# DeepSeek V3 Turbo API Pricing

As of October 10, 2026, DeepSeek V3 Turbo costs $0.40 per 1M input tokens and $1.30 per 1M output tokens on Novita AI. It has a 64,000-token context window and returns up to 16,000 tokens per response.

- Page: https://models.litellm.ai/models/deepseek-v3-turbo
- Lab: DeepSeek
- LiteLLM model name: `novita/deepseek/deepseek-v3-turbo`
- Context window: 64,000 tokens
- Max output: 16,000 tokens
- Added to LiteLLM: January 2026
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| Novita AI | `novita/deepseek/deepseek-v3-turbo` | $0.40 | $1.30 | – | – | – | 64K |

## Cost examples

1,000 requests with 2,000 input and 500 output tokens each:

- Novita AI: $1.45

## Features

Supported: Function calling, Parallel tool calls.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="novita/deepseek/deepseek-v3-turbo",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does DeepSeek V3 Turbo cost?

DeepSeek V3 Turbo costs $0.40 per 1M input tokens and $1.30 per 1M output tokens on Novita AI.

### What is the context window of DeepSeek V3 Turbo?

DeepSeek V3 Turbo has a 64,000-token context window and returns up to 16,000 tokens per response.

### Which providers offer DeepSeek V3 Turbo?

DeepSeek V3 Turbo is available from Novita AI through LiteLLM, using the model name novita/deepseek/deepseek-v3-turbo.

### How do I call DeepSeek V3 Turbo with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="novita/deepseek/deepseek-v3-turbo", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### What features does DeepSeek V3 Turbo support?

DeepSeek V3 Turbo supports function calling and parallel tool calls.

### When did LiteLLM add DeepSeek V3 Turbo?

DeepSeek V3 Turbo was added to LiteLLM's model price file in January 2026.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json