Documentation
Supported Models
GroqCloud currently supports the following models:
Production Models
Note: Production models are intended for use in your production environments. They meet or exceed our high standards for speed and quality.
MODEL ID | DEVELOPER | CONTEXT WINDOW (TOKENS) | MAX COMPLETION TOKENS | MAX FILE SIZE | MODEL CARD LINK |
---|---|---|---|---|---|
distil-whisper-large-v3-en | HuggingFace | - | - | 25 MB | Card |
gemma2-9b-it | 8,192 | - | - | Card | |
llama-3.3-70b-versatile | Meta | 128K | 32,768 | - | Card |
llama-3.1-8b-instant | 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 |
Preview Models
Note: Preview models are intended for evaluation purposes only and should not be used in production environments as they may be discontinued at short notice.
MODEL ID | DEVELOPER | CONTEXT WINDOW (TOKENS) | MAX COMPLETION TOKENS | MAX FILE SIZE | MODEL CARD LINK |
---|---|---|---|---|---|
qwen-2.5-32b | Alibaba Cloud | 128K | 8,192 | - | Card |
deepseek-r1-distill-qwen-32b | DeepSeek | 128K | 16,384 | - | Card |
deepseek-r1-distill-llama-70b-specdec | DeepSeek | 128K | 16,384 | - | Card |
deepseek-r1-distill-llama-70b | DeepSeek | 128K | - | - | Card |
llama-3.3-70b-specdec | Meta | 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 |
Deprecated models are models that are no longer supported or will no longer be supported in the future. A suggested alternative model for you to use is listed for each deprecated model. See our deprecated models here
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())