Moondream releases two small vision-language models, each with 9B total parameters and 2B active through mixture-of-experts. Both accept image and text input with a 32K context window and optional reasoning, priced at $0.30 per million input tokens and $2.50 per million output tokens. OpenRouter says the models support captions through the /caption command with {"length":"normal"}.
Part of a thread · earlier post
Small vision-language models (9B total, 2B active MoE): image + text in, 32K context, optional reasoning. Use /caption {"length":"normal"} for captions
Both are $0.30/M input and $2.50/M output tokens
See more:
https://openrouter.ai/moondream/moondream3.1-9b-a2b
Source: OpenRouter · x.comPublished
