Price Per TokenPrice Per Token
Fireworks AI

Fireworks AI Pricing

Compare Fireworks AI pricing for 245 models. Includes serverless, batch, and cache pricing across LLMs, image generation, and speech models.

Last updated: Feb 25, 2026

Fireworks AI Overview

245
Total Models
229
LLMs
6
Image Models
10
Audio & Embedding
$0.07
Cheapest LLM Input/1M

Fireworks AI Model Pricing

Provider
Model
Tier
Context
Input/1M
Output/1M
Cache Read/1M
Batch In/1M
Batch Out/1M
custom
131k
$0.070
$0.300
$0.04
$0.04
$0.15
CodeGemma 2B
<4B
8k
$0.100
$0.100
$0.05
$0.05
$0.05
Cogito v1 Preview Llama 3B
<4B
131k
$0.100
$0.100
$0.05
$0.05
$0.05
DeepSeek Coder 1.3B Base
<4B
16k
$0.100
$0.100
$0.05
$0.05
$0.05
Gemma 2B
<4B
8k
$0.100
$0.100
$0.05
$0.05
$0.05
Llama Guard 3 1B
<4B
131k
$0.100
$0.100
$0.05
$0.05
$0.05
Llama 3.2 1B
<4B
131k
$0.100
$0.100
$0.05
$0.05
$0.05
<4B
131k
$0.100
$0.100
$0.05
$0.05
$0.05
Llama 3.2 3B
<4B
131k
$0.100
$0.100
$0.05
$0.05
$0.05
<4B
131k
$0.100
$0.100
$0.05
$0.05
$0.05
<4B
256k
$0.100
$0.100
$0.05
$0.05
$0.05
Qwen2.5 Coder 3B
<4B
33k
$0.100
$0.100
$0.05
$0.05
$0.05
Qwen2.5 Coder 3B Instruct
<4B
33k
$0.100
$0.100
$0.05
$0.05
$0.05
Qwen2.5 VL 3B Instruct
<4B
128k
$0.100
$0.100
$0.05
$0.05
$0.05
Qwen2 VL 2B Instruct
<4B
33k
$0.100
$0.100
$0.05
$0.05
$0.05
custom
131k
$0.150
$0.600
$0.07
$0.07
$0.30
GPT-OSS Safeguard 120B
custom
131k
$0.150
$0.600
$0.07
$0.07
$0.30
custom
131k
$0.150
$0.600
$0.07
$0.07
$0.30
custom
262k
$0.150
$0.600
$0.07
$0.07
$0.30
custom
262k
$0.150
$0.600
$0.07
$0.07
$0.30
Chronos Hermes 13B v2
4B-16B
4k
$0.200
$0.200
$0.10
$0.10
$0.10
CodeGemma 7B
4B-16B
8k
$0.200
$0.200
$0.10
$0.10
$0.10
Code Llama 13B
4B-16B
16k
$0.200
$0.200
$0.10
$0.10
$0.10
Code Llama 13B Instruct
4B-16B
16k
$0.200
$0.200
$0.10
$0.10
$0.10
Code Llama 13B Python
4B-16B
16k
$0.200
$0.200
$0.10
$0.10
$0.10
Code Llama 7B
4B-16B
16k
$0.200
$0.200
$0.10
$0.10
$0.10
Code Llama 7B Instruct
4B-16B
16k
$0.200
$0.200
$0.10
$0.10
$0.10
CodeQwen 1.5 7B
4B-16B
66k
$0.200
$0.200
$0.10
$0.10
$0.10
Cogito v1 Preview Llama 8B
4B-16B
131k
$0.200
$0.200
$0.10
$0.10
$0.10
Cogito v1 Preview Qwen 14B
4B-16B
131k
$0.200
$0.200
$0.10
$0.10
$0.10
DeepSeek Coder 7B Base
4B-16B
4k
$0.200
$0.200
$0.10
$0.10
$0.10
DeepSeek Coder 7B Base v1.5
4B-16B
4k
$0.200
$0.200
$0.10
$0.10
$0.10
DeepSeek Coder 7B Instruct v1.5
4B-16B
4k
$0.200
$0.200
$0.10
$0.10
$0.10
DeepSeek R1 0528 Qwen3 8B
4B-16B
131k
$0.200
$0.200
$0.10
$0.10
$0.10
R1 Distill Llama 8B
4B-16B
131k
$0.200
$0.200
$0.10
$0.10
$0.10
R1 Distill Qwen 14B
4B-16B
131k
$0.200
$0.200
$0.10
$0.10
$0.10
R1 Distill Qwen 1.5B
4B-16B
131k
$0.200
$0.200
$0.10
$0.10
$0.10
R1 Distill Qwen 7B
4B-16B
131k
$0.200
$0.200
$0.10
$0.10
$0.10
4B-16B
8k
$0.200
$0.200
$0.10
$0.10
$0.10
4B-16B
131k
$0.200
$0.200
$0.10
$0.10
$0.10
4B-16B
131k
$0.200
$0.200
$0.10
$0.10
$0.10
Gemma 7B
4B-16B
8k
$0.200
$0.200
$0.10
$0.10
$0.10
Gemma 7B Instruct
4B-16B
8k
$0.200
$0.200
$0.10
$0.10
$0.10
Hermes 2 Pro Mistral 7B
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
InternVL3 8B
4B-16B
16k
$0.200
$0.200
$0.10
$0.10
$0.10
Llama Guard 2 8B
4B-16B
8k
$0.200
$0.200
$0.10
$0.10
$0.10
4B-16B
131k
$0.200
$0.200
$0.10
$0.10
$0.10
Llama Guard 7B
4B-16B
4k
$0.200
$0.200
$0.10
$0.10
$0.10
Llama 2 13B
4B-16B
