
Moondream 3.1 9B A2B
Model ranking
Not matched to the current verified ranking snapshot.
| Provider | Price | Provider model ID | Status | Context / max output | Source |
|---|---|---|---|---|---|
Cloudflare Workers AImoondream3.1-9B-A2B | Standard Tariff not listedInput $0.3USD / 1M tokensOutput $1USD / 1M tokens Updated 2026-11-22 · 15:43 UTCCloudflare Workers AI · StandardInput: $0.3 Output: $1 Published Workers AI USD list tariffs. Free daily Neuron allowance is separate, not a zero unit price. Image tile/step components must be evaluated together; no flat image price is inferred. Checked 2026-11-22T15:43:15.988Z Price source ↗ | @cf/moondream/moondream3.1-9B-A2B | Catalog-listedConditionsPublic catalog listing; account eligibility and capacity can vary. Verified component tariffs are supplied by the existing pricing engine. | Not supplied | Official source ↗2026-10-20 |
Moondream 3.1 9B A2B is a vision-language mixture-of-experts model exposed through distinct visual skills. Its 2B active label is not the total parameter count.
Moondream 3.1 9B A2B: suitable applications
Use the documented query, caption, point or detect skill for image questions, descriptions and locating objects.
Capabilities and technical details
A skill-specific interface can return text or spatial information without requiring the application to parse a general chat response into every task.
The model accepts text, image and returns text, structured data. The recorded terms are Moondream Model License 1.0; the linked source explains their scope.
Limitations and selection
The selected skill determines required inputs and output shape. Detection or pointing can fail on small, occluded or ambiguous targets, and the model has its own license terms.
Evaluate each intended visual skill separately, with representative image quality and object descriptions, rather than treating one caption test as evidence for detection accuracy.
Cloudflare API pricing
Deployment pricing is tied to the selected endpoint and its documented token components. Compare input, output and cached-input charges only where those components are actually quoted; an absent component is not an invented free rate.
Review the official Cloudflare endpoint reference and the Moondream model documentation. Compare the linked Cloudflare Workers AI provider profile with the xpu live model directory when selecting a deployment.
Specifications
- Catalog model ID
- moondream/moondream3.1-9B-A2B
- Developer model ID / revision
- Not verified in cited sources
- Input modalities
- text, imageCloudflare Workers AI endpoint; route-specific capabilities ↗
- Output modalities
- text, structured dataCloudflare Workers AI endpoint; route-specific capabilities ↗
- Context / input token limit
- Not verified in cited sources
- Maximum output tokens
- Not verified in cited sources
- Tool calling
- Not verified in cited sources
- Structured output
- Not verified in cited sources
- API parameters (source-specific)
- Not verified in cited sources
- Weight access
- Not verified in cited sources
- Weight license / access terms
- Moondream Model License 1.0Developer weight license / hosted access terms ↗
- Total parameters (billions)
- 9Developer model card / documentation ↗
- Active parameters (billions)
- 2Developer model card / documentation ↗
- Parameter-count details
- Developer-declared nominal model size; serialized tensor counts can differ. Active parameters, when supplied, are separate from total parameters.Developer model card ↗
- Download size (GB)
- Depends on checkpoint and precision; no verified file size
- Release date
- Not verified in cited sources
- Notes
- Cloudflare deployment limits and transport options are recorded on its offering. Weight license is separate from hosted-service conditions. Parameter sizes are developer-declared nominal labels; serialized tensor counts may differ.
Catalog entries link to their specification and availability sources. This is a curated selection, not every model each provider offers. Best prices are the lowest collected USD tariffs, not a total-cost estimate. Token offers are selected by input price, with output from the same tariff; workload mix may change the cheapest provider. Listed variants may require batch processing, off-peak hours, or specific media settings. Price coverage varies by provider; collected tariffs include their source and observation time. Arena user-preference scores are checked automatically every six hours against the latest published Text / overall dataset. Source: Arena / LMArena; CC BY 4.0. Selection and catalog matching by XPU LIVE. They apply to the shown evaluation configuration; listed prices may use different settings. Models without verified scores are not assumed to be weaker.
