# Liquid d1.2 Ultra

Liquid d1.2-ultra is Liquid AI's most accurate decision model for classification, routing, and scoring across text and images. It answers typed yes/no, multiple-choice, and scale questions in a single forward pass and returns calibrated probabilities without generating output tokens, for demanding tasks such as document review and visual inspection.

- **Model ID:** `liquid/d1.2-ultra`
- **Type:** evaluation
- **Providers:** liquid
- **Context window:** 65,536
- **Maximum output tokens:** 0
- **Pricing:** $0.042/1M input tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/d1.2-ultra

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

```ts
import { experimental_decide as decide } from 'ai';

const result = await decide({
  model: 'liquid/d1.2-ultra',
  state: 'The support agent issued a full refund to the customer.',
  questions: {
    refunded: {
      type: 'boolean',
      instructions: 'Was a refund issued?',
    },
  },
})
```

## Links

- [Model page](https://vercel.com/ai-gateway/models/d1.2-ultra)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://www.liquid.ai/blog/d1-2)
- [Provider pricing](https://www.liquid.ai/blog/d1-2)


If you encounter incorrect information, can’t find what you need, need a capability Vercel doesn’t currently offer, or have any other feedback to report, please do it by following the instructions at https://vercel.com/feedback.md.
