Models Compare Providers Docs

Sign in Get Started

Loading providers...

Cerebras Provider

Cerebras high-performance inference with ultra-fast throughput

Get started Visit company

Supported Models

Llama 3.1 8B Instruct

meta

llama-3.1-8b-instruct

Context128,000 tokens

Providers1

Input₹9.40/M

Output₹9.40/M

Streaming

JSON Output

Qwen3 235B A22B Instruct 2507

alibaba

qwen3-235b-a22b-instruct-2507

Context131,072 tokens

Providers1

Input₹56.40/M

Output₹112.80/M

Streaming

Tools

JSON Output