DeepSeek V4
DeepSeek V4
← All integrations
Terminal coding agentOpenAI Chat CompletionsExperimentalSources checked 2026-09-14

Use DeepSeek V4 with Aider

Connect Aider to DeepSeek V4.1 Flash through the DeepSeek-V4.io OpenAI-compatible endpoint.

Create API KeyRead API Docs

DeepSeek-V4.io is an independent API gateway, not the official DeepSeek website. A paid DeepSeek-V4.io key is required.

The public model ID remains deepseek-v4-flash. Text requests now route to DeepSeek V4.1 Flash; image input remains outside this gateway's verified support boundary.

How the integration works

Aider supports OpenAI-compatible endpoints through OPENAI_API_BASE and an OpenAI-prefixed model name. Keep the site API key in an environment variable and use the stable public model ID; the gateway handles the current upstream mapping.

One site key

Create and manage it on /developer.

OpenAI Chat Completions

The client talks to its native compatible endpoint.

Upstream hidden

Provider credentials and routing stay on the server.

Before you start

  • Aider installed in an isolated Python environment
  • A paid DeepSeek-V4.io account with an API key from /developer
  • A test repository where Aider can read files without touching production code

Configure Aider

1.Set the endpoint and site API key
export DEEPSEEK_V4_API_KEY="your-deepseek-v4-io-key"
export OPENAI_API_BASE="https://deepseek-v4.io/api/v1"
export OPENAI_API_KEY="$DEEPSEEK_V4_API_KEY"
2.Start Aider with the stable public model ID
cd /path/to/your/test-project
aider --model openai/deepseek-v4-flash

Verify the setup

The page remains Experimental until these checks pass against the public DeepSeek-V4.io gateway.

  1. 1Ask Aider to explain one tracked file without editing it.
  2. 2Confirm the model response streams to completion.
  3. 3Check that the request appears in the DeepSeek-V4.io Developer usage view before allowing edits.
Create and test an API key

Troubleshooting

Aider calls the default OpenAI endpoint

Export OPENAI_API_BASE in the same shell before starting Aider, then start a new process.

Model name is rejected

Use openai/deepseek-v4-flash in Aider. The openai/ prefix selects Aider's OpenAI-compatible adapter; it is not part of the gateway model ID.

Authentication fails

Set OPENAI_API_KEY to a paid DeepSeek-V4.io key. Keys issued by another provider cannot authenticate with this gateway.

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 Aider?

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.

Open Developer Dashboard