Moondream 3.1 and Clef models available on Prime Inference and OpenRouter
Article timeline
The articles in this story. Times are ET.
OpenRouter@OpenRouterOfficialMoondream releases 9B vision-language models with 2B active parametersAIMoondream 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"}.
- OpenRouter@OpenRouterOfficialMoondream 3 Preview and 3.1 are now on OpenRouter
AIOpenRouter now offers Moondream 3 Preview and Moondream 3.1, served by Prime Intellect. Users can run object detection and pointing in chat by attaching one image and starting the message with /detect {"object":"coffee cup"} or /point {"object":"croissant"}.
- OpenRouter · New modelsBlogMoondream releases Moondream 3 Preview, a 9B-parameter vision-language model
AIMoondream announces Moondream 3 Preview, a vision-language model with 9B total parameters and 2B active through mixture-of-experts. The model handles visual question answering, captioning, OCR, and visual reasoning over images.
- OpenRouter · New modelsBlogMoondream releases Moondream 3.1, a 9B-parameter vision-language model
AIMoondream releases Moondream 3.1, a vision-language model with 9B total parameters and 2B active through mixture-of-experts. The model handles visual question answering, captioning, and OCR, and succeeds Moondream 3 Preview.
Prime Intellect@PrimeIntellectOfficialPrime Intellect adds Moondream 3.1 and Clef models to Prime InferenceAIPrime Intellect says Moondream 3.1 is now live on Prime Inference, running on Moondream's Photon engine. Clef and Clef Flash, also powered by Photon, are available on Prime Inference and OpenRouter.
