Skip to content
Alpha
  • Models
  • Rankings
  • Ori
Talk to sales

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Ori
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Customers
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for moondream

Moondream: Moondream 3 Preview

moondream/moondream3-preview

Model weights
Compare

Moondream 3 Preview is served by 1 provider and supports reasoning.

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 a 32K-token context and an optional reasoning mode.

Modalities
In / out price
$0.30 / $2.50per 1M
Context
32K
Released
Oct 15, 2026
Compare
ProvidersPricingPerformanceUptimeAppsActivityDocumentationFAQExplore

Providers

This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Not currently available through EU in-region routing. In-region routing docs

Documentation

Guides, cookbooks, blog posts, and tools for building with Moondream: Moondream 3 Preview on OpenRouter.

  • Find Objects in ImagesCookbook

Explore more models

AI Models with Vision: Multimodal LLMs for Image UnderstandingCollectionAI Model RankingsRanking
Latency / throughput
$0.30$2.500.18s113 tok/s
93.44%
ProviderInput / Output /M
ThroughputUptime
  • Favicon for PrimeIntellect
    Input $0.30 / Output $2.50
    Throughput 113 tok/sUptime 93.44%
Throughput
113tok/s

P50, best across providers

Latency
0.18s

P50, best provider

1.
Favicon for https://betarena.ai/
ChartAI Predictions
new
2.58Mtokens
2.
Favicon for https://hellohaven.ai/
Hello Haven
new
2.28Mtokens
3.
Favicon for https://docfu.ai/
Docfu
new
1.2Mtokens
4.
Favicon for https://pilascontrole.com.br/
Pilas Controle
new
343Ktokens
5.
Favicon for https://aiyubot.com/
Aiyubot
new
340Ktokens
Rest of OpenRouter
46.7M
Top 5 Apps
11K

Frequently asked questions

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 a 32K-token context and an optional reasoning mode.

The Moondream 3 Preview documentation on OpenRouter includes the Find Objects in Images cookbook. The quickstart covers API keys and your first request, and the API reference lists every parameter.

Moondream 3 Preview costs $0.30/M input tokens and $2.50/M output tokens.

Moondream 3 Preview has a 32,000 token context window. It supports up to 4,096 completion tokens.

No. Moondream 3 Preview does not accept tools, so function calling is unavailable. It does not support response_format, so JSON output is not enforced.

Moondream 3 Preview accepts text and images as input and returns text.

Moondream 3.1 is another text model from Moondream.

Moondream 3 Preview was released on October 15, 2026.

More models from Moondream

Parakeet Ultra

Parakeet Ultra is Moondream's post-trained version of NVIDIA's Parakeet TDT 0.6B v3 speech-to-text model, with the same architecture, tokenizer, and 0.6B parameters. It lowers word error rate on the Open ASR Leaderboard English sets (5.80% vs 6.26%) and the 25-language FLEURS set (9.55% vs 11.62%), with larger gains on noisy and long-form audio. Supports 25 European languages and returns transcribed text with segment and word timestamps.

Transcription$0.000017/second
Moondream 3.1

Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with a 32K-token context and an optional reasoning mode.

Text32K context$0.30 / $2.50