> ## 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.

# Novita

> Novita AI provides GPU cloud inference for both text and image generation, supporting LLM chat completions alongside Stable Diffusion image synthesis through a unified platform.

Novita offers 37 models through Lava's AI Gateway, supporting Chat Completions, Embeddings. Authentication uses `Authorization: Bearer`. See the [Novita API docs](https://novita.ai/docs/api-reference) 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%2Fapi.novita.ai%2Fv3%2Fopenai%2Fchat%2Fcompletions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    Authorization: `Bearer ${forwardToken}`,
  },
  body: JSON.stringify({
    model: 'qwen/qwen3-4b-fp8',
    messages: [{ role: "user", content: "Hello!" }],
  }),
});
```

## Chat Completions

**Target URL:** `https://api.novita.ai/v3/openai/chat/completions`

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

| Model                                             | Input / 1M tokens | Output / 1M tokens |
| ------------------------------------------------- | ----------------- | ------------------ |
| deepseek/deepseek-r1                              | \$4.00            | \$4.00             |
| sao10k/l3-70b-euryale-v2.1                        | \$1.48            | \$1.48             |
| sao10k/l31-70b-euryale-v2.2                       | \$1.48            | \$1.48             |
| deepseek/deepseek\_v3                             | \$0.89            | \$0.89             |
| qwen/qwen2.5-vl-72b-instruct                      | \$0.80            | \$0.80             |
| deepseek/deepseek-r1-distill-llama-70b            | \$0.80            | \$0.80             |
| deepseek/deepseek-prover-v2-671b                  | \$0.70            | \$2.50             |
| deepseek/deepseek-r1-0528                         | \$0.70            | \$2.50             |
| deepseek/deepseek-r1-turbo                        | \$0.70            | \$2.50             |
| microsoft/wizardlm-2-8x22b                        | \$0.62            | \$0.62             |
| meta-llama/llama-3-70b-instruct                   | \$0.51            | \$0.74             |
| deepseek/deepseek-v3-turbo                        | \$0.40            | \$1.30             |
| qwen/qwen-2.5-72b-instruct                        | \$0.38            | \$0.40             |
| deepseek/deepseek-r1-distill-qwen-32b             | \$0.30            | \$0.30             |
| deepseek/deepseek-v3-0324                         | \$0.27            | \$1.12             |
| meta-llama/llama-4-maverick-17b-128e-instruct-fp8 | \$0.27            | \$0.85             |
| thudm/glm-4-32b-0414                              | \$0.24            | \$0.24             |
| qwen/qwen3-235b-a22b-fp8                          | \$0.20            | \$0.80             |
| meta-llama/llama-4-scout-17b-16e-instruct         | \$0.18            | \$0.59             |
| deepseek/deepseek-r1-distill-qwen-14b             | \$0.15            | \$0.15             |
| nousresearch/hermes-2-pro-llama-3-8b              | \$0.14            | \$0.14             |
| meta-llama/llama-3.3-70b-instruct                 | \$0.135           | \$0.40             |
| google/gemma-3-27b-it                             | \$0.119           | \$0.20             |
| qwen/qwen3-32b-fp8                                | \$0.10            | \$0.45             |
| qwen/qwen3-30b-a3b-fp8                            | \$0.09            | \$0.45             |
| gryphe/mythomax-l2-13b                            | \$0.09            | \$0.09             |
| qwen/qwen2.5-7b-instruct                          | \$0.07            | \$0.07             |
| Sao10K/L3-8B-Stheno-v3.2                          | \$0.05            | \$0.05             |
| sao10k/l3-8b-lunaris                              | \$0.05            | \$0.05             |
| mistralai/mistral-nemo                            | \$0.04            | \$0.17             |
| meta-llama/llama-3-8b-instruct                    | \$0.04            | \$0.04             |
| qwen/qwen3-8b-fp8                                 | \$0.035           | \$0.138            |
| qwen/qwen3-4b-fp8                                 | \$0.03            | \$0.03             |
| meta-llama/llama-3.2-3b-instruct                  | \$0.03            | \$0.05             |
| meta-llama/llama-3.2-1b-instruct                  | \$0.02            | \$0.05             |
| meta-llama/llama-3.1-8b-instruct                  | \$0.02            | \$0.05             |

## Embeddings

**Target URL:** `https://api.novita.ai/v3/openai/embeddings`

|                  |                    |
| ---------------- | ------------------ |
| **Content Type** | `application/json` |
| **Streaming**    | No                 |

| Model       | Input | Output |
| ----------- | ----- | ------ |
| baai/bge-m3 | Free  | Free   |

## 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>