modelpedia
Models
Providers
Compare
Analytics
API
Cerebras
Cloud Platform
OpenAI compatible
Ultra-fast inference powered by wafer-scale compute chips, offering the fastest LLM speeds.
Active models
3
+ 12 deprecated
Families
5
Headquarters
🇺🇸 Sunnyvale, CA
Founded
2016
API Base URL
https://api.cerebras.ai/v1
Models
inference-docs.cerebras.ai/introduction
OSS
Show deprecated (12)
R
reasoning
V
vision
T
tool call
S
streaming
J
structured output
F
fine tuning
Model
Caps
Context
Pricing
Qwen 3 235B Instruct
OSS
qwen-3-235b-a22b-instruct
R
V
T
S
J
F
131K
$0.6
$1.2
Z.ai GLM 4.7
zai-glm-4.7
R
V
T
S
J
F
131K
$2.25
$2.75
OpenAI GPT OSS
OSS
gpt-oss-120b
R
T
S
J
131K
$0.35
$0.75
Human
AI