Best for budget
Low input/output cost for high-volume workloads.
Model · Moondream
Moondream 3.1
Moondream 3.1 is served by Moondream through OpenRouter. It provides 32K tokens of context and supports text, vision inputs.
Context window
32K tokens
Input / 1M tokens
$0.300
Output / 1M tokens
$2.50
Key facts
| Provider | Moondream |
| OpenRouter ID | moondream/moondream3.1-9b-a2b |
| Modalities | Text, Vision |
| Best for | Multimodal, Budget |
Source
openrouter.ai/api/v1/models Verified 2026-10-16 Drift-checked daily 06:00 CST Best-fit workloads
Best multimodal
Handles images, files, audio or video inputs.
Cost estimates
These examples use the 2026-10-16 input and output prices. Cache discounts, provider surcharges and tool fees are excluded.
| Workload | Input | Output | Estimated cost |
|---|---|---|---|
| Quick test | 20,000 | 5,000 | $0.019 |
| Product chat month | 500,000 | 125,000 | $0.463 |
| Document batch | 5,000,000 | 1,000,000 | $4.00 |
Strengths
- ✓ A 9B vision-language model with 2B active parameters, open weights on Hugging Face
- ✓ Built for visual question answering, captioning, OCR and visual reasoning over images
- ✓ Reads images at $0.30 per million input tokens — a tenth of the flagship multimodal rows
Limitations
- ! 32,000-token context and a 4,096-token output ceiling: a reader for pictures, not a long-document model
- ! Text output only
- ! The preview and 3.1 rows are both live at the same price, so the version you get depends on the id you call
OpenRouter API quickstart
Run these examples from your server or edge function. Keep the OpenRouter API key private and do not expose it in browser code.
cURL
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "moondream/moondream3.1-9b-a2b",
"messages": [{ "role": "user", "content": "Summarize this document in five bullet points." }],
"max_tokens": 500
}'JavaScript / TypeScript
const response = await fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.OPENROUTER_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "moondream/moondream3.1-9b-a2b",
messages: [{ role: "user", content: "Summarize this document in five bullet points." }],
max_tokens: 500,
}),
});
const data = await response.json();
console.log(data.choices[0].message.content);How to evaluate Moondream 3.1
- Run five real tasks from your product, not generic demo prompts.
- Record token usage, latency and output quality.
- Estimate cost using your real input/output mix.
- Compare it against one model with a similar price and one stronger model.
Compare models View on OpenRouter ↗
Moondream 3.1 FAQ
What is Moondream 3.1?
Moondream 3.1 is a Moondream model available through OpenRouter. It supports text, vision inputs and is suited for multimodal, budget workloads.
How much does Moondream 3.1 cost on OpenRouter?
The 2026-10-16 snapshot lists $0.300 per 1M input tokens and $2.50 per 1M output tokens. Verify current pricing on OpenRouter before production.
How large is Moondream 3.1's context window?
Moondream 3.1 offers 32K tokens of context in the current snapshot. Provider-specific limits and surcharges may apply.
Pricing and context data are based on a 2026-10-16 snapshot. Provider limits can change; always verify on OpenRouter before production.