct | $0.200/M | $0.200/M | $0.200/M | 131,072 | vision |
| Llamaguard 7B | $0.200/M | $0.200/M | $0.200/M | 4,096 | |
| Ministral 3 14B Instruct 2512 | $0.200/M | $0.200/M | $0.200/M | 256,000 | |
| Ministral 3 8B Instruct 2512 | $0.200/M | $0.200/M | $0.200/M | 256,000 | |
| Mistral 7B | $0.200/M | $0.200/M | $0.200/M | 32,768 | |
| Mistral 7B Instruct 4K | $0.200/M | $0.200/M | $0.200/M | 32,768 | |
| Mistral 7B Instruct v0.2 | $0.200/M | $0.200/M | $0.200/M | 32,768 | |
| Mistral 7B Instruct v3 | $0.200/M | $0.200/M | $0.200/M | 32,768 | |
| Mistral 7B v0.2 | $0.200/M | $0.200/M | $0.200/M | 32,768 | |
| Mistral Nemo Base 2407 | $0.200/M | $0.200/M | $0.200/M | 128,000 | |
| Mistral Nemo Instruct 2407 | $0.200/M | $0.200/M | $0.200/M | 128,000 | |
| Mythomax L2 13B | $0.200/M | $0.200/M | $0.200/M | 4,096 | |
| Nous Capybara 7B v1.9 | $0.200/M | $0.200/M | $0.200/M | 32,768 | |
| Nous Hermes Llama 2 13B | $0.200/M | $0.200/M | $0.200/M | 4,096 | |
| Nous Hermes Llama 2 7B | $0.200/M | $0.200/M | $0.200/M | 4,096 | |
| Nvidia Nemotron nano 12B v2 | $0.200/M | $0.200/M | $0.200/M | 128,000 | |
| Nvidia Nemotron nano 9B v2 | $0.200/M | $0.200/M | $0.200/M | 128,000 | |
| Openchat 3.5 0106 7B | $0.200/M | $0.200/M | $0.200/M | 8,192 | |
| Openhermes 2 Mistral 7B | $0.200/M | $0.200/M | $0.200/M | 32,768 | |
| Openhermes 2.5 Mistral 7B | $0.200/M | $0.200/M | $0.200/M | 32,768 | |
| Openorca 7B | $0.200/M | $0.200/M | $0.200/M | 32,768 | |
| Phi 3 Vision 128K Instruct | $0.200/M | $0.200/M | $0.200/M | 32,064 | |
| Pythia 12B | $0.200/M | $0.200/M | $0.200/M | 2,048 | |
| Qwen V2.5 14B Instruct | $0.200/M | $0.200/M | $0.200/M | 32,768 | |
| Qwen V2.5 7B | $0.200/M | $0.200/M | $0.200/M | 131,072 | |
| Qwen2 7B Instruct | $0.200/M | $0.200/M | $0.200/M | 32,768 | |
| Qwen2 VL 7B Instruct | $0.200/M | $0.200/M | $0.200/M | 32,768 | |
| Qwen2.5 14B | $0.200/M | $0.200/M | $0.200/M | 131,072 | |
| Qwen2.5 7B Instruct | $0.200/M | $0.200/M | $0.200/M | 32,768 | |
| Qwen2.5 Coder 14B | $0.200/M | $0.200/M | $0.200/M | 32,768 | |
| Qwen2.5 Coder 14B Instruct | $0.200/M | $0.200/M | $0.200/M | 32,768 | |
| Qwen2.5 Coder 7B | $0.200/M | $0.200/M | $0.200/M | 32,768 | |
| Qwen2.5 Coder 7B Instruct | $0.200/M | $0.200/M | $0.200/M | 32,768 | |
| Qwen2.5 VL 3B Instruct | $0.200/M | $0.200/M | $0.200/M | 128,000 | |
| Qwen2.5 VL 7B Instruct | $0.200/M | $0.200/M | $0.200/M | 128,000 | |
| Qwen3 14B | $0.200/M | $0.200/M | $0.200/M | 40,960 | |
| Qwen3 4B | $0.200/M | $0.200/M | $0.200/M | 40,960 | |
| Qwen3 4B Instruct 2507 | $0.200/M | $0.200/M | $0.200/M | 262,144 | |
| Qwen3 8B | $0.200/M | $0.200/M | $0.200/M | 40,960 | reasoning |
| Qwen3 VL 8B Instruct | $0.200/M | $0.200/M | $0.200/M | 262,144 | |
| Rolm OCR | $0.200/M | $0.200/M | $0.200/M | 128,000 | |
| Snorkel Mistral 7B Pairrm DPO | $0.200/M | $0.200/M | $0.200/M | 32,768 | |
