How the integration works
Cline exposes Base URL, API Key, and Model ID fields through its OpenAI Compatible provider. Point those fields at DeepSeek-V4.io and keep the stable public model ID deepseek-v4-flash; the gateway currently maps that alias to DeepSeek V4.1 Flash upstream.
Create and manage it on /developer.
The client talks to its native compatible endpoint.
Provider credentials and routing stay on the server.
Before you start
- Cline installed in VS Code or a compatible editor
- A paid DeepSeek-V4.io account with an API key from /developer
- Access to the Cline API Provider settings
Safety before the first run
A coding agent operates with the workspace and execution permissions you grant it. Start with the smallest useful boundary.
- Start in a disposable repository or worktree and ask Cline to perform a read-only task before enabling edits or commands.
- Keep the DeepSeek-V4.io API key in Cline's provider settings. Never paste it into a prompt, source file, screenshot, or committed configuration.
- Leave image support disabled for this route. The underlying V4.1 model is multimodal, but this gateway has only verified text requests.
Configure Cline
API Provider: OpenAI Compatible
Base URL: https://deepseek-v4.io/api/v1
API Key: your-deepseek-v4-io-key
Model ID: deepseek-v4-flashVerify the setup
The page remains Experimental until these checks pass against the public DeepSeek-V4.io gateway.
- 1Start a new Cline task after saving the provider settings.
- 2Ask Cline to read one file without applying a change.
- 3Confirm streaming and a read-only tool call both complete.
Troubleshooting
Cline reports an invalid URL
Use the full base URL https://deepseek-v4.io/api/v1 without adding /chat/completions.
Authentication fails
Use the API key created on DeepSeek-V4.io. Keys from other providers are not accepted.
Cline reports model not found
Use deepseek-v4-flash with this gateway. The official DeepSeek model name deepseek-flash belongs to the official provider endpoint, not to DeepSeek-V4.io.
Existing task keeps the old model
Save the settings and create a new Cline task.
Frequently asked questions
Can Cline use DeepSeek V4.1 Flash?
Yes. Select Cline's OpenAI Compatible provider, use https://deepseek-v4.io/api/v1 as the Base URL, provide a paid DeepSeek-V4.io API key, and set the Model ID to deepseek-v4-flash. The gateway maps that stable alias to V4.1 Flash upstream.
Which model ID should I enter for DeepSeek V4.1 in Cline?
Use deepseek-v4-flash when the Base URL is DeepSeek-V4.io. DeepSeek's official API documents deepseek-flash, but model IDs are provider-specific and the two endpoints should not be mixed.
Does the Cline setup support images?
Not through this gateway today. Keep Cline's image-support setting disabled for this route even though the underlying DeepSeek V4.1 Flash release has native multimodal capability.
Is DeepSeek-V4.io the official DeepSeek API?
No. DeepSeek-V4.io is an independent gateway with separate accounts, API keys, balances, billing, and support.
Sources and support boundary
Configuration fields are checked against the tool publisher's documentation. DeepSeek-V4.io owns this gateway guide and support for its endpoint; it does not represent the tool publisher.
Ready to connect Cline?
Create a DeepSeek-V4.io API key, copy the configuration above, and verify one read-only tool call before using it on a real project.