- We recommend using
openai/gpt-oss-120bfor general use. - We recommend using
openai/gpt-oss-20bfor faster results. - For image understanding, Groq’s current options are Preview-tier only — see Multimodal Support below.
Multimodal Support
With Groq we supportImage as input, on vision-capable models.
Groq’s vision docs list the current image-capable models — qwen/qwen3.6-27b and qwen/qwen3.8-27b. Groq classes both as Preview models, which it describes as suitable for evaluation rather than production and subject to discontinuation at short notice. Groq names qwen/qwen3.6-27b as the replacement for the retired meta-llama/llama-4-scout-17b-16e-instruct. The default openai/gpt-oss-120b does not accept images.
Authentication
Set yourGROQ_API_KEY environment variable. Get your key from here.
Example
Install thegroq package:
Groq with your Agent:
View more examples here.
Parameters
Groq uses the groq Python SDK. It is a subclass of the Model class and has access to the same params. See the Groq reference for all parameters.