AI Agent StoreMoondream · Catalog verified
Moondream 3.1
Describe images, locate objects or answer questions about a picture. This is newly covered on our site; the model itself was released earlier.
Released 2026-07-07 · Catalog added 2026-10-15 UTC · Checked 2026-11-03. Catalog addition and provider launch are separate dates.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on your own tasks before switching; results for another version or thinking setting may not apply.
What you can use today
Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.
Exact catalog ID: moondream/moondream3.1-9b-a2b. The native model has separate skills for captions, questions, points and object boxes. Confirm that your chosen host exposes the skill you need; a chat endpoint may not expose every native feature.
Moondream 3.1 can run locally with Photon on supported NVIDIA GPUs or Apple Silicon. Its custom model license allows building applications but restricts reselling general-purpose model hosting or fine-tuning.
This OpenRouter offer lists $0.30 input and $2.50 output per million tokens. The provider’s July 7 launch lists its own Cloud service at $0.30/$1.00; choose the price for the service you actually use. Allow for retries and any tool fees. Models that think before answering may also charge for that work.
Provider release and specifications ↗
Inspect the exact catalog model ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. A cheaper token price does not guarantee a cheaper completed task.
Compare caching and long-context costs ↗