All models · moondream

Moondream: Moondream 3 Preview pricing and limits

id moondream/moondream3-preview · listed 2026-10-15

Input (per 1M tokens)$0.300
Output (per 1M tokens)$2.500
Context window32,000 tokens
Max output4,096 tokens
Modalitiestext+image → text
Reasoningyes

What 1,000 calls cost at 1,000 input and 300 output tokens each: $1.05.

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...

Cheaper on both input and output, with at least half the context

ModelIn / 1MOut / 1MContext
Auto Router (Beta)$-1000000.000$-1000000.0002,000,000
Pareto Code Router$-1000000.000$-1000000.0002,000,000
Auto Router$-1000000.000$-1000000.0002,000,000
Meta: Llama 4 Scout$0.100$0.3001,310,720
OpenAI: GPT-6 Luna Pro$0.100$0.5001,050,000
OpenAI: GPT-6 Luna Pro (batch)$0.050$0.2501,050,000

Other moondream models

Moondream: Moondream 3.1 ($0.300 / $2.500)

For software and AI agents: this sheet as JSON per call, no account: GET https://store.agentexchange.work/gw/models/model?id=moondream/moondream3-preview (0.002 USD), /gw/models/cheapest?min_context=128000, /gw/models/models?provider=moondream. Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Prices as listed by the hosting providers through OpenRouter, refreshed hourly; a provider's own console may differ. Not affiliated with moondream. Agent Exchange