| Starcoder 16B | $0.200/M | $0.200/M | $0.200/M | 8,192 | |
| Starcoder 7B | $0.200/M | $0.200/M | $0.200/M | 8,192 | |
| Starcoder2 15B | $0.200/M | $0.200/M | $0.200/M | 16,384 | |
| Starcoder2 7B | $0.200/M | $0.200/M | $0.200/M | 16,384 | |
| Toppy M 7B | $0.200/M | $0.200/M | $0.200/M | 32,768 | |
| Yi 6B | $0.200/M | $0.200/M | $0.200/M | 4,096 | |
| Zephyr 7B beta | $0.200/M | $0.200/M | $0.200/M | 32,768 | |
| DeepSeek V4 Flash 0731 Deprecated | $0.220/M | $0.660/M | $0.330/M | 1,048,576 | tools · reasoning |
| DeepSeek V4 Flash Vision exp Deprecated | $0.220/M | $0.660/M | $0.330/M | 1,048,576 | tools · vision |
| GLM 4.5 Air | $0.220/M | $0.880/M | $0.385/M | 131,072 | tools · reasoning |
| Llama 4 Maverick Instruct Basic | $0.220/M | $0.880/M | $0.385/M | 131,072 | |
| Qwen3 235B A22B | $0.220/M | $0.880/M | $0.385/M | 131,072 | |
| Qwen3 235B A22B Instruct 2507 | $0.220/M | $0.880/M | $0.385/M | 262,144 | |
| Qwen3 235B A22B Thinking 2507 | $0.220/M | $0.880/M | $0.385/M | 262,144 | |
| Qwen3 VL 235B A22B Instruct | $0.220/M | $0.880/M | $0.385/M | 262,144 | |
| Qwen3 VL 235B A22B Thinking | $0.220/M | $0.880/M | $0.385/M | 262,144 | |
| DeepSeek V4 Flash 0731 Deprecated | $0.220/M | $0.660/M | $0.330/M | 1,048,576 | tools · reasoning |
| DeepSeek V4 Flash Vision exp Deprecated | $0.220/M | $0.660/M | $0.330/M | 1,048,576 | tools · vision |
| GLM 5.3 Flash (router · US) Deprecates in 3d | $0.225/M | $0.750/M | $0.356/M | 1,048,576 | tools · vision |
| GLM 5.3 Flash Us Deprecates in 3d | $0.225/M | $0.750/M | $0.356/M | 1,048,576 | tools · vision |
| DeepSeek V4.1 Flash | $0.300/M | $1.20/M | $0.525/M | 1,048,576 | tools · vision · reasoning · cache |
| DeepSeek V4.1 Flash 1017 | $0.300/M | $1.20/M | $0.525/M | 1,048,576 | tools · vision · reasoning · cache |
| MiniMax M2 | $0.300/M | $1.20/M | $0.525/M | 196,608 | |
| MiniMax M2.1 | $0.300/M | $1.20/M | $0.525/M | 196,608 | tools |
| MiniMax M3 | $0.300/M | $1.20/M | $0.525/M | 512,000 | tools · reasoning |
| DeepSeek V4.1 Flash | $0.300/M | $1.20/M | $0.525/M | 1,048,576 | tools · vision · reasoning · cache |
| MiniMax M2.1 | $0.300/M | $1.20/M | $0.525/M | 196,608 | tools |
| MiniMax M2.7 | $0.300/M | $1.20/M | $0.525/M | 196,608 | tools · reasoning |
| MiniMax M3 | $0.300/M | $1.20/M | $0.525/M | 512,000 | tools · reasoning |
| Muse Glimmer 30B Deprecated | $0.350/M | $1.50/M | $0.638/M | 131,072 | tools · vision · reasoning |
| Muse Glimmer 30B Deprecated | $0.350/M | $1.50/M | $0.638/M | 131,072 | tools · vision · reasoning |
| Qwen3.7 Plus | $0.400/M | $1.60/M | $0.700/M | 262,144 | tools · vision · reasoning |
| Qwen3.7 Plus | $0.400/M | $1.60/M | $0.700/M | 262,144 | tools · vision · reasoning |
| DeepSeek V4.1 Flash 1017 Us | $0.450/M | $1.80/M | $0.787/M | 1,048,576 | tools · vision · reasoning · cache |
