Moondream 3.1
$0.30 per 1M input tokens and $2.50 per 1M output tokens · 32K context · vision, reasoning, open weights.
Prices checked Oct 21, 2026 · tracked by LLM Cost Index since Oct 21, 2026
$0.30
input / 1M tokens
$2.50
output / 1M tokens
32K
context window
4K
max output
What Moondream 3.1 costs per month
Estimated monthly bill for typical workloads. Try your own numbers in the cost calculator.
| Workload | Per month |
|---|---|
| Customer chatbot 1,000 conversations a day, 8 turns each | $318 |
| Document Q&A (RAG) 500 questions a day over retrieved documents | $45.75 |
| Coding / tool-using agent 200 tasks a day, long tool-heavy contexts | $168 |
| Content generation 30 long articles a day | $6.43 |
| Classification / extraction 100,000 short items a day | $383 |
Price history
We started tracking Moondream 3.1 on Oct 21, 2026; the chart appears as soon as there is a second data point. See all recent price changes.
Cheaper alternatives to Moondream 3.1
Models with the same image input for at least 20% less (3:1 input/output mix), most capable first.
| Model | Input / 1M | Output / 1M | Context | Capabilities |
|---|---|---|---|---|
| MiMo-V2.6-Pro Xiaomi | $0.435 | $0.87 | 1.05M | visionaudiotoolsreasoningJSONopen weights |
| Claude Haiku 5.5 Anthropic | $0.10 | $0.50 | 1M | visiontoolsreasoningJSON |
| GLM 5.3 Flash Z.ai | $0.041 | $0.12 | 1.05M | visiontoolsreasoningJSONopen weights |
| DeepSeek V4.1 Flash 1017 DeepSeek | $0.30 | $1.20 | 1.05M | visiontoolsreasoningJSONopen weights |
| GPT-6 Luna OpenAI | $0.10 | $0.50 | 1.05M | visiontoolsreasoningJSON |
How to pay less for Moondream 3.1
For a customer chatbot (1,000 conversations a day, 8 turns each) that costs $318 a month at list price without caching:
| Option | Per month | You save |
|---|---|---|
| Move to MiMo-V2.6-Pro (similar capabilities) | $136 | $182 (57%) |
Other workloads: cut-your-bill tool for Moondream 3.1.
Specifications
| Model ID | moondream/moondream3.1-9b-a2b |
| Input | text, image |
| Output | text |
| Tool calling | No |
| Structured output | No |
| Reasoning mode | Yes |
| Open weights | Yes — moondream/moondream3.1-9B-A2B |
| Released | Oct 15, 2026 |
FAQ
- How much does Moondream 3.1 cost?
- $0.30 per million input tokens and $2.50 per million output tokens. Prices as of Oct 21, 2026.
- What is the context window of Moondream 3.1?
- 32K tokens, with up to 4K output tokens per response.
- Does Moondream 3.1 support images, tools and structured output?
- Images as input: yes. Tool calling: no. Structured (JSON) output: no. Reasoning mode: yes.
- What are cheaper alternatives to Moondream 3.1?
- Models with the same key capabilities for at least 20% less include MiMo-V2.6-Pro ($0.435 / $0.87), Claude Haiku 5.5 ($0.10 / $0.50), GLM 5.3 Flash ($0.041 / $0.12).
More from Moondream: all Moondream models · how we collect prices