Cerebras

Ongoing verified 2026-07-11 · 19d ago OpenAI-compatible

Fastest tokens/sec on wafer-scale hardware

What's free

Access to all Cerebras-hosted models

Rate limits

Officially published per-model: 5 RPM / 30,000 TPM / 1,000,000 TPH / 1,000,000 TPD (e.g. gpt-oss-120b, zai-glm-4.7, gemma-4-31b); limits vary by model

The catch

Free tier includes community support (Discord) only; paid Developer tier gives "10x higher" rate limits

TypeOngoing free tier
Free typerenewing-quota
Expiresno expiry
Modalitiestext
OpenAI base URLhttps://api.cerebras.ai/v1

Free models · sample

gpt-oss-120bzai-glm-4.7gemma-4-31b

A sample of models reachable on the free tier — the live catalog changes. Pull the current set with GET https://api.cerebras.ai/v1/models.

Quickstart — chat completions

from openai import OpenAI

client = OpenAI(base_url="https://api.cerebras.ai/v1", api_key="<YOUR_FREE_API_KEY>")
resp = client.chat.completions.create(
    model="gpt-oss-120b",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

…or with curl:

curl https://api.cerebras.ai/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-oss-120b","messages":[{"role":"user","content":"Hello!"}]}'

Appears in

← All providers