Skip to main content

Llama 4 models are now available with SOTA intelligence, context length and multi-modal understanding. Try Llama 4 now

Model Library

Llama 4

Llama 4 Maverick provides SOTA intelligence and blazing fast speeds across multiple languages. Llama 4 Scout is a general purpose LLM equipped with multi-modality and 10M token context window to excel at use cases like multi-document summarization.

Try It Learn more
Meta logo

Llama 4 Maverick Instruct (Basic) model image

Llama 4 Maverick Instruct (Basic)

$0.22/M Input • $0.88/M Output • 1M Context
Serverless
Llama 4 Scout Instruct (Basic) model image

Llama 4 Scout Instruct (Basic)

$0.15/M Input • $0.60/M Output • 128k Context
Serverless
DeepSeek R1 (Fast) model image

DeepSeek R1 (Fast)

$3.00/M Input • $8.00/M Output • 160k Context
ServerlessTunable
Llama 3.1 405B Instruct model image

Llama 3.1 405B Instruct

$3.00/M Tokens • 128k Context
ServerlessTunable
DeepSeek V3 model image

DeepSeek V3

$0.90/M Tokens • 128k Context
ServerlessTunable

Stable Diffusion 3.5 Large model image

Stable Diffusion 3.5 Large

$0.065/ea
Stable Diffusion 3.5 Large Turbo model image

Stable Diffusion 3.5 Large Turbo

$0.04/ea
Stable Diffusion 3.5 Medium model image

Stable Diffusion 3.5 Medium

$0.035/ea
FLUX.1 [dev] FP8 model image

FLUX.1 [dev] FP8

$0.0005/step
Serverless
FLUX.1 [schnell] FP8 model image

FLUX.1 [schnell] FP8

$0.00035/step
Serverless

Streaming Speech Transcription model image

Streaming Speech Transcription

Serverless
Whisper V3 Large model image

Whisper V3 Large

Serverless
Whisper V3 Turbo model image

Whisper V3 Turbo

Serverless