Impulse
Search…
⌘
K
Models
Providers
Capabilities
Pricing
Compare
API
Playground
Providers
/
Cerebras
Visit website
C
Cerebras
Inference provider
·
cerebras.ai
Cerebras models via API.
Models
7
Endpoints
3
Regions
1
Avg input
$
0.97
Auth
Bearer token
SDKs
1
Endpoints
POST
/v1/chat/completions
Completions
Stream
POST
/v1/messages
Messages
Stream
POST
/v1/responses
Responses
Stream
Models · 7
Model
Context
Input
Output
Capabilities
gpt-oss-120b
Open
131K
$
0.35
$
0.75
Reasoning
Tools
JSON
qwen-3-32b
Open
128K
$
0.40
$
0.80
Reasoning
Tools
llama-3.3-70b
Open
128K
$
0.85
$
1.20
Tools
llama3.1-70b
Open
128K
$
0.60
$
0.60
Tools
llama3.1-8b
Open
128K
$
0.10
$
0.10
Tools
zai-glm-4.6
128K
$
2.25
$
2.75
Reasoning
Tools
zai-glm-4.7
128K
$
2.25
$
2.75
Reasoning
Tools
Release timeline
llama3.1-8b
zai-glm-4.6
zai-glm-4.7
Apr 2025
qwen-3-32b
Aug 2025
gpt-oss-120b
Details
Category
Inference provider
Website
cerebras.ai
Auth
Bearer token
Regions
1
Regions
global
SDKs
Python
docs ↗
pip install cerebras_cloud_sdk