| Qwen3 Coder 480B A35B Instruct | $0.450/M | $1.80/M | $0.787/M | 262,144 | reasoning |
| DeepSeek V4.1 Flash (router · US) | $0.450/M | $1.80/M | $0.787/M | 1,048,576 | tools · vision · reasoning · cache |
| DeepSeek V4.1 Flash Us | $0.450/M | $1.80/M | $0.787/M | 1,048,576 | tools · vision · reasoning · cache |
| DeepSeek Coder V2 Lite Base | $0.500/M | $0.500/M | $0.500/M | 163,840 | |
| DeepSeek Coder V2 Lite Instruct | $0.500/M | $0.500/M | $0.500/M | 163,840 | |
| DeepSeek V2 Lite Chat | $0.500/M | $0.500/M | $0.500/M | 163,840 | |
| Dolphin 2.6 Mixtral 8×7B | $0.500/M | $0.500/M | $0.500/M | 32,768 | |
| Firefunction v1 | $0.500/M | $0.500/M | $0.500/M | 32,768 | |
| gpt-oss Safeguard 20B | $0.500/M | $0.500/M | $0.500/M | 131,072 | |
| Mixtral 8×7B | $0.500/M | $0.500/M | $0.500/M | 32,768 | |
| Mixtral 8×7B Instruct | $0.500/M | $0.500/M | $0.500/M | 32,768 | |
| Mixtral 8×7B Instruct Hf | $0.500/M | $0.500/M | $0.500/M | 32,768 | |
| Nous Hermes 2 Mixtral 8×7B DPO | $0.500/M | $0.500/M | $0.500/M | 32,768 | |
| Qwen3 30B A3B Instruct 2507 | $0.500/M | $0.500/M | $0.500/M | 262,144 | |
| DeepSeek R1 Basic | $0.550/M | $2.19/M | $0.960/M | 163,840 | |
| GLM 4.5 | $0.550/M | $2.19/M | $0.960/M | 131,072 | tools · reasoning |
| GLM 4.6 | $0.550/M | $2.19/M | $0.960/M | 202,752 | tools · reasoning |
| DeepSeek v3.1 | $0.560/M | $1.68/M | $0.840/M | 128,000 | reasoning |
| DeepSeek V3.1 Terminus | $0.560/M | $1.68/M | $0.840/M | 128,000 | reasoning |
| DeepSeek v3.2 | $0.560/M | $1.68/M | $0.840/M | 163,840 | tools · reasoning |
| GLM 4.7 | $0.600/M | $2.20/M | $1.00/M | 202,752 | tools · reasoning |
| Kimi K2 Instruct | $0.600/M | $2.50/M | $1.08/M | 131,072 | tools |
| Kimi K2 Instruct 0905 | $0.600/M | $2.50/M | $1.08/M | 262,144 | tools |
| Kimi K2 Thinking | $0.600/M | $2.50/M | $1.08/M | 262,144 | tools |
| Kimi K2.5 | $0.600/M | $3.00/M | $1.20/M | 262,144 | tools |
| Nemotron 3 Ultra Nvfp4 Deprecates in 3d | $0.600/M | $2.40/M | $1.05/M | 262,144 | tools · reasoning |
| GLM 4.7 | $0.600/M | $2.20/M | $1.00/M | 202,752 | tools · reasoning |
| Kimi K2.5 | $0.600/M | $3.00/M | $1.20/M | 262,144 | tools |
| Nemotron 3 Ultra Nvfp4 Deprecates in 3d | $0.600/M | $2.40/M | $1.05/M | 262,144 | tools · reasoning |
| Code Llama 34B | $0.900/M | $0.900/M | $0.900/M | 16,384 | |
| Code Llama 34B Instruct | $0.900/M | $0.900/M | $0.900/M | 16,384 | |
| Code Llama 34B Python | $0.900/M | $0.900/M | $0.900/M | 16,384 | |
| Code Llama 70B | $0.900/M | $0.900/M | $0.900/M | 4,096 | |
| Code Llama 70B Instruct | $0.900/M | $0.900/M | $0.900/M | 4,096 | |
| Code Llama 70B Python | $0.900/M | $0.900/M | $0.900/M | 4,096 | |
| Cogito V1 preview Llama 70B | $0.900/M | $0.900/M | $0.900/M | 131,072 | |
| Cogito V1 preview Qwen 32B | $0.900/M | $0.900/M | $0.900/M | 131,072 | |
| DeepSeek Coder 33B Instruct | $0.900/M | $0.900/M | $0.900/M | 16,384 | |
