# Parallel Decisions

> Parallel Decisions on Clonvo: 32K context, $0.00 input and $0.00 output per 1M tokens.

Parallel's decision model, grounded in the live web: it researches your question and answers the fields of your JSON schema (choices, yes/no probabilities, scores) with probabilities and the sources it used. Requires response_format json_schema.

-   Model id: `parallel/decisions-fast`
-   Provider: Parallel
-   Released: Not published
-   Context: 32K tokens
-   Max output: not published

## Pricing

The provider’s list price in USD. Requests on credits are charged exactly this; each response reports its cost in usage.cost.

| Charge | Price | Unit |
| --- | --- | --- |
| Input (prompt) | $0.00 | per 1M tokens |
| Output (completion) | $0.00 | per 1M tokens |
| Request | $0.001 | per request |

## Capabilities

-   Structured outputs

### Supported parameters

Upstream parameters this model honours. Others may be ignored.

-   `response_format`
-   `structured_outputs`

## Quick start

Use the OpenAI SDK with Clonvo’s base URL and this model id.

```python
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.clonvo.com/v1",
    api_key=os.environ["CLONVO_API_KEY"],
)

completion = client.chat.completions.create(
    model="parallel/decisions-fast",
    messages=[{"role": "user", "content": "Summarise the plot of Hamlet in one sentence."}],
)
print(completion.choices[0].message.content)
```

## Data policy

Requests to this model are sent to Parallel, whose API terms govern how they handle your data: [Parallel data policy](https://parallel.ai/customer-terms). Clonvo doesn’t store prompts or responses unless your organization turns on retention.