← All models
Nemotron-Labs-Diffusion-VLM-8B is the vision-language extension of the Nemotron-Labs-Diffusion family.
Details
- Accepts
- image
Pricing
- Input
- 625 cr / 1M tokens
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| promptrequired | string | Prompt to answer about the image. |
| image_urlrequired | string | URL of the image to be processed. |
| threshold | number | Confidence threshold used by diffusion decoding. |
| max_tokens | integer | Maximum number of tokens to generate. |
| block_length | integer | Block length used by diffusion decoding. |
| num_inference_steps | — | Number of diffusion decoding steps. Defaults to 256, rounded up only when omitted and required by the upstream block schedule. Explicit values must be at least max_tokens / block_length and divisible by max_tokens / block_length. |
Output
| Field | Type | Description |
|---|---|---|
| usage | — | Token and diffusion decoding usage information. |
| output | string | Generated answer. |
| timings | — | Request timing breakdown in seconds. |