TypingMind×
Cloudflare AI GatewayHow to use DeepSeek V4 Pro with your Cloudflare AI Gateway API key on TypingMind
Learn how to access and use DeepSeek V4 Pro with your Cloudflare AI Gateway API key through TypingMind. Get started with this AI model in minutes.
Open MoE flagship with million-token context for coding and long agent runs
Cloudflare AI Gateway sits between your apps and AI providers such as OpenAI, Anthropic, Google, xAI, and DeepSeek, adding caching, rate limiting, logging, and analytics across all of them. Its unified OpenAI-compatible endpoint lets one Cloudflare API token reach models from every provider.
Store your provider keys in the gateway or use Cloudflare's Unified Billing to pay per token, then connect TypingMind with an authentication token created inside your gateway.
See the official Cloudflare AI Gateway documentation for more details.
DeepSeek V4 Pro Overview
| Model Name | DeepSeek V4 Pro |
| Provider | Cloudflare AI Gateway |
| Model ID | deepseek/deepseek-v4-pro |
| Model Logo | Get the logo URL |
| Release Date | Apr 24, 2026 |
| Last Updated | Apr 24, 2026 |
| Knowledge Cutoff | 2025-05 |
| Context Window | 131,072 tokens |
| Max Output | 384,000 tokens |
| Pricing /1M tokens | $1.74 input $3.48 output $0.145 cache read |
| Input Modalities | text |
| Output Modalities | text |
| Capabilities | ReasoningTool CallingStructured OutputTemperature ControlOpen Weights |
Complete Setup Guide
Get Your Cloudflare AI Gateway API Key
First, you'll need to obtain an API key from Cloudflare AI Gateway. This key allows you to access their AI models directly and pay only for what you use.
-
Go to Cloudflare AI Gateway. Sign up for a Cloudflare account first if you don't have one.
-
Click Create custom gateway.
-
Enter a Gateway ID, for example
typingmind, and create the gateway. This is your<GATEWAY_ID>.
-
Open the new gateway and create an authentication token with the AI Gateway Run permission. Copy the token right away. This is your
<CLOUDFLARE_API_TOKEN>.
-
Go to dash.cloudflare.com and copy your Account ID from the page URL. For example, in
https://dash.cloudflare.com/38cms9x0cms9jg7239fdsc8c8cccd/home, the Account ID is38cms9x0cms9jg7239fdsc8c8cccd. This is your<ACCOUNT_ID>.
Sometimes, this provider will require you to add a payment method to your account before you can use your API key to chat with AI. So, to avoid any hiccups, make sure you've got a payment method set up and ready to go!
Important: Keep your API key secure and never share it publicly. Store it safely as you'll need it to connect with TypingMind.
Configure TypingMind with Cloudflare AI Gateway API Key
Open the Models page
Open TypingMind, click "Models" in the left sidebar, then click "Add custom model" in the top right corner.
Enter the model details
Keep "Create Manually" selected and fill in the model details:
Name:DeepSeek V4 Pro via Cloudflare AI Gateway(or your preferred name)Model ID:deepseek/deepseek-v4-profor example (check Cloudflare AI Gateway model list)Context Length: Enter the model's context window (e.g., 131072 for deepseek/deepseek-v4-pro)
Set up authentication
In the "Authentication" tab, set the connection details:
API Type:OpenAI Chat Completions APIEndpoint URL:https://gateway.ai.cloudflare.com/v1/<ACCOUNT_ID>/<GATEWAY_ID>/compat/chat/completionsExample:
https://gateway.ai.cloudflare.com/v1/38cms9x0cms9jg7239fdsc8c8cccd/typingmind/compat/chat/completionsAuthentication Type:API Key via HTTP HeaderHeader Key:AuthorizationHeader Value:Bearer <CLOUDFLARE_API_TOKEN>
Add pricing (optional)
Open the "Pricing" tab and enter the model's input, output, and cache prices per 1M tokens so TypingMind can estimate your usage costs.
Check the capabilities
In the "Capabilities" tab, keep "Auto check capabilities on save" on so TypingMind detects supported features like plugins, image input, and thinking, or enable them manually.
Route requests via TypingMind Cloud
Cloudflare AI Gateway doesn't accept requests directly from the browser. Open the "Request Options" tab and turn on "Route requests via TypingMind Cloud".
Test and save
Click "Test & Save" to verify the connection and add the model.
Start chatting with DeepSeek V4 Pro
Now you can start chatting with DeepSeek V4 Pro through TypingMind:
- Select DeepSeek V4 Pro from the model dropdown menu
- Start typing your message in the chat input
- Enjoy faster responses and better features than the official interface
- Switch between different AI models as needed
💡 Pro tips for better results:
- Use specific, detailed prompts for better responses (How to use Prompt Library)
- Create AI agents with custom instructions for repeated tasks (How to create AI Agents)
- Use plugins to extend DeepSeek V4 Pro with web search, code execution, and more (How to use plugins)
Why TypingMind + Cloudflare AI Gateway?
Chat with DeepSeek V4 Pro and 200+ other models in one workspace, using your own Cloudflare AI Gateway API key.
Best-in-class UI
TypingMind's interface is far superior to standard chat UIs.
Model flexibility
Switch between DeepSeek V4 Pro and 200+ models instantly.
Cost control
Pay only for what you use through Cloudflare AI Gateway.
One-time purchase
Buy TypingMind once, use forever with any Cloudflare AI Gateway model.
Data privacy
Your conversations are stored locally by default, not on external servers.
Plugins, MCP, Skills & AI agents
Extend DeepSeek V4 Pro with web search, image generation, and custom AI agents.
Frequently Asked Questions
Do I need a subscription to use DeepSeek V4 Pro?
No. With your own Cloudflare AI Gateway API key, you pay only for what you use, with no monthly subscription. TypingMind is also a one-time purchase, not a subscription.
How much does it cost to use DeepSeek V4 Pro?
DeepSeek V4 Pro costs $1.74/1M input tokens and $3.48/1M output tokens via Cloudflare AI Gateway. A typical conversation costs around $0.01-0.10, depending on length.
Can I use other models besides DeepSeek V4 Pro?
Yes. Any model your Cloudflare AI Gateway API key can access works in TypingMind, and you can switch between it and models from other providers in the same chat.
Is my data private when using DeepSeek V4 Pro with TypingMind?
TypingMind stores your conversations locally (in your browser on the web version, on your device in the desktop app). Your messages are sent to Cloudflare AI Gateway with your API key, so check Cloudflare AI Gateway's data policy for how it handles API requests.
