> ## Documentation Index
> Fetch the complete documentation index at: https://lava.so/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Chutes

> Chutes.ai is a decentralized AI compute platform offering LLM inference and other AI workloads across distributed GPU providers.

Chutes offers 18 models through Lava's AI Gateway, supporting Chat Completions. Authentication uses `Authorization: Bearer`. See the [Chutes API docs](https://chutes.ai/docs) for provider-specific parameters.

<Info>Supports both **managed** (Lava's API keys) and **unmanaged** (bring your own credentials) mode.</Info>

## Quick Start

```typescript theme={null}
const response = await fetch('https://api.lava.so/v1/forward?u=https%3A%2F%2Fllm.chutes.ai%2Fv1%2Fchat%2Fcompletions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    Authorization: `Bearer ${forwardToken}`,
  },
  body: JSON.stringify({
    model: 'deepseek-ai/DeepSeek-V3-0324',
    messages: [{ role: "user", content: "Hello!" }],
  }),
});
```

## Chat Completions

**Target URL:** `https://llm.chutes.ai/v1/chat/completions`

|                  |                                          |
| ---------------- | ---------------------------------------- |
| **Content Type** | `application/json`                       |
| **Streaming**    | Yes (set `stream: true` in request body) |

| Model                                         | Input / 1M tokens | Output / 1M tokens |
| --------------------------------------------- | ----------------- | ------------------ |
| tngtech/DeepSeek-TNG-R1T2-Chimera             | \$0.3024          | \$0.3024           |
| deepseek-ai/DeepSeek-V3-0324                  | \$0.27216         | \$0.27216          |
| deepseek-ai/DeepSeek-R1-0528                  | \$0.27216         | \$0.27216          |
| deepseek-ai/DeepSeek-V3                       | \$0.27216         | \$0.27216          |
| unsloth/gemma-3-27b-it                        | \$0.1568          | \$0.1568           |
| Qwen/Qwen2.5-72B-Instruct                     | \$0.1008          | \$0.1008           |
| NousResearch/DeepHermes-3-Mistral-24B-Preview | \$0.06552         | \$0.06552          |
| deepseek-ai/DeepSeek-R1-Distill-Llama-70B     | \$0.0504          | \$0.0504           |
| Qwen/Qwen3-30B-A3B                            | \$0.03024         | \$0.03024          |
| chutesai/Mistral-Small-3.2-24B-Instruct-2506  | \$0.03024         | \$0.03024          |
| Qwen/Qwen3-14B                                | \$0.03024         | \$0.03024          |
| Qwen/Qwen2.5-VL-32B-Instruct                  | \$0.03024         | \$0.03024          |
| Qwen/Qwen2.5-Coder-32B-Instruct               | \$0.03024         | \$0.03024          |
| unsloth/gemma-3-12b-it                        | \$0.03024         | \$0.03024          |
| unsloth/Mistral-Small-24B-Instruct-2501       | \$0.03024         | \$0.03024          |
| Qwen/Qwen3-32B                                | \$0.027216        | \$0.027216         |
| chutesai/Mistral-Small-3.1-24B-Instruct-2503  | \$0.027216        | \$0.027216         |
| unsloth/Mistral-Nemo-Instruct-2407            | \$0.01512         | \$0.01512          |

## Next Steps

<CardGroup cols={2}>
  <Card title="All Providers" icon="grid" href="/gateway/supported-providers">
    Browse all supported AI providers
  </Card>

  <Card title="Forward Proxy" icon="route" href="/gateway/forward-proxy">
    Learn how to construct proxy URLs and authenticate requests
  </Card>
</CardGroup>