| DeepSeek R1 Distill Llama 70B | $0.900/M | $0.900/M | $0.900/M | 131,072 | |
| DeepSeek R1 Distill Qwen 32B | $0.900/M | $0.900/M | $0.900/M | 131,072 | |
| DeepSeek V3 | $0.900/M | $0.900/M | $0.900/M | 131,072 | |
| DeepSeek v3.0324 | $0.900/M | $0.900/M | $0.900/M | 163,840 | |
| Devstral Small 2505 | $0.900/M | $0.900/M | $0.900/M | 131,072 | |
| Dobby Unhinged Llama 3.3 70B New | $0.900/M | $0.900/M | $0.900/M | 131,072 | |
| Dolphin 2.9 2 Qwen2 72B | $0.900/M | $0.900/M | $0.900/M | 131,072 | |
| Fare 20B | $0.900/M | $0.900/M | $0.900/M | 131,072 | |
| Firefunction v2 | $0.900/M | $0.900/M | $0.900/M | 8,192 | tools |
| Gemma 3 27B IT | $0.900/M | $0.900/M | $0.900/M | 131,072 | |
| Internvl3 38B | $0.900/M | $0.900/M | $0.900/M | 16,384 | |
| Internvl3 78B | $0.900/M | $0.900/M | $0.900/M | 16,384 | |
| Kat Coder | $0.900/M | $0.900/M | $0.900/M | 262,144 | |
| Kat Dev 32B | $0.900/M | $0.900/M | $0.900/M | 131,072 | |
| Kat Dev 72B exp | $0.900/M | $0.900/M | $0.900/M | 131,072 | |
| Llama V2 70B Chat | $0.900/M | $0.900/M | $0.900/M | 2,048 | |
| Llama V3 70B Instruct | $0.900/M | $0.900/M | $0.900/M | 8,192 | |
| Llama V3 70B Instruct Hf | $0.900/M | $0.900/M | $0.900/M | 8,192 | |
| Llama V3.1 70B Instruct | $0.900/M | $0.900/M | $0.900/M | 131,072 | |
| Llama V3.1 Nemotron 70B Instruct | $0.900/M | $0.900/M | $0.900/M | 131,072 | |
| Llama V3.2 90B Vision Instruct | $0.900/M | $0.900/M | $0.900/M | 131,072 | vision |
| Llama V3.3 70B Instruct | $0.900/M | $0.900/M | $0.900/M | 131,072 | |
| Llava Yi 34B | $0.900/M | $0.900/M | $0.900/M | 4,096 | |
| Mistral Small 24B Instruct 2501 | $0.900/M | $0.900/M | $0.900/M | 32,768 | |
| Nous Hermes 2 Yi 34B | $0.900/M | $0.900/M | $0.900/M | 4,096 | |
| Nous Hermes Llama 2 70B | $0.900/M | $0.900/M | $0.900/M | 4,096 | |
| Phind Code Llama 34B Python v1 | $0.900/M | $0.900/M | $0.900/M | 16,384 | |
| Phind Code Llama 34B v1 | $0.900/M | $0.900/M | $0.900/M | 16,384 | |
| Phind Code Llama 34B v2 | $0.900/M | $0.900/M | $0.900/M | 16,384 | |
| QwQ 32B preview | $0.900/M | $0.900/M | $0.900/M | 32,768 | |
| Qwen1.5 72B Chat | $0.900/M | $0.900/M | $0.900/M | 32,768 | |
| Qwen2 72B Instruct | $0.900/M | $0.900/M | $0.900/M | 32,768 | |
| Qwen2 VL 72B Instruct | $0.900/M | $0.900/M | $0.900/M | 32,768 | |
| Qwen2.5 32B | $0.900/M | $0.900/M | $0.900/M | 131,072 | |
| Qwen2.5 32B Instruct | $0.900/M | $0.900/M | $0.900/M | 32,768 | |
| Qwen2.5 72B | $0.900/M | $0.900/M | $0.900/M | 131,072 | |
| Qwen2.5 72B Instruct | $0.900/M | $0.900/M | $0.900/M | 32,768 | |
| Qwen2.5 Coder 32B | $0.900/M | $0.900/M | $0.900/M | 32,768 | |
| Qwen2.5 Coder 32B Instruct | $0.900/M | $0.900/M | $0.900/M | 4,096 | |
| Qwen2.5 Coder 32B Instruct 128K | $0.900/M | $0.900/M | $0.900/M | 131,072 | |
| Qwen2.5 Coder 32B Instruct 32K Rope | $0.900/M | $0.900/M | $0.900/M | 32,768 | |
