10 actions in 8 pieces of software · ranked by words, meaning and measured trust · 642 ms
modelrecord174 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord77,997 downloads/month
- image-text-to-text
Task: image-text-to-text
- image-text-to-text
modelrecord20,742 downloads/month
- audio-text-to-text
Task: audio-text-to-text
- audio-text-to-text
modelrecord114,276 downloads/month
- automatic-speech-recognition
Task: automatic-speech-recognition
- automatic-speech-recognition
modelrecord
- text+audio+file->text
Takes text, audio, file; returns text.
- structured-outputs
Can return JSON matching a schema.
- tool-calling
Can call tools (function calling).
- text+audio+file->text
modelrecord
- text+file->text
Takes text, file; returns text.
- text+file->text
modelrecord
- deepseek-ai/deepseek-vl2-small
DeepSeek-VL2-small, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL
- deepseek-ai/deepseek-vl2-small
- 8devstraldemo or tutorialno passport yet
MCP serverleonets/devstral
- registered-users
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.