{
  "name": "groq",
  "engine": "openai",
  "display_name": "Groq (d)",
  "description": "Fast inference with Groq hardware",
  "api_key_env": "GROQ_API_KEY",
  "base_url": "https://api.groq.com/openai/v1/chat/completions",
  "models": [
    {
      "name": "moonshotai/kimi-k2-instruct-0905",
      "context_limit": 262144,
      "max_tokens": 16384
    },
    {
      "name": "openai/gpt-oss-120b",
      "context_limit": 131072,
      "max_tokens": 65536
    },
    {
      "name": "openai/gpt-oss-20b",
      "context_limit": 131072,
      "max_tokens": 65536
    },
    {
      "name": "meta-llama/llama-4-maverick-17b-128e-instruct",
      "context_limit": 131072,
      "max_tokens": 8192
    },
    {
      "name": "meta-llama/llama-4-scout-17b-16e-instruct",
      "context_limit": 131072,
      "max_tokens": 8192
    },
    {
      "name": "qwen/qwen3-32b",
      "context_limit": 131072,
      "max_tokens": 40960
    },
    {
      "name": "llama-3.3-70b-versatile",
      "context_limit": 131072,
      "max_tokens": 32768
    },
    {
      "name": "llama-3.1-8b-instant",
      "context_limit": 131072,
      "max_tokens": 131072
    },
    {
      "name": "openai/gpt-oss-safeguard-20b",
      "context_limit": 131072,
      "max_tokens": 65536
    },
    {
      "name": "meta-llama/llama-guard-4-12b",
      "context_limit": 131072,
      "max_tokens": 1024
    }
  ],
  "supports_streaming": true
}