| Qwen2.5 Coder 32B Instruct 64K | $0.900/M | $0.900/M | $0.900/M | 65,536 | |
| Qwen2.5 Math 72B Instruct | $0.900/M | $0.900/M | $0.900/M | 4,096 | |
| Qwen2.5 VL 32B Instruct | $0.900/M | $0.900/M | $0.900/M | 128,000 | |
| Qwen2.5 VL 72B Instruct | $0.900/M | $0.900/M | $0.900/M | 128,000 | |
| Qwen3 30B A3B Thinking 2507 | $0.900/M | $0.900/M | $0.900/M | 262,144 | |
| Qwen3 32B | $0.900/M | $0.900/M | $0.900/M | 131,072 | reasoning |
| Qwen3 Coder 480B Instruct BF16 | $0.900/M | $0.900/M | $0.900/M | 262,144 | |
| Qwen3 Next 80B A3B Instruct | $0.900/M | $0.900/M | $0.900/M | 4,096 | |
| Qwen3 Next 80B A3B Thinking | $0.900/M | $0.900/M | $0.900/M | 4,096 | |
| Qwen3 VL 32B Instruct | $0.900/M | $0.900/M | $0.900/M | 4,096 | |
| QwQ 32B | $0.900/M | $0.900/M | $0.900/M | 131,072 | |
| Yi 34B | $0.900/M | $0.900/M | $0.900/M | 4,096 | |
| Yi 34B 200K Capybara | $0.900/M | $0.900/M | $0.900/M | 200,000 | |
| Yi 34B Chat | $0.900/M | $0.900/M | $0.900/M | 4,096 | |
| Kimi K2.6 Deprecated | $0.950/M | $4.00/M | $1.71/M | 262,144 | tools · vision · reasoning |
| Kimi K2.7 Code Deprecated | $0.950/M | $4.00/M | $1.71/M | 262,144 | tools · vision · reasoning |
| Kimi K2.6 Deprecated | $0.950/M | $4.00/M | $1.71/M | 262,144 | tools · vision · reasoning |
| Kimi K2.7 Code Deprecated | $0.950/M | $4.00/M | $1.71/M | 262,144 | tools · vision · reasoning |
| Inkling Deprecates in 3d | $1.00/M | $4.05/M | $1.76/M | 1,048,576 | tools · vision |
| Cogito 671B V2 P1 | $1.20/M | $1.20/M | $1.20/M | 163,840 | |
| DBRX Instruct | $1.20/M | $1.20/M | $1.20/M | 32,768 | |
| DeepSeek Coder V2 Instruct | $1.20/M | $1.20/M | $1.20/M | 65,536 | |
| DeepSeek Prover v2 | $1.20/M | $1.20/M | $1.20/M | 163,840 | |
| DeepSeek V2.5 | $1.20/M | $1.20/M | $1.20/M | 32,768 | |
| DeepSeek V4 Pro Deprecated | $1.20/M | $1.20/M | $1.20/M | 1,048,576 | tools · reasoning |
| GLM 4.5v | $1.20/M | $1.20/M | $1.20/M | 131,072 | reasoning |
| gpt-oss Safeguard 120B | $1.20/M | $1.20/M | $1.20/M | 131,072 | |
| Mistral Large 3 FP8 | $1.20/M | $1.20/M | $1.20/M | 256,000 | |
| Mixtral 8×22B | $1.20/M | $1.20/M | $1.20/M | 65,536 | |
| Mixtral 8×22B Instruct | $1.20/M | $1.20/M | $1.20/M | 65,536 | |
| Mixtral 8×22B Instruct Hf | $1.20/M | $1.20/M | $1.20/M | 65,536 | tools |
| Muse Spark Open | $1.25/M | $4.25/M | $2.00/M | 1,048,576 | tools · vision · reasoning |
| DeepSeek V4 Pro 0813 Deprecated | $1.32/M | $3.96/M | $1.98/M | 1,048,576 | tools · reasoning |
| DeepSeek V4 Pro 0813 Deprecated | $1.32/M | $3.96/M | $1.98/M | 1,048,576 | tools · reasoning |
| GLM 5.1 | $1.40/M | $4.40/M | $2.15/M | 202,752 | tools · reasoning |
| GLM 5.2 Deprecated | $1.40/M | $4.40/M | $2.15/M | 1,048,576 | tools · reasoning |
| GLM 5.3 | $1.40/M | $4.40/M | $2.15/M | 1,048,576 | tools · reasoning |