4k
$0.200
$0.200
$0.10
$0.10
$0.10
Llama 2 13B Chat
4B-16B
4k
$0.200
$0.200
$0.10
$0.10
$0.10
Llama 2 7B
4B-16B
4k
$0.200
$0.200
$0.10
$0.10
$0.10
Llama 2 7B Chat
4B-16B
4k
$0.200
$0.200
$0.10
$0.10
$0.10
Llama 3 8B
4B-16B
8k
$0.200
$0.200
$0.10
$0.10
$0.10
4B-16B
8k
$0.200
$0.200
$0.10
$0.10
$0.10
Llama 3 8B Instruct (HF)
4B-16B
8k
$0.200
$0.200
$0.10
$0.10
$0.10
4B-16B
131k
$0.200
$0.200
$0.10
$0.10
$0.10
4B-16B
131k
$0.200
$0.200
$0.10
$0.10
$0.10
4B-16B
256k
$0.200
$0.200
$0.10
$0.10
$0.10
4B-16B
256k
$0.200
$0.200
$0.10
$0.10
$0.10
Mistral 7B
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
Mistral 7B v0.2
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
Molmo 2 4B
4B-16B
37k
$0.200
$0.200
$0.10
$0.10
$0.10
4B-16B
37k
$0.200
$0.200
$0.10
$0.10
$0.10
4B-16B
4k
$0.200
$0.200
$0.10
$0.10
$0.10
4B-16B
131k
$0.200
$0.200
$0.10
$0.10
$0.10
Nous Capybara 7B v1.9
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
Nous Hermes Llama 2 13B
4B-16B
4k
$0.200
$0.200
$0.10
$0.10
$0.10
Nous Hermes Llama 2 7B
4B-16B
4k
$0.200
$0.200
$0.10
$0.10
$0.10
Nemotron Nano 12B V2
4B-16B
128k
$0.200
$0.200
$0.10
$0.10
$0.10
4B-16B
128k
$0.200
$0.200
$0.10
$0.10
$0.10
OpenChat 3.5 0106
4B-16B
8k
$0.200
$0.200
$0.10
$0.10
$0.10
OpenHermes 2 Mistral 7B
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
OpenHermes 2.5 Mistral 7B
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
Mistral 7B OpenOrca
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
Pythia 12B
4B-16B
2k
$0.200
$0.200
$0.10
$0.10
$0.10
Qwen2 7B Instruct
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
Qwen2.5 0.5B Instruct
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
Qwen2.5 14B
4B-16B
131k
$0.200
$0.200
$0.10
$0.10
$0.10
Qwen2.5 14B Instruct
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
Qwen2.5 1.5B Instruct
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
Qwen2.5 7B
4B-16B
131k
$0.200
$0.200
$0.10
$0.10
$0.10
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
Qwen2.5 Coder 0.5B
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
Qwen2.5 Coder 0.5B Instruct
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
Qwen2.5 Coder 14B
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
Qwen2.5 Coder 14B Instruct
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
Qwen2.5 Coder 1.5B
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
Qwen2.5 Coder 1.5B Instruct
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
Qwen2.5 Coder 7B
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
4B-16B
128k
$0.200
$0.200
$0.10
$0.10
$0.10
Qwen2 VL 7B Instruct
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
Qwen3 0.6B
4B-16B
41k
$0.200
$0.200
$0.10
$0.10
$0.10
4B-16B
41k
$0.200
$0.200
$0.10
$0.10
$0.10
Qwen3 1.7B
4B-16B
131k
$0.200
$0.200
$0.10
$0.10
$0.10
Qwen3 4B
4B-16B
41k
$0.200
$0.200
$0.10
$0.10
$0.10
Qwen3 4B Instruct 2507
4B-16B
262k
$0.200
$0.200
$0.10
$0.10
$0.10
4B-16B
41k
$0.200
$0.200
$0.10
$0.10
$0.10
4B-16B
262k
$0.200
$0.200
$0.10
$0.10
$0.10
Qwen2.5 14B Instruct (alt)
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
Qwen2.5 7B (alt)
4B-16B
131k
$0.200
$0.200
$0.10
$0.10
$0.10
Snorkel Mistral PairRM DPO
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
Toppy M 7B
