Cline 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 Cline and click the gear icon to open its settings.
2. Set API Provider to OpenAI Compatible.
3. Paste https://nokeep.ai/v1 into Base URL. Stop at /v1: Cline adds the rest.
4. Paste sk-nokeep-test into OpenAI Compatible API Key.
5. Set Model ID to deepseek-v4.1-flash-uncensored. Cline loads the list from our /v1/models, or you can type it.
6. Open Model Configuration. Leave Supports Images ticked, set Context Window Size to 1000000 and Max Output Tokens to 32768.
7. Set Input Price / 1M tokens to 0.45 and Output Price / 1M tokens to 1.75, so Cline’s cost counter is close.
8. Give Cline a task. A reply that starts “Connected to” means the setup works.
9. Swap in your own key from the console.

Set both numbers. Cline doesn’t know this model id, so it assumes a 128,000-token window and trims the conversation long before DeepSeek’s million tokens are used, and it sends no reply limit, so each reply stops at our default of 8,192 tokens.

Labels can move between Cline versions. If one isn’t where this says, look in the same settings panel.

Settings worth knowing

• Cline’s counter doesn’t know the cached price, so it reads high: most of an agent’s input is cached and billed at about a fortieth of the full rate. The console shows the real bill.
• Plan and Act modes can use different models. GLM is fine for planning short tasks; keep DeepSeek for Act, where the history grows.
• Tool calls, file edits and terminal commands all go through as Cline sends them. Nothing of ours is added to its prompt.

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 Cline, Reasoning Effort sits under the model settings and starts at None. Choose Low or High for a hard task. Cline also lists Medium and Xhigh; they run as High and Max.

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.