| GLM 5.1 | $1.40/M | $4.40/M | $2.15/M | 202,752 | tools · reasoning |
| GLM 5.2 Deprecated | $1.40/M | $4.40/M | $2.15/M | 1,048,576 | tools · reasoning |
| GLM 5.3 | $1.40/M | $4.40/M | $2.15/M | 1,048,576 | tools · reasoning |
| DeepSeek V4 Pro | $1.74/M | $3.48/M | $2.18/M | 1,048,576 | tools · reasoning |
| Kimi K2.7 Code Fast (router) Deprecated | $1.90/M | $8.00/M | $3.43/M | 262,144 | tools · vision · reasoning |
| Kimi K2.7 Code Fast Deprecated | $1.90/M | $8.00/M | $3.43/M | 262,144 | tools · vision · reasoning |
| Qwen3.8 Max | $2.00/M | $6.00/M | $3.00/M | 262,144 | tools · vision · reasoning |
| Kimi K2.6 Fast (router) Deprecated | $2.00/M | $8.00/M | $3.50/M | 262,144 | tools · vision · reasoning |
| Kimi K2.6 Fast Deprecated | $2.00/M | $8.00/M | $3.50/M | 262,144 | tools · vision · reasoning |
| Qwen3.8 Max | $2.00/M | $6.00/M | $3.00/M | 262,144 | tools · vision · reasoning |
| GLM 5.2 Fast (router) Deprecated | $2.10/M | $6.60/M | $3.22/M | 1,048,576 | tools · reasoning |
| GLM 5.2 Fast (router · US) Deprecated | $2.10/M | $6.60/M | $3.22/M | 1,048,576 | tools · reasoning |
| GLM 5.3 Fast (router) | $2.10/M | $6.60/M | $3.22/M | 1,048,576 | tools · reasoning |
| GLM 5.3 (router · US) | $2.10/M | $6.60/M | $3.22/M | 1,048,576 | tools · reasoning |
| GLM 5.2 Fast Deprecated | $2.10/M | $6.60/M | $3.22/M | 1,048,576 | tools · reasoning |
| GLM 5.2 Fast Us Deprecated | $2.10/M | $6.60/M | $3.22/M | 1,048,576 | tools · reasoning |
| GLM 5.3 Fast | $2.10/M | $6.60/M | $3.22/M | 1,048,576 | tools · reasoning |
| GLM 5.3 Us | $2.10/M | $6.60/M | $3.22/M | 1,048,576 | tools · reasoning |
| GLM 5.1 Fast (router) | $2.80/M | $8.80/M | $4.30/M | 202,800 | tools · reasoning |
| GLM 5.1 Fast | $2.80/M | $8.80/M | $4.30/M | 202,800 | tools · reasoning |
| DeepSeek R1 | $3.00/M | $8.00/M | $4.25/M | 163,840 | |
| DeepSeek R1 0528 | $3.00/M | $8.00/M | $4.25/M | 163,840 | |
| Ember 1 | $3.00/M | $15.00/M | $6.00/M | 1,048,576 | tools · vision · reasoning |
| Kimi K3 | $3.00/M | $15.00/M | $6.00/M | 1,048,576 | tools · vision · reasoning |
| Llama V3.1 405B Instruct | $3.00/M | $3.00/M | $3.00/M | 131,072 | tools |
| Yi Large | $3.00/M | $3.00/M | $3.00/M | 32,768 | |
| Kimi K3 | $3.00/M | $15.00/M | $6.00/M | 1,048,576 | tools · vision · reasoning |
| Kimi K3 Fast (router) | $4.50/M | $22.50/M | $9.00/M | 1,048,576 | tools · vision · reasoning |
| Kimi K3 (router · US) | $4.50/M | $22.50/M | $9.00/M | 1,048,576 | tools · vision · reasoning |
| Kimi K3 Fast | $4.50/M | $22.50/M | $9.00/M | 1,048,576 | tools · vision · reasoning |
| Kimi K3 Us | $4.50/M | $22.50/M | $9.00/M | 1,048,576 | tools · vision · reasoning |
| Auto (router) | — | — | — | — | tools · reasoning |
| Auto Instant (router) | — | — | — | — | tools · reasoning |
| FireRouter | — | — | — | — | tools · reasoning |
| Flux 1 Dev Controlnet Union | — | — | — | 4,096 | |
