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

Use DeepSeek V4 with Continue

Configure Continue with DeepSeek V4.1 Flash through the DeepSeek-V4.io OpenAI-compatible provider.

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

Continue supports custom OpenAI-compatible providers in config.yaml. Point apiBase at this site, reference the site key through Continue secrets, and keep the public model ID stable while the gateway controls upstream routing.

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

  • Continue installed in VS Code or JetBrains
  • A paid DeepSeek-V4.io account with an API key from /developer
  • Access to Continue config.yaml and its local secrets store

Configure Continue

1.Save the API key as a Continue secret

Use Continue's secrets UI or local secrets file. Do not commit the literal key with config.yaml.

Secret name: DEEPSEEK_V4_API_KEY
Secret value: your-deepseek-v4-io-key
2.Add the model to Continue config.yaml
name: DeepSeek-V4.io
version: 0.0.1
schema: v1
models:
  - name: DeepSeek V4.1 Flash
    provider: openai
    model: deepseek-v4-flash
    apiBase: https://deepseek-v4.io/api/v1
    apiKey: ${{ secrets.DEEPSEEK_V4_API_KEY }}
    capabilities:
      - tool_use

Verify the setup

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

  1. 1Select DeepSeek V4.1 Flash in the Continue model picker.
  2. 2Ask Continue to summarize the active file without applying changes.
  3. 3Confirm one streamed response and one Developer usage row complete before enabling broader agent actions.
Create and test an API key

Troubleshooting

The model does not appear

Validate config.yaml, reload the Continue extension, and confirm the model is nested under the top-level models list.

The secret is unresolved

Create DEEPSEEK_V4_API_KEY in Continue's secrets store and keep the ${{ secrets.DEEPSEEK_V4_API_KEY }} reference unchanged.

Tool use is unavailable

Keep tool_use under capabilities and begin a new Continue session after saving the configuration.

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 Continue?

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