Loading template…
✦

moondream3-preview

⚡ Run with API

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

Pricing: Input 72 credits / 1M tokens (≈ $0.36), Output 600 credits / 1M tokens (≈ $3.00).

Prices updated

Conversation
✦

How can I help you today?

This demo page does not include the full memory features of the client. For the complete experience, please use the client or the CLI.

More AI models from Moondream

≡
README
Complete guide to using Moondream 3 Preview

Moondream 3 Preview API on ModelFold

Moondream 3 Preview is a vision-language model from Moondream with 9B total and 2B active parameters (mixture-of-experts), handling visual question answering, captioning, OCR and visual reasoning over images. Try Moondream 3 Preview in the ModelFold Playground, then call it from your own code through an OpenAI-compatible chat completions API.

What Is the Moondream 3 Preview API

Moondream 3 Preview at a glance

Moondream 3 Preview is a chat model from Moondream. It accepts text and images as input and returns text, with a context window of up to 32K tokens.

Use it without hosting anything

On ModelFold you call Moondream 3 Preview with a single API key — no model weights to download and no inference servers to run. The same key also works for the other chat, image, video and audio models on ModelFold.

Core Capabilities of Moondream 3 Preview

Up to 32K tokens of context

Keep long conversations, large documents and sizeable code in a single request, so the model can reason over the full material instead of fragments.

Understands images

Besides text, Moondream 3 Preview accepts images as input, so a single request can combine instructions with visual or other media.

Reasoning mode

Moondream 3 Preview can produce reasoning before its final answer; in the Playground you can switch reasoning on or off to compare results.

How to Use Moondream 3 Preview on ModelFold

  1. 1

    Step 1: Try it in the Playground

    Open the Playground at the top of this page, type a prompt and see how Moondream 3 Preview responds before writing any code.

  2. 2

    Step 2: Create an API key

    Sign in to ModelFold and create an API key in the console. Keep it secret and send it as a Bearer token.

  3. 3

    Step 3: Send a request

    Call POST https://modelfold.ai/v1/chat/completions with "model": "moondream3-preview" and your messages. Existing OpenAI-compatible SDKs work by changing the base URL and key.

  4. ✓

    Step 4: Ship and monitor

    Integrate the response into your product and check token usage and spend for every call in the console logs.

What You Can Build with Moondream 3 Preview

Screenshot and image understanding

Read screenshots, charts, diagrams and photos alongside text — for UI review, visual QA or turning images into structured data.

High-volume pipelines

Run classification, extraction, rewriting and batch jobs at scale where cost per request matters.

Long-document workflows

Feed in long reports, contracts, manuals or codebases and ask for summaries, comparisons and answers grounded in the material.

Frequently Asked Questions

What is Moondream 3 Preview?⌄

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

Which inputs does Moondream 3 Preview support?⌄

Moondream 3 Preview accepts text and images and returns text. Through ModelFold you can send text and images (OpenAI-style image_url content); in the Playground you can also attach documents, which are converted to text.

How long is the context window of Moondream 3 Preview?⌄

Up to 32K tokens, shared between your input and the model’s output.

Does Moondream 3 Preview support function calling?⌄

Function calling is not listed for Moondream 3 Preview; requests that include tools will be rejected. Use plain prompts or JSON output instead.

How is Moondream 3 Preview billed on ModelFold?⌄

Pay as you go by tokens: input and output tokens are charged at the per-million-token prices shown on this page. There is no monthly fee, and failed requests are not charged.

How do I call Moondream 3 Preview through the API?⌄

Send a POST request to https://modelfold.ai/v1/chat/completions with "model": "moondream3-preview", using your ModelFold API key as the Bearer token.

Rate card
Input72 credits 1M tokens≈ $0.36
Output600 credits 1M tokens≈ $3.00

Billed per token: input and output are priced separately, and thinking tokens count as output. The Playground charges exactly the same way.

Read API docs →AI Agents · Claude Code / Cursor / Trae →
Quick start
POST/v1/chat/completions
curl https://modelfold.ai/v1/chat/completions \
  -H "Authorization: Bearer $MODELFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"moondream3-preview","messages":[{"role":"user","content":"Hello"}]}'