| MiniMax M2.7 Deprecated | — | — | — | 196,608 | tools |
image generation 11
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| Flux 1 Dev | — | — | — | 4,096 | |
| Flux 1 Dev FP8 | — | — | — | 4,096 | |
| Flux 1 Schnell | — | — | — | 4,096 | |
| Flux 1 Schnell FP8 | — | — | — | 4,096 | |
| Flux Kontext Max | — | — | — | 4,096 | |
| Flux Kontext Pro | — | — | — | 4,096 | |
| Japanese Stable Diffusion Xl | — | — | — | 4,096 | |
| Playground V2 1024px Aesthetic | — | — | — | 4,096 | |
| Playground V2.5 1024px Aesthetic | — | — | — | 4,096 | |
| Ssd 1B | — | — | — | 4,096 | |
| Stable Diffusion Xl 1024 v1.0 | — | — | — | 4,096 |
embedding 9
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| Nomic AI Nomic Embed Text v1 | $0.008000/M | — | — | 8,192 | |
| Nomic AI Nomic Embed Text v1.5 | $0.008000/M | — | — | 8,192 | |
| Thenlper GTE Base | $0.008000/M | — | — | 512 | |
| Thenlper GTE Large | $0.0160/M | — | — | 512 | |
| Whereisai Uae Large v1 | $0.0160/M | — | — | 512 | |
| Fireworks models (account path) | $0.1000/M | — | — | 40,960 | |
| Qwen3 Embedding 8B | $0.1000/M | — | — | 40,960 | |
| Qwen3 Embedding 0 6B | — | — | — | 32,768 | |
| Qwen3 Embedding 4B | — | — | — | 40,960 |
audio transcription 4
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| Fireworks Asr Large | — | — | — | 4,096 | |
| Fireworks Asr v2 | — | — | — | 4,096 | |
| Whisper v3 | — | — | — | 4,096 | |
| Whisper V3 Turbo | — | — | — | 4,096 |
rerank 3
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| Qwen3 Reranker 8B | $0.200/M | — | — | 40,960 | |
| Qwen3 Reranker 0 6B | — | — | — | 40,960 | |
| Qwen3 Reranker 4B | — | — | — | 40,960 |
FAQ
How many Fireworks AI models are there?
342 Fireworks AI models are listed across 5 modalities on this page. 318 have public per-token pricing.
How is Fireworks AI pricing verified?
Pricing is aggregated from BerriAI/litellm, models.dev, and OpenRouter and refreshed weekly. Each row shows a per-model "verified" date. If a price is wrong, click the row to open the model page and use the inline "suggest edit" link — submissions go into a public review queue.
Which Fireworks AI model is cheapest?
Input pricing on Fireworks AI starts at $0.008000 per 1M tokens. Sort the table by price (or use the in-page filter at the top) to find the cheapest model that matches your capability requirements.
Can I route to Fireworks AI via an OpenAI-compatible API?
Yes — point your OpenAI client at Future AGI's Agent Command Center, configure a Fireworks AI target, and call Fireworks AI models with the standard /v1/chat/completions surface. The same gateway can route to other providers as fallback. Free for the first 100K requests/month.
Route any Fireworks AI model via Agent Command Center →
OpenAI-compatible endpoint. Caching, fallback, guardrails, observability. Free for 100K requests/month.