Moondream 3.1
General purposeVisionMoondream · Released October 2026
Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts).
Facts and pricing
- Provider
- Moondream
- Context window
- 32K tokens
- Input price
- 3.6 credits / 1M tokens ($0.30 raw)
- Output price
- 30.0 credits / 1M tokens ($2.50 raw)
- Vision (image input)
- Yes
- Tool calling
- No
- Extended reasoning
- No
Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin. Raw prices shown per 1M tokens.
Try Moondream 3.1 now
What Moondream 3.1 is best for
- Balanced everyday work: writing, questions, brainstorming and summarization
- Working with images: screenshots, charts, photos and scanned documents alongside text
Moondream family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| Moondream 3 Preview | 32K | 3.6 | 30.0 | October 2026 |
| Moondream 3.1 | 32K | 3.6 | 30.0 | October 2026 |
Model comparisons
- Claude Opus 5.5 vs Claude Opus 5
- Claude Opus 5.5 vs GPT-6 Astra
- Claude Opus 5.5 vs GPT-6 Sol
- Claude Opus 5.5 vs Claude Sonnet 5
Frequently asked questions
- What is Moondream 3.1?
- Moondream 3.1 is an AI model by Moondream. Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts).
- How much does Moondream 3.1 cost on Zeplik?
- Input tokens cost 3.6 credits per million and output tokens 30.0 credits per million (1 credit = $0.10; the raw provider rates are $0.30 and $2.50 per million). New accounts start with free credits.
- How long can a conversation with Moondream 3.1 be?
- Moondream 3.1 has a 32K-token context window (32,000 tokens), which covers the conversation plus any documents you attach.
- Does Moondream 3.1 support images and tools?
- Moondream 3.1 accepts image input and does not support tool calling.
Related models
Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts).
Ripple-65B-Preview by ricursiveAI, a 65B model with native tool calling, served in BF16.
Crouton Alpha is a lightweight model built for scalable coding, agentic, and multimodal workflows. It's ideal for executing agentic sub-tasks, tool use, and document analysis in high-volume, repeated work.
GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text.
Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash.
More you can do with Moondream 3.1
- 468 AI skillsReady-to-run expert methods for writing, data, code and more, each running on Moondream 3.1 or any model you pick.
- 997 integrationsConnect Gmail, Slack, GitHub, Notion and hundreds more so the assistant can work in your apps.
- Simple pricingPlus, Pro and Max plans with a monthly credit allowance that works across every model.