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
Zephyr 7B Beta
4B-16B
33k
$0.200
$0.200
$0.10
$0.10
$0.10
custom
197k
$0.300
$1.200
$0.03
$0.15
$0.60
custom
205k
$0.300
$1.200
$0.03
$0.15
$0.60
MiniMax M2.5
custom
197k
$0.300
$1.200
$0.03
$0.15
$0.60
Dolphin 2.6 Mixtral 8x7B
MoE 0-56B
33k
$0.500
$0.500
$0.25
$0.25
$0.25
Mixtral 8x7B
MoE 0-56B
33k
$0.500
$0.500
$0.25
$0.25
$0.25
MoE 0-56B
33k
$0.500
$0.500
$0.25
$0.25
$0.25
Mixtral 8x7B Instruct (HF)
MoE 0-56B
33k
$0.500
$0.500
$0.25
$0.25
$0.25
Nous Hermes 2 Mixtral 8x7B DPO
MoE 0-56B
33k
$0.500
$0.500
$0.25
$0.25
$0.25
custom
131k
$0.560
$1.680
$0.28
$0.28
$0.84
custom
164k
$0.560
$1.680
$0.28
$0.28
$0.84
custom
164k
$0.560
$1.680
$0.28
$0.28
$0.84
custom
164k
$0.560
$1.680
$0.28
$0.28
$0.84
custom
164k
$0.560
$1.680
$0.28
$0.28
$0.84
custom
203k
$0.600
$2.200
$0.30
$0.30
$1.10
custom
203k
$0.600
$2.200
$0.30
$0.30
$1.10
custom
131k
$0.600
$2.500
$0.30
$0.30
$1.25
custom
262k
$0.600
$2.500
$0.30
$0.30
$1.25
Kimi K2.5
custom
262k
$0.600
$3.000
$0.10
$0.30
$1.50
Kimi K2 Thinking
custom
$0.600
$2.500
$0.30
$0.30
$1.25
>16B
164k
$0.900
$0.900
$0.45
$0.45
$0.45
Code Llama 34B
>16B
16k
$0.900
$0.900
$0.45
$0.45
$0.45
Code Llama 34B Instruct
>16B
16k
$0.900
$0.900
$0.45
$0.45
$0.45
Code Llama 34B Python
>16B
16k
$0.900
$0.900
$0.45
$0.45
$0.45
Code Llama 70B
>16B
4k
$0.900
$0.900
$0.45
$0.45
$0.45
Code Llama 70B Instruct
>16B
4k
$0.900
$0.900
$0.45
$0.45
$0.45
Code Llama 70B Python
>16B
4k
$0.900
$0.900
$0.45
$0.45
$0.45
Cogito v1 Preview Llama 70B
>16B
131k
$0.900
$0.900
$0.45
$0.45
$0.45
Cogito v1 Preview Qwen 32B
>16B
131k
$0.900
$0.900
$0.45
$0.45
$0.45
DeepSeek Coder 33B Instruct
>16B
16k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
131k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
131k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
$0.900
$0.900
$0.45
$0.45
$0.45
Dolphin 2.9.2 Qwen2 72B
>16B
131k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
131k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
$0.900
$0.900
$0.45
$0.45
$0.45
FARE 20B
>16B
131k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
131k
$0.900
$0.900
$0.45
$0.45
$0.45
InternVL3 38B
>16B
16k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
16k
$0.900
$0.900
$0.45
$0.45
$0.45
KAT Dev 32B
>16B
131k
$0.900
$0.900
$0.45
$0.45
$0.45
KAT Dev 72B Exp
>16B
131k
$0.900
$0.900
$0.45
$0.45
$0.45
Llama 2 70B
>16B
4k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
8k
$0.900
$0.900
$0.45
$0.45
$0.45
Llama 3 70B Instruct (HF)
>16B
8k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
131k
$0.900
$0.900
$0.45
$0.45
$0.45
Llama 3.1 405B Instruct Long
>16B
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
131k
$0.900
$0.900
$0.45
$0.45
$0.45
Llama 3.1 70B Instruct 1B
>16B
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
131k
$0.900
$0.900
$0.45
$0.45
$0.45
Llama 3.2 90B Vision Instruct
>16B
131k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
131k
$0.900
$0.900
$0.45
$0.45
$0.45
MedGemma 27B
>16B
$0.900
$0.900
$0.45
$0.45
$0.45
Mistral Small 24B Instruct 2501
>16B
33k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
262k
$0.900
$0.900
$0.45
$0.45
$0.45
Nous Hermes Llama 2 70B
>16B
4k
$0.900
$0.900
$0.45
$0.45
$0.45
