Cerebras Provider
Cerebras high-performance inference with ultra-fast throughput
Available Models
GPT OSS 120B
gpt-oss-120bProviders
Cerebras
cerebras/gpt-oss-120bContext Size
131.1k
Stability
STABLEPricing
Input
$0.35/M
Cached
—/M
Output
$0.75/M
Capabilities
Streaming
Tools
Reasoning
JSON Output
Llama 3.1 8B Instruct
llama-3.1-8b-instructProviders
Cerebras
cerebras/llama-3.1-8b-instructContext Size
128k
Stability
STABLEPricing
Input
$0.10/M
Cached
—/M
Output
$0.10/M
Capabilities
Streaming
JSON Output
Llama 3.3 70B Instruct
llama-3.3-70b-instructProviders
Cerebras
cerebras/llama-3.3-70b-instructContext Size
128k
Stability
STABLEPricing
Input
$0.85/M
Cached
—/M
Output
$1.20/M
Capabilities
Streaming
Tools
JSON Output
Qwen3 235B A22B Instruct 2507
qwen3-235b-a22b-instruct-2507Providers
Cerebras
cerebras/qwen3-235b-a22b-instruct-2507Context Size
262k
Stability
STABLEPricing
Input
$0.60/M
Cached
—/M
Output
$1.20/M
Capabilities
Streaming
Tools
JSON Output
Qwen3 32B
qwen3-32bProviders
Cerebras
cerebras/qwen3-32bContext Size
32.8k
Stability
STABLEPricing
Input
$0.40/M
Cached
—/M
Output
$0.80/M
Capabilities
Streaming
Tools
JSON Output
GLM-4.6
glm-4.6Providers
Cerebras
cerebras/glm-4.6Context Size
200k
Stability
unstablePricing
Input
$2.25/M
Cached
—/M
Output
$2.75/M
Capabilities
Streaming
Tools
Reasoning
JSON Output