Groq language model instantiation
Create a Groq language model by passing the model ID as a string to the groq provider instance: `const model = groq('gemma2-9b-it');`
AI SDK · Providers · all subjects
groq/models
2 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.
Groq model capabilities table
Groq model capabilities: gemma2-9b-it (Image Input: No, Object Generation: Yes, Tool Usage: Yes, Tool Streaming: Yes), llama-3.1-8b-instant (No, Yes, Yes, Yes), llama-3.3-70b-versatile (No, Yes, Yes, Yes), meta-llama/llama-guard-4-12b (Yes, Yes, No, No), deepseek-r1-distill-llama-70b (No, Yes, Yes, Yes), meta-llama/llama-4-maverick-17b-128e-instruct (Yes, Yes, Yes, Yes), meta-llama/llama-4-scout-17b-16e-instruct (Yes, Yes, Yes, Yes), meta-llama/llama-prompt-guard-2-22m (No, Yes, No, No), meta-llama/llama-prompt-guard-2-86m (No, Yes, No, No), moonshotai/kimi-k2-instruct-0905 (No, Yes, Yes, Yes), qwen/qwen3-32b (No, Yes, Yes, Yes), llama-guard-3-8b (No, Yes, Yes, Yes), llama3-70b-8192 (No, Yes, Yes, Yes), llama3-8b-8192 (No, Yes, Yes, Yes), mixtral-8x7b-32768 (No, Yes, Yes, Yes), qwen-qwq-32b (No, Yes, Yes, Yes), qwen-2.5-32b (No, Yes, Yes, Yes), deepseek-r1-distill-qwen-32b (No, Yes, Yes, Yes), openai/gpt-oss-20b (No, Yes, Yes, Yes), openai/gpt-oss-120b (No, Yes, Yes, Yes).