Cerebras

Cerebras

active

Ultra-fast LLM inference via custom wafer-scale chips — free tier offers 30 RPM and 1M tokens/day with no credit card required.

https://api.cerebras.ai/v1

Avg Latency

90-day Uptime

%

Rate Limits

30 RPM / 14,400 RPD

Sign-up Required

Yes

Info

Base URL https://api.cerebras.ai/v1
Sign-up Required Yes
Credit Card Not required
Context Window 128K
Last Verified 2026-03-30
fast-inferenceopenai-compatiblellamafunction-call

Models (4)

llama3.1-8b

CTX: 128K · 30 RPM

active

gpt-oss-120b

CTX: 128K · 30 RPM

active

qwen-3-235b-a22b-instruct-2507

CTX: 128K · 30 RPM

active

zai-glm-4.7

CTX: 128K · 10 RPM

active

Quick Start

bash
export API_KEY="your_api_key_here"
curl https://api.cerebras.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  -d '{
    "model": "llama3.1-8b",
    "messages": [
      {"role": "user", "content": "Hello! How are you?"}
    ]
  }'