Moondream model
Moondream 3 Preview API cost calculator
Moondream 3 Preview costs $0.30 per 1M input tokens and $2.50 per 1M output tokens on the Moondream API, with a 32K-token context window. A typical request (2K input, 500 output tokens) costs $0.0019 — about $55.50/month at 1,000 requests per day. Use the calculator below to model your exact workload.
Find me a cheaper modelWhat real workloads cost on Moondream 3 Preview
| Workload | Tokens (in / out) | Per request | Per 1K requests |
|---|---|---|---|
| Chatbot message | 500 / 300 | $0.0009 | $0.90 |
| RAG query with context | 4,000 / 500 | $0.0024 | $2.45 |
| Document summarization | 20,000 / 1,000 | $0.0085 | $8.50 |
| Agent coding session | 100,000 / 5,000 | $0.04 | $42.50 |
Moondream 3 Preview vs other Moondream models
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| Moondream 3 Preview | $0.30 | $2.50 | 32K |
| Moondream 3.1 | $0.30 | $2.50 | 32K |
Frequently asked questions
How much does Moondream 3 Preview cost per 1M tokens?
According to current pricing data, Moondream 3 Preview costs $0.30 per 1M input tokens and $2.50 per 1M output tokens. Processing 1M tokens each way costs $2.80.
What does a typical API request to Moondream 3 Preview cost?
A typical request with 2,000 input tokens and 500 output tokens costs $0.0019. At 1,000 requests per day that is $1.85 daily, or about $55.50 per month.
What is Moondream 3 Preview's context window?
Moondream 3 Preview supports a 32K-token context window (32,000 tokens).
Does Moondream 3 Preview support prompt caching?
No cache-read pricing is published for Moondream 3 Preview, so every input token is billed at the full $0.30 per 1M rate.
What is a cheaper alternative to Moondream 3 Preview?
gpt-oss-20b from OpenAI is currently the cheapest comparable option at $0.02 per 1M input tokens versus $0.30 for Moondream 3 Preview — roughly 17x cheaper on input.
Compare all current prices on the live model pricing dashboard, see Moondream 3 Preview vs gpt-oss-20b pricing, or run Moondream 3 Preview head-to-head against other models in the side-by-side comparison playground.
Pricing data via the OpenRouter models API.