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
249
on this provider
Cheapest input
$0.07
per 1M tokens
Cheapest output
$0.10
per 1M tokens
Max context
1M
tokens
| Model ID | |||||
|---|---|---|---|---|---|
| gpt-oss-20b | OpenAI | 131K | $0.07 | $0.30 | fireworks_ai/accounts/fireworks/models/gpt-oss-20b |
| Llama V3p1 8B Instruct | Meta | 16K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct |
| Llama V3p2 3B Instruct | Meta | 16K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct |
| Cogito V1 Preview Llama 3B | Meta | 131K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-3b |
| 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 |
| Ernie 4p5 21B A3b Pt | Baidu | 4K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/ernie-4p5-21b-a3b-pt |
| Ernie 4p5 300B A47b Pt | Baidu | 4K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/ernie-4p5-300b-a47b-pt |
| Flux 1 Dev | Black Forest Labs | 4K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/flux-1-dev |
| 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 Guard 3 1B | Meta | 131K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/llama-guard-3-1b |
| Llama V2 70B | Meta | 4K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/llama-v2-70b |
| Llama V3p1 70B Instruct 1B | Meta | 4K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b |
| Phi 2 3B | Microsoft | 2K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/phi-2-3b |
| Phi 3 Mini 128k Instruct | Microsoft | 131K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/phi-3-mini-128k-instruct |
| Qwen2 VL 2B Instruct | Alibaba | 33K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/qwen2-vl-2b-instruct |
| Qwen2p5 0p5b Instruct | Alibaba | 33K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/qwen2p5-0p5b-instruct |
| Qwen2p5 1p5b Instruct | Alibaba | 33K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/qwen2p5-1p5b-instruct |
| Qwen2p5 Coder 0p5b | Alibaba | 33K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b |
| Qwen2p5 Coder 0p5b Instruct | Alibaba | 33K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b-instruct |
| 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 |
| Qwen2p5 Coder 3B | Alibaba | 33K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b |
| 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 |
| 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 |
| Qwen3 1p7b FP8 Draft 40960 | Alibaba | 41K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960 |
| 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 |
| Llama V3p1 405B Instruct Long | Meta | 4K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct-long |
| Llama V3p2 1B Instruct | Meta | 16K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct |
| Codegemma 2B | 8K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/codegemma-2b | |
| Nemotron Nano V2 12B VL | NVIDIA | 4K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/nemotron-nano-v2-12b-vl |
| Starcoder2 3B | BigCode | 16K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/starcoder2-3b |
| Ministral 3 3B Instruct 2512 | Mistral | 256K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/ministral-3-3b-instruct-2512 |
| Stablecode 3B | Other | 4K | $0.10 | $0.10 | fireworks_ai/accounts/fireworks/models/stablecode-3b |
| 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 30B A3B | Alibaba | 131K | $0.15 | $0.60 | fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b |
| 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 VL 30B A3B Thinking | Alibaba | 262K | $0.15 | $0.60 | fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-thinking |
| Code Llama 7B Instruct | Meta | 16K | $0.20 | $0.20 | fireworks_ai/accounts/fireworks/models/code-llama-7b-instruct |
| Code Llama 7B Python | Meta | 16K | $0.20 | $0.20 | fireworks_ai/accounts/fireworks/models/code-llama-7b-python |
| Code Qwen 1p5 7B | Alibaba | 66K | $0.20 | $0.20 | fireworks_ai/accounts/fireworks/models/code-qwen-1p5-7b |
| Codegemma 7B | 8K | $0.20 | $0.20 | fireworks_ai/accounts/fireworks/models/codegemma-7b |
1–50 of 249
Page 1 of 5
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