Phind CodeLlama 34B Python v1
>16B
16k
$0.900
$0.900
$0.45
$0.45
$0.45
Phind CodeLlama 34B v1
>16B
16k
$0.900
$0.900
$0.45
$0.45
$0.45
Phind CodeLlama 34B v2
>16B
16k
$0.900
$0.900
$0.45
$0.45
$0.45
Qwen 1.5 72B Chat
>16B
33k
$0.900
$0.900
$0.45
$0.45
$0.45
Qwen2 72B Instruct
>16B
33k
$0.900
$0.900
$0.45
$0.45
$0.45
Qwen2.5 32B
>16B
131k
$0.900
$0.900
$0.45
$0.45
$0.45
Qwen2.5 32B Instruct
>16B
33k
$0.900
$0.900
$0.45
$0.45
$0.45
Qwen2.5 72B
>16B
131k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
33k
$0.900
$0.900
$0.45
$0.45
$0.45
Qwen2.5 Coder 32B
>16B
33k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
33k
$0.900
$0.900
$0.45
$0.45
$0.45
Qwen2.5 Coder 32B Instruct 128K
>16B
131k
$0.900
$0.900
$0.45
$0.45
$0.45
Qwen2.5 Coder 32B Instruct 32K RoPE
>16B
33k
$0.900
$0.900
$0.45
$0.45
$0.45
Qwen2.5 Coder 32B Instruct 64K
>16B
66k
$0.900
$0.900
$0.45
$0.45
$0.45
Qwen2.5 Math 72B Instruct
>16B
4k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
128k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
128k
$0.900
$0.900
$0.45
$0.45
$0.45
Qwen2 VL 72B Instruct
>16B
33k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
131k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
262k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
262k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
131k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
262k
$0.900
$0.900
$0.45
$0.45
$0.45
Qwen3 30B A3B Thinking 2507
>16B
262k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
131k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
262k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
262k
$0.900
$0.900
$0.45
$0.45
$0.45
Qwen3 Coder 480B Instruct BF16
>16B
262k
$0.900
$0.900
$0.45
$0.45
$0.45
Qwen3 Next 80B A3B Instruct
>16B
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
$0.900
$0.900
$0.45
$0.45
$0.45
Qwen3 Omni 30B A3B Instruct
>16B
66k
$0.900
$0.900
$0.45
$0.45
$0.45
Qwen3.5 397B A17B
>16B
262k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
262k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
262k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
$0.900
$0.900
$0.45
$0.45
$0.45
QwQ 32B Preview
>16B
33k
$0.900
$0.900
$0.45
$0.45
$0.45
>16B
131k
$0.900
$0.900
$0.45
$0.45
$0.45
Seed OSS 36B Instruct
>16B
524k
$0.900
$0.900
$0.45
$0.45
$0.45
GLM 5
custom
203k
$1.000
$3.200
$0.20
$0.50
$1.60
Mixtral 8x22B
MoE 56-176B
66k
$1.200
$1.200
$0.60
$0.60
$0.60
MoE 56-176B
66k
$1.200
$1.200
$0.60
$0.60
$0.60
DeepSeek Coder V2 Lite Base
164k
$N/A
$N/A
DeepSeek Coder V2 Lite Instruct
164k
$N/A
$N/A
DeepSeek Prover V2
164k
$N/A
$N/A
164k
$N/A
$N/A
164k
$N/A
$N/A
DeepSeek R1 (Basic)
164k
$N/A
$N/A
DeepSeek V2 Lite Chat
164k
$N/A
$N/A
DeepSeek V2.5
33k
$N/A
$N/A
Devstral Small 2505
131k
$N/A
$N/A
FireFunction V1
33k
$N/A
$N/A
FireFunction V2
$N/A
$N/A
Firesearch OCR V6
8k
$N/A
$N/A
131k
$N/A
$N/A
131k
$N/A
$N/A
131k
$N/A
$N/A
203k
$N/A
$N/A
KAT Coder
262k
$N/A
$N/A
1049k
$N/A
$N/A
1049k
$N/A
$N/A
$N/A
$N/A
256k
$N/A
$N/A
Mistral Nemo Base 2407
128k
$N/A
$N/A
128k
$N/A
$N/A
Phi-3 Mini 128K Instruct
131k
$N/A
$N/A
Phi-3.5 Vision Instruct
32k
$N/A
$N/A
Rolm OCR
128k
$N/A
$N/A

Pricing from Fireworks AI. Batch pricing is 50% of serverless. Cached input is 50% of input unless custom.