large-models-interface
Version:
A comprehensive, unified interface for all types of AI models - natural language, vision, audio, and video. Supports 51 providers with dynamic model discovery and multi-modal capabilities.
17 lines (16 loc) • 422 B
JSON
{
"url": "https://api.stepfun.com/v1/chat/completions",
"model": {
"default": "step-1v-8k",
"large": "step-1v-32k",
"small": "step-1v-8k",
"agent": "step-1v-32k"
},
"createMessageObject": "getMessageObject",
"stream": true,
"jsonMode": false,
"maxTokens": true,
"hasEmbeddings": false,
"modelsEndpoint": "https://api.stepfun.com/v1/models",
"modelsFile": "./data/models/stepfun.json"
}