moondream
Moondream: Moondream 3.1
moondream/moondream3.1-9b-a2b
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
Moondream 3.1 (moondream/moondream3.1-9b-a2b) is a vendor-documented vision-language model that accepts text and images and returns text. Its documentation describes a mixture-of-experts design with 9B total and 2B active parameters, native query, detect, point, and caption skills, and local or hosted access. The OpenRouter catalog also lists OCR and a 32,000-token context. Performance claims are source-reported; the pack contains no independent measurements.[1][2]
Strengths
- The vendor reports a mixture-of-experts architecture with 9B total and 2B active parameters, presented as fast and inexpensive to deploy.[2]
- It accepts image and text inputs, produces text, and is listed with a 32,000-token context length.[1]
- Documented native skills include query, detect, point, and caption with structured output; the catalog also describes OCR.[1][2]
Limitations
- Evidence comes from a catalog and vendor documentation; no independent benchmark results or workload measurements were supplied.[1][2]
- The source names a custom Moondream license but does not provide its operative terms, so permitted uses cannot be determined from the evidence alone.[2]
- Local execution is documented only through Photon on NVIDIA Ampere-or-newer GPUs and Apple Silicon Macs; support elsewhere is unknown.[2]
Where to use it
- Consider evaluating it for captioning, visual question answering, and OCR-oriented workflows that require text output.[1][2]
- It may suit prototypes needing structured object detection or visual pointing outputs.[2]
- Teams can compare local Photon deployment with the hosted API, subject to hardware, license, and workload validation.[2]
Sources
- [1] OpenRouter catalog · Moondream: Moondream 3.1Sources checked: Nov 13, 2026
- [2] Model documentation · Moondream: Moondream 3.1Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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). It handles visual question answering, captioning, OCR, and...
Specifications
- Model ID
- moondream/moondream3.1-9b-a2b
- Canonical ID
- moondream/moondream3.1-9b-a2b-20261013
- Creator
- moondream
- Added to OpenRouter
- 15.10.2026
- Context length
- 32,000
- Modality
- text+image->text
- Input modalities
- text, image
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.300 / out $2.5
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Coding | No measurement | — |
| Agents | No measurement | — |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| PrimeIntellectfp8 | 32,000 | $0.300 | $2.5 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.