Setup guide - From DeepSeek and Continue docs
Use DeepSeek in Continue
Continue 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.
Last verified 3 steps3 official sources
Steps
- Step 1.
Get an API key from DeepSeek (https://platform.deepseek.com/api_keys).
- Step 2.
Add a model entry to your Continue config (verbatim template from Continue docs).
YAMLname: My Config version: 0.0.1 schema: v1 models: - name: <MODEL_NAME> provider: deepseek model: <MODEL_ID> apiKey: <YOUR_DEEPSEEK_API_KEY> - Step 3.
Fill in <MODEL_ID> with a current DeepSeek model id, for example:
YAMLmodels: - name: DeepSeek Flash provider: deepseek model: deepseek-flash apiKey: <YOUR_DEEPSEEK_API_KEY>
Caveats
- This combines Continue's documented deepseek provider template with DeepSeek's documented model ids. Continue's page uses <MODEL_ID> as a placeholder and does not list ids.
- Continue's page does not show the provider's default base URL. The value listed here is DeepSeek's documented OpenAI-format base URL.
- DeepSeek thinking mode is on by default. With tools, reasoning_content must be passed back on later requests or the API returns a 400 error. Continue's docs do not say how its deepseek provider handles this.
More setup guides
Same tool, other providers
Related reading
- DeepSeek V4.1-Flash-1017: Benchmarks vs Opus 5, Pricing, Switch?DeepSeek V4.1-Flash-1017 jumps 11 points on Terminal-Bench 4.0 at the same deepseek-flash price. Benchmarks vs Opus 5, K3, GLM-5.3 and when to switch.
- DeepSeek 4.1 Flash as a Daily Coding Model: Cache, Peak Hours and LimitsDeepSeek 4.1 Flash as a daily coding model: what a session costs, how peak hours double the bill, why caching matters, and where the subsidy argument holds.
- Where to Run DeepSeek V4.1 Flash Free and CheapDeepSeek V4.1 Flash replaced V4 Flash. Official API: $0.15 input, $0.60 output off-peak. OpenRouter hosts start near $0.05. MIT weights are on Hugging Face.
- DeepSeek V4 Flash Vision Exp: Experimental Vision, Limits, and How to Run It in OpenCodeDeepSeek V4 Flash Vision Exp guide: supported image formats, three input methods, the 384-token per-image cap, and how to run it in OpenCode today.
- We Read DeepSeek Harness: What 453K Lines of Agent Runtime Actually SayDeepSeek Harness (dsh) code read: a 453K-line plugin runtime on a vendored Cordis fork, three patterns worth stealing, and the gaps the launch does not mention.
- DeepSeek V4 Flash Is 90% Off Through Novita on Vercel AI Gateway: The Cost MathDeepSeek V4 Flash via Novita on Vercel AI Gateway was 90% off for Pro customers through August 11. The before/after cost math and the provider-pinning setup.
FAQ
How do I use DeepSeek in Continue?
Continue 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.
Which DeepSeek model ids work in Continue?
The official docs read for this guide list deepseek-flash and deepseek-v4-pro. Requests go to https://api.deepseek.com.
Is this an official DeepSeek and Continue setup?
The steps draw on both DeepSeek's and Continue's docs. It was last checked against 3 official pages on October 17, 2026.
Sources
Last verified against 3 official pages.
- docs.continue.devhttps://docs.continue.dev/customize/model-providers/more/deepseek
- api-docs.deepseek.comhttps://api-docs.deepseek.com/
- api-docs.deepseek.comhttps://api-docs.deepseek.com/guides/thinking_mode
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.