# Cloudflare

Cloudflare serves 1 model on LLM API: DeepSeek V4.1 Flash 1017 from DeepSeek.

Model ID prefix: `cloudflare/` · 1 model · [Cloudflare privacy policy](https://www.cloudflare.com/policies/privacy/)
Updated: 2026-11-13
Canonical: https://llmapi.ai/providers/cloudflare/

## Models and prices

Prices when Cloudflare serves the request.

### Text (1)

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/) | `cloudflare/deepseek-v4.1-flash-1017` | $0.3 | $1.2 | $0.006 | 1.05M |

**Volume pricing.** At higher monthly volume, models on Cloudflare 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 Cloudflare

Put `cloudflare/` before a model ID and the request goes to Cloudflare. If Cloudflare’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="cloudflare/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)