Skip to content
AnyRouter
All releases
Added

Moondream 3 Preview

Moondream 3 Preview joins the catalog through BYOK: a 9B mixture-of-experts vision-language model with 2B active parameters and a 32K-token context window.

moondream/moondream3-preview is Moondream's vision-language model with a mixture-of-experts design (9B total, 2B active parameters). It takes text and image input and answers in text: visual question answering, captioning, OCR and visual reasoning, with a 32K-token context window. Moondream released it in September 2025; Moondream 3.1 is its successor. Hosts list it at $0.30 per million input tokens and $2.50 per million output tokens.

AI SDK
import { createAnyRouter } from "@anyr/ai-sdk-provider"
import { generateText } from "ai"

const anyrouter = createAnyRouter()
const { text } = await generateText({
  model: anyrouter("moondream/moondream3-preview"),
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "What is in this image?" },
        { type: "image", image: new URL("https://example.com/photo.jpg") },
      ],
    },
  ],
})
console.log(text)
Coding agent
curl -fsSL https://anyrouter.dev/setup.sh | bash
anyr login
anyr claude --model "moondream/moondream3-preview"

Moondream 3 Preview is BYOK-only. Add a key under Dashboard → BYOK; AnyRouter charges nothing for a BYOK route and your provider bills you at its own rate.

Playbooks: AI SDK, OpenAI SDK, coding agents, playground.

Moondream 3 Preview open-vocabulary object detection with boxes drawn on an image
Open-vocabulary detection. Source: Moondream.
Moondream 3 Preview pointing at and counting objects in an image
Pointing and counting. Source: Moondream.

Looking for the full catalog? Browse all models.