Continue setup

The values

Start with the free test key: it answers every request with one fixed line and no tool calls, which proves the URL and the key are right without spending anything. Then paste your own key from the console. Credits from $5, no subscription.

Connect

1. Open config.yaml: in the chat input’s configs menu, click the cog beside Local Config. The file is ~/.continue/config.yaml on macOS and Linux, %USERPROFILE%\.continue\config.yaml on Windows.
2. Add the two models below under models, or replace the file with it.
3. Save, pick DeepSeek V4.1 Flash Uncensored in Continue’s model menu, and send a message. A reply that starts “Connected to” means it works.
4. Replace sk-nokeep-test with your own key from the console and save again.

name: nokeep
version: 0.0.1
schema: v1
models:
  - name: DeepSeek V4.1 Flash Uncensored
    provider: openai
    model: deepseek-v4.1-flash-uncensored
    apiBase: https://nokeep.ai/v1
    apiKey: sk-nokeep-test
    roles:
      - chat
      - edit
      - apply
    capabilities:
      - tool_use
      - image_input
    defaultCompletionOptions:
      contextLength: 1000000
      maxTokens: 32768
  - name: GLM 5.3 Flash Uncensored
    provider: openai
    model: glm-5.3-flash-uncensored
    apiBase: https://nokeep.ai/v1
    apiKey: sk-nokeep-test
    roles:
      - chat
      - edit
    capabilities:
      - tool_use
    defaultCompletionOptions:
      contextLength: 128000
      maxTokens: 32768

Keep tool_use under capabilities. Continue doesn’t recognise these model ids, and Agent mode needs a model it knows can call tools.

Settings worth knowing

• contextLength tells Continue how much it can send; maxTokens is the cap on each reply.
• image_input lets you paste screenshots to DeepSeek. GLM reads text only, so its entry leaves it out.
• Leave autocomplete to another model. The API serves chat completions only, with no fill-in-the-middle endpoint.

Which model

Use DeepSeek for agent work. A whole repository fits in its context, it calls tools in every form, and the history an agent resends on each call bills at the cached $0.011 per million. Use GLM for short one-off tasks that don’t resend a long history, where its lower fresh-input and output prices win.

Both models have their refusals removed from the weights, so work near a sensitive subject, such as security testing on your own systems or moderation tooling, gets code instead of a refusal. Compare the models.

Thinking

DeepSeek answers at once unless a request names a reasoning_effort, which suits the quick edit-and-run loop of an agent. For planning or a hard bug, ask it to think: it takes none, low, high, max. Other apps’ minimal, medium and xhigh run at the nearest of these; any other value is refused with 400 invalid_reasoning_effort. Thinking is billed as output.

In Continue, send the effort as an extra body field. Add this to the DeepSeek entry, at the same depth as roles, for a model that thinks on every request; keep a second entry without it for quick work.

    requestOptions:
      extraBodyProperties:
        reasoning_effort: high

What a session costs

An agent sends the whole conversation on every call: the instructions, the files it read, every step so far. Say a call sends 60,000 tokens, 55,000 of them the same start as the last call, and writes 1,000. On DeepSeek that call costs about $0.0046, so 200 calls are about $0.92. With no cache the same call would be $0.0288.

• Caching is automatic: nothing to turn on. A start of about 1,000 tokens or more, repeated within a few minutes, bills at the cached price.
• Each call holds what it could cost, its prompt and its max output, and settles to what it used. At 32,768 max output tokens the output part of the hold is about $0.0573.
• The console shows each call’s real tokens, cached tokens and credits. An agent’s own cost counter may not know the cached price, and then reads high.

How billing works.

If it doesn’t work

Every error is listed with its fix in Errors.