Login
MoondreamReasoningReasoningActive

Moondream: Moondream 3 Preview

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

Image
Start with this modelBrowse all models
Specification
Model ID
moondream/moondream3-preview
Weight license
Not verified; consult the exact publisher model card
Modality
Text+image >text
Context
32K tokens
Input
$0.300/1M
Output
$2.50/1M
Updated
Nov 14, 2026
Scores
Capabilities
  • No tool calling listed
  • Supports vision inputs
  • Standard context workflows
  • Supports deeper reasoning tasks

Input and output

Accepts Text, Image inputs. Returns Text outputs.

Supported parameters

include_reasoningmax_completion_tokensmax_tokensreasoningtemperaturetop_p

Related models

InclusionAI

inclusionAI: Ling 3.2 Flash (free)

Ling 3.2 Flash is a hybrid reasoning model from inclusionAI that accepts text and image input, with a 1M-token context window and up to 200 images per request. Thinking can...

Google

Google: Gemini 4 Hydrogen

Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than...

Google

Google: Gemini 4 Hydrogen (batch)

Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than...

Build with Moondream: Moondream 3 Preview

Describe what you want to make and pick this model in the composer. A database and hosting are included.

Start with this model