Groq

Groq offers 9 models through Lava’s AI Gateway, supporting Chat Completions, Transcription. Authentication uses Authorization: Bearer. See the Groq API docs for provider-specific parameters.

Supports both managed (Lava’s API keys) and unmanaged (bring your own credentials) mode.

Quick Start

const response = await fetch('https://api.lava.so/v1/forward?u=https%3A%2F%2Fapi.groq.com%2Fopenai%2Fv1%2Fchat%2Fcompletions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    Authorization: `Bearer ${forwardToken}`,
  },
  body: JSON.stringify({
    model: 'openai/gpt-oss-safeguard-20b',
    messages: [{ role: "user", content: "Hello!" }],
  }),
});

Chat Completions

Target URL: https://api.groq.com/openai/v1/chat/completions


Content Type	`application/json`
Streaming	Yes (set `stream: true` in request body)

Model	Input / 1M tokens	Output / 1M tokens
qwen/qwen3.6-27b	$0.60	$3.00
llama-3.3-70b-versatile	$0.59	$0.79
openai/gpt-oss-120b	$0.15	$0.60
openai/gpt-oss-safeguard-20b	$0.075	$0.30
openai/gpt-oss-20b	$0.075	$0.30
llama-3.1-8b-instant	$0.05	$0.08

Transcription

Target URL: https://api.groq.com/openai/v1/audio/transcriptions


Content Type	`multipart/form-data`
Streaming	No

Model	Input / minute	Output / minute
whisper-large-v3	$0.00185	Free
whisper-large-v3-turbo	$0.001	Free
whisper-large-v3-en	$0.0003	Free

Next Steps

All Providers

Browse all supported AI providers

Forward Proxy

Learn how to construct proxy URLs and authenticate requests

⌘I

Get Started

AI Gateway

AI Spend

Monetize

Integration

SDK

Cookbook

Comparisons

Quick Start

Chat Completions

Transcription

Next Steps

All Providers

Forward Proxy

​Quick Start

​Chat Completions

​Transcription

​Next Steps

All Providers

Forward Proxy

Quick Start

Chat Completions

Transcription

Next Steps