ModelPriceWatch.com
Last scan 2026-10-16 Models tracked 290 Providers 40 Cheapest paid Granite 4.0 H Micro $0.017/Mtok in Every price links to its source

Moondream 3.1 9B A2B

by Moondream · 9B (2B active) parameters

Current open weights open weights cheap tier
Email me when Moondream 3.1 9B A2B gets cheaper
Availability: Sold by Moondream on Moondream Cloud (every workspace includes $5 a month of usage credits), and through OpenRouter, where PrimeIntellect is the only provider. The weights are on Hugging Face under the Moondream model license, which allows most commercial use but not offering the model as a hosted service without a separate licence.

Today's price · per 1M tokens

Input

$0.300

per 1M tokens

Output

$1.00

per 1M tokens

Blended

$0.475

blended $/1M — 3:1 weighted input:output

How this price is scoped: Moondream's own pricing page lists Moondream 3.1 9B A2B at $0.30 / 1M input tokens and $1.00 / 1M output tokens real-time, and half that in batch ($0.15 / $0.50). We publish the real-time rate. OpenRouter lists this model at $2.50 per 1M output tokens; that is the rate of PrimeIntellect, the third-party host serving it there, not Moondream's.

Source: official Moondream pricing · read MODELPRICEWATCH.COM · 2026-10-16

Price receipt

We read Moondream's own pricing page on and found MOONDREAM 3.1 9B A2B — REAL-TIME listed with a price on the same row — that read is where the number above comes from, recorded as a new model. We keep the page text we read; its content hash is 7acf40ef9a.

Overview

Moondream's vision language model, a mixture-of-experts with 9B total and 2B active parameters. It answers questions about images, captions, reads text (OCR), points at, counts and detects objects, and has a 32K-token context window. $0.30 per 1M input tokens and $1.00 per 1M output tokens on Moondream Cloud.

Run it yourself

Deploy this open model on rented GPUs

Open weights mean you can self-host instead of paying per-token API prices. These platforms let you serve it on demand — often cheaper at scale.

RunPod →
Rent GPUs by the second and serve any open-weight model yourself.
Novita AI →
Serverless open-model inference billed per token — no GPU ops.
Vast.ai →
GPU marketplace — rent spot/on-demand GPUs cheaply and serve any open-weight model.

Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.

Capabilities

struck through = not supported
Input 2/4
Text ✓ Image ✓ Audio Video
Output
Text ✓
Features 2/9
Prompt caching Reasoning Coding Fast inference Long context Open weights ✓ Multimodal ✓ Web search Realtime

Specifications

Provider
Moondream
Context window
32K tokens
Modality
text, image
Parameters
9B (2B active)
Open source
Yes — open weights available
Released
Status
Current
Last updated
Tags
open-weightsmultimodalmoe

Availability verified: — listed on Moondream's own page

Official pricing page