Model Library

Llama 3.1 405B Instruct

131,072 Context

Llama 3.1 70B Instruct

$0.90/M Tokens • 131,072 Context

Llama 3.1 8B Instruct

$0.20/M Tokens • 131,072 Context

Llama 3.2 3B Instruct

$0.20/M Tokens • 131,072 Context

Mixtral MoE 8x22B Instruct

$0.90/M Tokens • 65,536 Context

Qwen2.5-Coder-32B-Instruct

$0.90/M Tokens • 32,768 Context

Llama 3.2 11B Vision Instruct

$0.20/M Tokens • 131,072 Context

Zephyr 7B Beta

$0.20/M Tokens • 4,096 Context

Llama Guard 7B

$0.20/M Tokens • 4,096 Context

Qwen2 72B Instruct

$0.90/M Tokens • 32,768 Context

Llama 2 13B Chat

$0.20/M Tokens • 4,096 Context

CodeGemma 7B

$0.20/M Tokens • 8,192 Context

Mixtral MoE 8x7B Instruct (HF version)

$0.50/M Tokens • 32,768 Context

DeepSeek Coder 1.3B Base

$0.20/M Tokens • 16,384 Context

CodeGemma 2B

$0.20/M Tokens • 8,192 Context

Code Qwen 1.5 7B

$0.20/M Tokens • 65,536 Context

Yi-Large

$3.00/M Tokens • 32,768 Context

DeepSeek Coder V2 Lite Base

163,840 Context

Llama 3 70B Instruct (HF version)

$0.90/M Tokens • 8,192 Context

Hermes 2 Pro Mistral 7B

$0.20/M Tokens

Stable Diffusion 3.5 Medium

$0.035/ea

Stable Diffusion 3.5 Large

$0.065/ea

Stable Diffusion 3.5 Large Turbo

$0.04/ea

FLUX.1 [dev] FP8

$0.0005/step

FLUX.1 [schnell] FP8

$0.00035/step

FLUX.1 [schnell]

$0.0007/step

FLUX.1 [dev]

$0.001/step

Stable Diffusion XL

$0.00013/step

Stable Diffusion 3 Large

$0.065/ea

Stable Diffusion 3 Medium

$0.035/ea

Playground v2 1024

$0.00013/step

Playground v2.5 1024

$0.00013/step

Segmind Stable Diffusion 1B (SSD-1B)

$0.00013/step

Japanese Stable Diffusion XL

$0.00013/step

Stable Diffusion 3 Turbo

$0.04/ea