> ## 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.

# Baseten

> Baseten runs open-weight frontier models (GLM, DeepSeek, Kimi, gpt-oss, Nemotron) on dedicated US infrastructure through an OpenAI-compatible API, and also hosts custom fine-tuned models as production endpoints.

Baseten offers 16 models through Lava's AI Gateway, supporting Chat Completions. Authentication uses `Authorization: Bearer`. See the [Baseten API docs](https://docs.baseten.co) 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%2Finference.baseten.co%2Fv1%2Fchat%2Fcompletions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    Authorization: `Bearer ${forwardToken}`,
  },
  body: JSON.stringify({
    model: 'baseten-glm-5.3',
    messages: [{ role: "user", content: "Hello!" }],
  }),
});
```

## Chat Completions

**Target URL:** `https://inference.baseten.co/v1/chat/completions`

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

| Model | Input / 1M tokens | Output / 1M tokens |
| - | - | - |
| baseten-kimi-k3 | \$3.00 | \$15.00 |
| baseten-glm-5.3-fast | \$2.10 | \$6.60 |
| baseten-glm-5.2-fast | \$2.10 | \$6.60 |
| baseten-deepseek-v4-pro | \$1.74 | \$3.48 |
| baseten-glm-5.3 | \$1.40 | \$4.40 |
| baseten-glm-5.2 | \$1.40 | \$4.40 |
| baseten-inkling | \$1.00 | \$4.05 |
| baseten-kimi-k2.7-code | \$0.95 | \$4.00 |
| baseten-kimi-k2.6 | \$0.95 | \$4.00 |
| baseten-glm-4.7 | \$0.60 | \$2.20 |
| baseten-nemotron-3-ultra | \$0.60 | \$2.40 |
| baseten-inkling-small | \$0.50 | \$1.20 |
| baseten-deepseek-v4.1-flash | \$0.30 | \$1.20 |
| baseten-glm-5.3-flash | \$0.15 | \$0.50 |
| baseten-deepseek-v4-flash-0731 | \$0.13 | \$0.26 |
| baseten-gpt-oss-120b | \$0.10 | \$0.50 |

## Next Steps

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

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


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.