Fireworks AI LLM API pricing
Every model Fireworks AI serves, with its pricing per 1M tokens and the exact model ID to copy. Sorted cheapest input first. Verified against LiteLLM and OpenRouter daily.
Models served
261
on this provider
Cheapest input
$0.05
per 1M tokens
Cheapest output
$0.10
per 1M tokens
Max context
1M
tokens
| Model ID | |||||
|---|---|---|---|---|---|
| Nemotron Lightning 3p5 30B A3b | NVIDIA | 262K | $0.05 | $0.20 | fireworks_ai/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b |
| gpt-oss-20b | OpenAI | 131K | $0.07 | $0.30 | fireworks_ai/accounts/fireworks/models/gpt-oss-20b |
| Llama V3p2 3B Instruct | Meta | 16K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct |
| Llama V3p1 8B Instruct | Meta | 16K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct |
| Llama V3p2 1B Instruct | Meta | 16K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct |
| Cogito V1 Preview Llama 3B | Meta | 131K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-3b |
| Codegemma 2B | 8K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/codegemma-2b | |
| DeepSeek Coder 1B Base | DeepSeek | 16K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/deepseek-coder-1b-base |
| DeepSeek R1 Distill Qwen 1p5b | DeepSeek | 131K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b |
| Flux 1 Dev | Black Forest Labs | 4K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/flux-1-dev |
| Ernie 4p5 300B A47b Pt | Baidu | 4K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/ernie-4p5-300b-a47b-pt |
| Ernie 4p5 21B A3b Pt | Baidu | 4K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/ernie-4p5-21b-a3b-pt |
| Flux 1 Schnell | Black Forest Labs | 4K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/flux-1-schnell |
| Gemma 2B It | 8K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/gemma-2b-it | |
| Llama V3p1 405B Instruct Long | Meta | 4K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct-long |
| Llama V3p1 70B Instruct 1B | Meta | 4K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b |
| Llama V3p2 1B | Meta | 131K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/llama-v3p2-1b |
| Llama V3p2 3B | Meta | 131K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/llama-v3p2-3b |
| MiniMax M1 80k | MiniMax | 1M | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/minimax-m1-80k |
| Ministral 3 3B Instruct 2512 | Mistral | 256K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/ministral-3-3b-instruct-2512 |
| Llama Guard 3 1B | Meta | 131K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/llama-guard-3-1b |
| Qwen2p5 Coder 0p5b | Alibaba | 33K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b |
| Starcoder2 3B | BigCode | 16K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/starcoder2-3b |
| Qwen2p5 Coder 1p5b | Alibaba | 33K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b |
| Qwen2p5 Coder 1p5b Instruct | Alibaba | 33K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b-instruct |
| Llama V2 70B | Meta | 4K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/llama-v2-70b |
| Qwen2p5 Coder 3B | Alibaba | 33K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b |
| Qwen3 1p7b FP8 Draft 40960 | Alibaba | 41K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960 |
| Qwen2p5 Coder 3B Instruct | Alibaba | 33K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b-instruct |
| Qwen3 0p6b | Alibaba | 41K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/qwen3-0p6b |
| Qwen3 1p7b | Alibaba | 131K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/qwen3-1p7b |
| Qwen2p5 Coder 0p5b Instruct | Alibaba | 33K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b-instruct |
| Qwen2 VL 2B Instruct | Alibaba | 33K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/qwen2-vl-2b-instruct |
| Qwen2p5 1p5b Instruct | Alibaba | 33K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/qwen2p5-1p5b-instruct |
| Phi 2 3B | Microsoft | 2K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/phi-2-3b |
| Qwen3 1p7b FP8 Draft | Alibaba | 262K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft |
| Qwen3 1p7b FP8 Draft 131072 | Alibaba | 131K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-131072 |
| Qwen2p5 0p5b Instruct | Alibaba | 33K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/qwen2p5-0p5b-instruct |
| Nemotron Nano V2 12B VL | NVIDIA | 4K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/nemotron-nano-v2-12b-vl |
| Phi 3 Mini 128k Instruct | Microsoft | 131K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/phi-3-mini-128k-instruct |
| Stablecode 3B | Other | 4K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/stablecode-3b |
| DeepSeek V4 Flash 0423 | DeepSeek | 1M | $0.14 | $0.28 | fireworks_ai/accounts/fireworks/models/deepseek-v4-flash |
| DeepSeek V4 Flash 0731 | DeepSeek | 1M | $0.14 | $0.28 | fireworks_ai/deepseek-v4-flash-0731 |
| gpt-oss-120b | OpenAI | 131K | $0.15 | $0.60 | fireworks_ai/accounts/fireworks/models/gpt-oss-120b |
| Llama4 Scout Instruct Basic | Meta | 131K | $0.15 | $0.60 | fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic |
| Qwen3 VL 30B A3B Thinking | Alibaba | 262K | $0.15 | $0.60 | fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-thinking |
| Qwen3 Coder 30B A3B Instruct | Alibaba | 262K | $0.15 | $0.60 | fireworks_ai/accounts/fireworks/models/qwen3-coder-30b-a3b-instruct |
| Qwen3 VL 30B A3B Instruct | Alibaba | 262K | $0.15 | $0.60 | fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct |
| Qwen3 30B A3B | Alibaba | 131K | $0.15 | $0.60 | fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b |
| Llama V3p2 11B Vision Instruct | Meta | 16K | $0.20 | $0.20 | fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct |
1–50 of 261
Page 1 of 6
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI