Douwe Osinga
9251da4314
Co-authored-by: Douwe Osinga <douwe@squareup.com> Co-authored-by: Michael Neale <michael.neale@gmail.com>
31 lines
685 B
JSON
31 lines
685 B
JSON
{
|
|
"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": "openai/gpt-oss-120b",
|
|
"context_limit": 131072
|
|
},
|
|
{
|
|
"name": "llama-3.1-8b-instant",
|
|
"context_limit": 131072
|
|
},
|
|
{
|
|
"name": "llama-3.3-70b-versatile",
|
|
"context_limit": 131072
|
|
},
|
|
{
|
|
"name": "meta-llama/llama-guard-4-12b",
|
|
"context_limit": 131072
|
|
},
|
|
{
|
|
"name": "openai/gpt-oss-20b",
|
|
"context_limit": 131072
|
|
}
|
|
],
|
|
"supports_streaming": true
|
|
} |