10 actions in 5 pieces of software · ranked by words, meaning and measured trust · 410 ms
modelrecord12,037 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord1,030,720 downloads/month
- image-text-to-text
Task: image-text-to-text
- image-text-to-text
modelrecord
- tool-calling
Can call tools (function calling).
- structured-outputs
Can return JSON matching a schema.
- tool-calling
MCP serverrecord
- kimi_k3_demo_chat
Chat with Kimi K3 (Moonshot AI) via HF Inference Providers. Supports text and image input, streams the response, and preserves K3's thinking history across turns (required for good multi-turn behavior). If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload th
- kimi_k3_demo__lambda_
- kimi_k3_demo__lambda__3
- kimi_k3_demo__lambda__2
- kimi_k3_demo__lambda__1
- kimi_k3_demo_chat
modelrecord55,631 downloads/month
- image-text-to-video
Task: image-text-to-video
- image-text-to-video
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.