Moondream / moondream/moondream3-preview

Moondream 3 Preview - access through LLMTR

Moondream 3 Preview is the preview release of Moondream 3, a vision-language model with 9B parameters and 2B active per token, for visual question answering, captions, reading text in images (OCR) and visual reasoning. It takes text and image input and returns text, with a 32,000-token context window. Send images as base64 data URLs; https image URLs are not accepted. Reasoning is off by default; turn it on with reasoning: true or the :think suffix. Tool calling, response_format and stop sequences are not supported. The newer release of the family is Moondream 3.1.

Technical specifications

Canonical IDmoondream/moondream3-preview
ProviderMoondream
Context window32,000 tokens
OperationsCHAT_COMPLETIONS
Modalitiestext, image

Pricing

An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.

OperationMetricUnitPrice
CHAT_COMPLETIONSINPUT_TEXTPER_1M_TOKENS$0.300000
CHAT_COMPLETIONSOUTPUT_TEXTPER_1M_TOKENS$2.50

Example usage

With existing OpenAI SDK flows, change only the base URL and model identifier.

curl https://llmtr.com/v1/chat/completions   -H "Authorization: Bearer llmtr-your_key"   -H "Content-Type: application/json"   -d '{"model":"moondream/moondream3-preview","messages":[{"role":"user","content":"Hello"}]}'

Guides about this model

Related models