# Divergent Labs

> Documentation for Divergent Labs models, GPU compute and sandboxes.

Divergent Labs has three products. All three draw on the same org credit.

## Models

Small models that each do one job in a product, such as writing a chat title or an inbox preview. Your code sends the item as JSON and gets one line back. Billed per token.

| Model | What it does | Price |
| --- | --- | --- |
| [Rubric](https://docs.divergentlabs.xyz/models/rubric.md) | Chat titles, and one-line previews of emails, messages, tickets and agent actions. | $0.10 per million input tokens. Output is free. |

[Get started with models →](https://docs.divergentlabs.xyz/models.md)

## Compute (private beta)

GPUs by the minute for training and evaluation jobs. Start a run from your code's directory with the `div` CLI, or from an agent with the MCP server. Set a spend limit in dollars and the run stops when it reaches it. From $4.95 per H100 hour.

```bash
div login
div run --gpu h100 train.py::run --max-spend 5.00
```

Compute is open to invited orgs, and its commands and prices can change before general availability. [Request access](https://tally.so/r/yPOxpB).

[Get started with compute →](https://docs.divergentlabs.xyz/compute.md)

## Sandboxes

Linux machines for agents. Create one, run commands in it, stop it, and resume it later with its files and memory intact. Every sandbox runs Claude Code and OpenCode, so you can send it a task with `div agent prompt`. From 3¢ an hour, billed by the minute. Sandboxes have no GPU. For GPU jobs, use Compute.

```bash
SB=$(div sandbox create)
div sandbox exec $SB -- npm test
```

[Get started with sandboxes →](https://docs.divergentlabs.xyz/sandboxes.md)

## Docs as Markdown

Every page is also available as Markdown: add `.md` to the URL, or use **Copy page**. [`/llms.txt`](https://docs.divergentlabs.xyz/llms.txt) lists every page, for agents that read the docs before calling the API or the CLI.