Groq Provider

Groq's ultra-fast LPU inference with various models

Get startedVisit company

S

Available Models

GPT OSS 120B

openai
groq/gpt-oss-120b
Context Size
131.1k
Stability
STABLE
Pricing
Input
$0.15/M
Cached
—/M
Output
$0.75/M
Capabilities
Streaming
Tools
Reasoning
JSON Output
Try in Playground

GPT OSS 20B

openai
groq/gpt-oss-20b
Context Size
131.1k
Stability
STABLE
Pricing
Input
$0.10/M
Cached
—/M
Output
$0.50/M
Capabilities
Streaming
Tools
Reasoning
JSON Output
Try in Playground

Kimi K2

moonshot
groq/kimi-k2
Context Size
131.1k
Stability
STABLE
Pricing
Input
$1.00/M
Cached
$0.50/M
Output
$3.00/M
Capabilities
Streaming
Tools
JSON Output
Try in Playground

Llama Guard 4 12B

meta
groq/llama-guard-4-12b
Context Size
131.1k
Stability
STABLE
Pricing
Input
$0.20/M
Cached
—/M
Output
$0.20/M
Capabilities
Streaming
Try in Playground

DeepSeek R1 Distill Llama 70B

deepseek
groq/deepseek-r1-distill-llama-70b
Context Size
131.1k
Stability
STABLE
Pricing
Input
$0.75/M
Cached
—/M
Output
$0.99/M
Capabilities
Streaming
Tools
JSON Output
Try in Playground

Gemma2 9B IT

google
groq/gemma2-9b-it
Context Size
8.1k
Stability
unstable
Pricing
Input
$0.20/M
Cached
—/M
Output
$0.20/M
Capabilities
Streaming
Tools
Try in Playground