Skip to content
OmniRail
← All models

Moondream · Language model

Moondream 3.1

moondream/moondream3.1-9b-a2b
  • Language
Released Oct 15, 2026

Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...

Specifications

Context window
32,000 tokens
Max output
4,096 tokens
Input
text, image
Output
text
Reasoning
supported
Tokenizer
Other

Supported parameters

Accepted by the model and forwarded as-is by the gateway.

  • max_completion_tokens
  • max_tokens
  • reasoning
  • temperature
  • top_p

Use it

POST /api/v1/chat/completions · MCP chat · full reference

curl https://omnirail.org/api/v1/chat/completions \
  -H "Authorization: Bearer $OMNIRAIL_KEY" -H "Content-Type: application/json" \
  -d '{"model":"moondream/moondream3.1-9b-a2b","messages":[{"role":"user","content":"Hello"}],"max_tokens":300}'