> ## 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.

# Fireworks

> Fireworks AI delivers fast open-source model inference with integrated fine-tuning capabilities, allowing teams to both deploy and customize models through the same platform.

Fireworks offers 9 models through Lava's AI Gateway, supporting Chat Completions. Authentication uses `Authorization: Bearer`. See the [Fireworks API docs](https://docs.fireworks.ai/api-reference) for provider-specific parameters.

> [!NOTE]
>
> Supports both **managed** (Lava's API keys) and **unmanaged** (bring your own credentials) mode.

## Quick Start

```typescript theme={null}
const response = await fetch('https://api.lava.so/v1/forward?u=https%3A%2F%2Fapi.fireworks.ai%2Finference%2Fv1%2Fchat%2Fcompletions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    Authorization: `Bearer ${forwardToken}`,
  },
  body: JSON.stringify({
    model: 'accounts/fireworks/models/kimi-k3',
    messages: [{ role: "user", content: "Hello!" }],
  }),
});
```

## Chat Completions

**Target URL:** `https://api.fireworks.ai/inference/v1/chat/completions`

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

| Model | Input / 1M tokens | Output / 1M tokens |
| - | - | - |
| accounts/fireworks/routers/kimi-k3-fast | \$4.50 | \$22.50 |
| accounts/fireworks/models/kimi-k3 | \$3.00 | \$15.00 |
| accounts/fireworks/routers/glm-5p3-fast | \$2.10 | \$6.60 |
| accounts/fireworks/models/qwen3p8-max | \$2.00 | \$6.00 |
| accounts/fireworks/models/glm-5p3 | \$1.40 | \$4.40 |
| accounts/fireworks/models/minimax-m3 | \$0.30 | \$1.20 |
| accounts/fireworks/models/deepseek-v4p1-flash | \$0.22 | \$0.66 |
| accounts/fireworks/models/glm-5p3-flash | \$0.15 | \$0.50 |
| accounts/fireworks/models/minimax-m3p1-flash | \$0.15 | \$0.60 |

## Next Steps

> [card] [All Providers](https://lava.so/docs/gateway/supported-providers.md)
>
> Browse all supported AI providers

> [card] [Forward Proxy](https://lava.so/docs/gateway/forward-proxy.md)
>
> Learn how to construct proxy URLs and authenticate requests


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