DeepSeek
Use DeepSeek in your coding tools
Step-by-step setup for DeepSeek in 11 coding tools: Aider, Claude Code, Cline, Codex CLI, Continue, GitHub Copilot, Goose, Kilo Code, OpenCode, Roo Code and Zed. Every step comes from official docs, read on .
DeepSeek setup guides
- From DeepSeek and Aider docsUse DeepSeek in AiderAider's DeepSeek page still uses the discontinued deepseek/deepseek-chat id. To use current models, use Aider's documented OpenAI-compatible path: set OPENAI_API_BASE to DeepSeek's base URL and run aider --model openai/deepseek-flash.api.deepseek.com4 steps
- Documented by DeepSeekUse DeepSeek in Claude CodeDeepSeek publishes a Claude Code integration guide that points Claude Code at DeepSeek's Anthropic-compatible endpoint (https://api.deepseek.com/anthropic) through environment variables. The default model is deepseek-flash, which serves DeepSeek-V4.1-Flash-1017 (1M context, 384K max output).api.deepseek.com5 steps
- Documented by ClineUse DeepSeek in ClineCline has a built-in DeepSeek API provider. You select DeepSeek in the API Provider dropdown, paste your key and choose a model. Cline's own issue tracker shows deepseek-flash available in that model list in Cline 4.1.21.api.deepseek.com5 steps
- Documented by DeepSeekUse DeepSeek in Codex CLIDeepSeek publishes a Codex integration that uses DeepSeek's native Responses API support. You add a [model_providers.deepseek] section to ~/.codex/config.toml with wire_api = "responses", plus a ~/.codex/models.json model catalog, either with a one-click setup script or by hand. The same config also covers the ChatGPT desktop app and the Codex IDE extension.api.deepseek.com5 steps
- From DeepSeek and Continue docsUse DeepSeek in ContinueContinue has a built-in deepseek provider, set up with a models entry in config.yaml (provider: deepseek). Continue's page leaves the model id as a placeholder, so fill it with a current DeepSeek id such as deepseek-flash.api.deepseek.com3 steps
- From DeepSeek and GitHub Copilot docsUse DeepSeek in GitHub CopilotCopilot Chat in VS Code supports bring-your-own-key models through the Custom Endpoint provider (Chat Completions, Responses or Messages API), configured in chatLanguageModels.json. You point it at DeepSeek's documented chat completions endpoint with model deepseek-flash.api.deepseek.com4 steps
- From DeepSeek and Goose docsUse DeepSeek in GooseGoose has no built-in DeepSeek provider, but it documents custom providers that use OpenAI-compatible APIs (Desktop, goose configure, or a JSON file in custom_providers). You point one at DeepSeek's documented chat completions endpoint with model deepseek-flash.api.deepseek.com4 steps
- From DeepSeek and Kilo Code docsUse DeepSeek in Kilo CodeKilo Code has a built-in DeepSeek provider for both the VS Code extension (Settings > Providers) and the CLI (DEEPSEEK_API_KEY plus kilo.json). Kilo's example default model is the discontinued deepseek/deepseek-chat, so use a current DeepSeek id instead.api.deepseek.com5 steps
- From DeepSeek and OpenCode docsUse DeepSeek in OpenCodeOpenCode has a built-in DeepSeek provider, and both DeepSeek's integration guide and OpenCode's provider docs describe the same setup: /connect, choose DeepSeek, paste your API key, then pick a DeepSeek model with /models.api.deepseek.com5 steps
- From DeepSeek and Roo Code docsUse DeepSeek in Roo CodeRoo Code's built-in DeepSeek provider still ships only the discontinued deepseek-chat / deepseek-reasoner ids. To use current models, use Roo Code's documented OpenAI Compatible provider with DeepSeek's documented OpenAI-format base URL and the model id deepseek-flash or deepseek-v4-pro.api.deepseek.com5 steps
- Documented by ZedUse DeepSeek in ZedZed has DeepSeek as a first-class API provider for the Zed Agent and other Zed AI features. Enter your key in Agent Settings or set DEEPSEEK_API_KEY. Zed's docs give a custom-models example that already uses the current deepseek-flash and deepseek-v4-pro ids.api.deepseek.com3 steps
No verified DeepSeek guide yet for Cursor. We only publish a pairing once official docs cover it.
Newsletter
New models, set up the day they ship
One email per week. New model releases, the coding tools that support them and how to wire them up.