Documentation
Supported Models
GroqCloud currently supports the following models:
Model ID | Developer | Context Window (tokens) | Max Tokens | Max File Size | Model Card Link |
---|---|---|---|---|---|
distil-whisper-large-v3-en | HuggingFace | - | - | 25 MB | Card |
gemma2-9b-it | 8,192 | - | - | Card | |
gemma-7b-it | 8,192 | - | - | Card | |
llama3-groq-70b-8192-tool-use-preview | Groq | 8,192 | - | - | Card |
llama3-groq-8b-8192-tool-use-preview | Groq | 8,192 | - | - | Card |
llama-3.1-70b-versatile | Meta | 128k | 32,768 | - | Card |
llama-3.1-70b-specdec | Meta | 128k | 8,192 | Card | |
llama-3.1-8b-instant | Meta | 128k | 8,192 | - | Card |
llama-3.2-1b-preview | Meta | 128k | 8,192 | - | Card |
llama-3.2-3b-preview | Meta | 128k | 8,192 | - | Card |
llama-3.2-11b-vision-preview | Meta | 128k | 8,192 | - | Card |
llama-3.2-90b-vision-preview | Meta | 128k | 8,192 | - | Card |
llama-guard-3-8b | Meta | 8,192 | - | - | Card |
llama3-70b-8192 | Meta | 8,192 | - | - | Card |
llama3-8b-8192 | Meta | 8,192 | - | - | Card |
mixtral-8x7b-32768 | Mistral | 32,768 | - | - | Card |
whisper-large-v3 | OpenAI | - | - | 25 MB | Card |
whisper-large-v3-turbo | OpenAI | - | - | 25 MB | Card |
Deprecated Models |
Note: Models with a context window of 128K tokens are currently limited to 8,192 max tokens in preview. Models without a context window or max tokens are denoted with a dash ("-").
Hosted models are directly accessible through the GroqCloud Models API endpoint using the model IDs mentioned above. You can use the https://api.groq.com/openai/v1/models
endpoint to return a JSON list of all active models:
1import requests
2import os
3
4api_key = os.environ.get("GROQ_API_KEY")
5url = "https://api.groq.com/openai/v1/models"
6
7headers = {
8 "Authorization": f"Bearer {api_key}",
9 "Content-Type": "application/json"
10}
11
12response = requests.get(url, headers=headers)
13
14print(response.json())