Cerebras#

Fastest inference speeds using revolutionary wafer-scale computing technology.

Provider Information#

Field	Value
Provider ID	`cerebras`
Total Models	9
Authentication	API Key Required
Environment Variable	`CEREBRAS_API_KEY`
Status Page	https://status.cerebras.ai/

🔗 API Endpoints#

Documentation: https://inference-docs.cerebras.ai/models/overview

Models API: https://api.cerebras.ai/v1/models

Chat Completions: https://api.cerebras.ai/v1/chat/completions

Health API: https://status.cerebras.ai/api/v2/summary.json

🔒 Privacy & Data Handling#

Privacy Policy: https://www.cerebras.ai/privacy-policy

Terms of Service: https://www.cerebras.ai/terms-of-service

Retains User Data: No

Trains on User Data: No

⏱️ Data Retention Policy#

Policy Type: No Retention

Retention Duration: Immediate deletion

Details: API inputs and outputs are not retained for training, inference and chatbot services. Data is processed for immediate response generation and then discarded.

🛡️ Content Moderation#

Requires Moderation: No

Content Moderated: Yes

Moderated by: Cerebras

🏢 Headquarters#

Sunnyvale, CA, USA

Available Models#

GPT#

Model	Context	Input	Output	Features
gpt-oss-120b	131.1k	$0.25	$0.69	📝 ⚡

Llama#

Model	Context	Input	Output	Features
llama-3.3-70b	65.5k	$0.70	$2.80	📝 🔧 ⚡
llama-4-maverick-17b-128e-instruct	N/A	N/A	N/A	📝 ⚡
llama-4-scout-17b-16e-instruct	131k	$0.27	$0.85	📝 🔧 ⚡
llama3.1-8b	N/A	N/A	N/A	📝 🔧 ⚡

Qwen#

Model	Context	Input	Output	Features
qwen-3-235b-a22b-instruct-2507	131k	$0.60	$1.20	📝 ⚡
qwen-3-235b-a22b-thinking-2507	N/A	N/A	N/A	📝 ⚡
qwen-3-32b	N/A	N/A	N/A	📝 ⚡
qwen-3-coder-480b	131k	$2.00	$2.00	📝 ⚡

Configuration#

Authentication#

This provider requires an API key. Set it as an environment variable:

1export CEREBRAS_API_KEY="your-api-key-here"

Using with Model.Wiki#

1# List all models from this provider
2starmap list models --provider cerebras
3
4# Fetch latest models from provider API
5starmap fetch --provider cerebras
6
7# Sync provider data
8starmap sync --provider cerebras