Skip to main content

DeepSeek R1, a state-of-the-art open model, is now available. Try it now or read our DeepSeek quickstart!

Model Library

DeepSeek R1

DeepSeek R1 is a state-of-the-art large language model optimized with reinforcement learning and cold-start data for exceptional reasoning, math, and code performance.

Try It Learn more
DeepSeek logo

DeepSeek R1

$3.00/M Input • $8.00/M Output • 160k Context
ServerlessTunable

Llama 3.1 405B Instruct

$3.00/M Tokens • 128k Context
ServerlessTunable

DeepSeek V3

$0.90/M Tokens • 128k Context
ServerlessTunable

Llama 3.1 8B Instruct

$0.20/M Tokens • 128k Context
ServerlessTunable

Deepseek R1 Distill Qwen 7B

Tunable

Stable Diffusion 3.5 Large Turbo

$0.04/ea

Stable Diffusion 3.5 Large

$0.065/ea

Stable Diffusion 3.5 Medium

$0.035/ea

FLUX.1 [dev] FP8

$0.0005/step
Serverless

FLUX.1 [schnell] FP8

$0.00035/step
Serverless

Streaming Speech Transcription

Serverless

Whisper V3 Large

Serverless

Whisper V3 Turbo

Serverless