# DeepSeek

DeepSeek serves 3 text models on LLM API, all from DeepSeek.

Model ID prefix: `deepseek/` · 3 models · [DeepSeek privacy policy](https://cdn.deepseek.com/policies/en-US/deepseek-privacy-policy.html)
Updated: 2026-11-13
Canonical: https://llmapi.ai/providers/deepseek/

## Models and prices

Prices when DeepSeek serves the request.

### Text (3)

Prices per 1M tokens.

| Model | Model ID | Input | Output | Cache read | Context |
| --- | --- | --- | --- | --- | --- |
| [DeepSeek V4.1 Flash 1017](https://llmapi.ai/models/deepseek-v4-1-flash-1017/) | `deepseek/deepseek-v4.1-flash-1017` | $0.15 | $0.6 | $0.003 | 1M |
| [DeepSeek V4 Pro](https://llmapi.ai/models/deepseek-deepseek-v4-pro/) | `deepseek/deepseek-v4-pro` | $0.66 | $1.98 | $0.022 | 1.05M |
| [DeepSeek V4.1 Flash](https://llmapi.ai/models/deepseek-deepseek-v4-1-flash/) | `deepseek/deepseek/deepseek-v4.1-flash` | $0.15 | $0.6 | $0.003 | 1M |

**Volume pricing.** At higher monthly volume, models on DeepSeek may cost less. Book a call and sales will quote a price for your usage. [Book a call with sales](https://meetings.hubspot.com/julia-andriienko/llmapi) or [Create an account first](https://app.llmapi.ai/signup).

## Send requests to DeepSeek

Put `deepseek/` before a model ID and the request goes to DeepSeek. If DeepSeek’s uptime over the last 5 minutes is below 90%, it goes to another provider of the model, unless it sends `X-No-Fallback: true`. [Routing docs](https://docs.llmapi.ai/features/routing)

Example: DeepSeek V4.1 Flash 1017, Chat Completions (`POST /v1/chat/completions`). Set LLMAPI_KEY to your LLM API key.

```python
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.llmapi.ai/v1",
    api_key=os.environ["LLMAPI_KEY"],
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v4.1-flash-1017",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)
```

Prices synced 2026-11-13.

Next step: [Get API key](https://app.llmapi.ai/signup)