qwen
Moondream 3 Preview vs Qwen3.8 27B
58.1 overall · $0.730 / 1M
// moondream
Moondream 3 Preview
moondream/moondream3-preview
Moondream 3 Preview costs $0.300 per 1M input tokens and $2.50 per 1M output tokens with a 32K-token context window.
A reasoning model from moondream, released Oct 15, 2026. LiveBench hasn't published a run for it, so this page carries measured price and specs only — no benchmark numbers.
- Input / 1M
- $0.300
- Output / 1M
- $2.50
- Context
- 32K
- LiveBench overall
- Not evaluated
Specs and pricing
| Input price USD per 1M prompt tokens | $0.300 |
|---|---|
| Output price USD per 1M completion tokens, reasoning included | $2.50 |
| Blended price 3:1 input:output — #161 most expensive of 350 listed models | $0.850 |
| Cached input read Blank means not priced separately — not free | — |
| Cache write | — |
| Context window | 32,000 tokens |
| Max output | 4,096 tokens |
| Input modalities | text, image |
| Tool calling | No |
| Extended reasoning | Yes |
| Knowledge cutoff | — |
| Listed | Oct 15, 2026 |
What Moondream 3 Preview costs to run
Monthly list cost across five workload shapes, using the published cached-input rate where there is one. A floor, not a quote — batch discounts and cache writes aren't included.
| Workload | Per month |
|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $272.00/mo |
| RAG assistant 8K in / 600 out × 100K requests | $390.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $440.00/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $487.50/mo |
| Bulk classification 500 in / 20 out × 5M requests | $1,000/mo |
Compare Moondream 3 Preview with
Benchmarked models at a similar price.
xiaomi
Moondream 3 Preview vs MiMo-V2.6-Pro
74.9 overall · $0.544 / 1M
minimax
Moondream 3 Preview vs MiniMax M3
52.6 overall · $0.525 / 1M
stepfun
Moondream 3 Preview vs Step 5 Preview
62.0 overall · $1.43 / 1M
Moondream 3 Preview vs Gemini 3.7 Flash
67.2 overall · $1.50 / 1M
z-ai
Moondream 3 Preview vs GLM 5.3
60.7 overall · $1.57 / 1M
Moondream 3 Preview FAQ
How much does Moondream 3 Preview cost?
Moondream 3 Preview lists at $0.300 per 1M input tokens and $2.50 per 1M output tokens. A RAG assistant handling 100K requests a month (8K tokens in, 600 out) comes to about $390.00 at list price.
What is the context window of Moondream 3 Preview?
Moondream 3 Preview accepts up to 32,000 tokens of context and can return up to 4,096 output tokens per response.
Does Moondream 3 Preview support tool calling?
Moondream 3 Preview does not list tool (function) calling support and exposes extended reasoning. It accepts text, image input.
How does Moondream 3 Preview score on benchmarks?
LiveBench has not published a run for Moondream 3 Preview yet. Until it does, compare it on price and specs, or run your own evaluation on your own tasks.
What is the API model ID for Moondream 3 Preview?
On OpenRouter the model ID is "moondream/moondream3-preview". It was listed on Oct 15, 2026.
More from moondream
How these numbers are produced
- Price and specs — provider list data from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores and ranks — LiveBench release 2026-09-02. Ranks count only models that have a published run; a blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.