Zed 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 Agent Settings: run agent: open settings from the command palette.
2. In LLM Providers, click Add Provider.
3. Name it nokeep, paste https://nokeep.ai/v1 as the API URL, deepseek-v4.1-flash-uncensored as the model id and 1000000 as the context window.
4. Paste sk-nokeep-test as the key. Zed keeps it in your system keychain.
5. Open the agent panel, pick DeepSeek V4.1 Flash Uncensored and send a message. A reply that starts “Connected to” means it works.
6. Replace the key with your own from the console.

Or set it up in settings.json, which also turns on pictures, parallel tool calls and the cache key. Never put the key there: Zed reads it from the keychain, or from NOKEEP_API_KEY, the provider name in capitals plus _API_KEY.

{
  "language_models": {
    "openai_compatible": {
      "nokeep": {
        "api_url": "https://nokeep.ai/v1",
        "available_models": [
          {
            "name": "deepseek-v4.1-flash-uncensored",
            "display_name": "DeepSeek V4.1 Flash Uncensored",
            "max_tokens": 1000000,
            "max_output_tokens": 32768,
            "capabilities": {
              "tools": true,
              "images": true,
              "parallel_tool_calls": true,
              "prompt_cache_key": true
            }
          },
          {
            "name": "glm-5.3-flash-uncensored",
            "display_name": "GLM 5.3 Flash Uncensored",
            "max_tokens": 128000,
            "max_output_tokens": 32768,
            "capabilities": {
              "tools": true,
              "images": false,
              "parallel_tool_calls": false,
              "prompt_cache_key": false
            }
          }
        ]
      }
    }
  }
}

Settings worth knowing

• max_tokens is the context window in Zed’s settings, not the reply cap. max_output_tokens is the cap on each reply.
• prompt_cache_key sends each thread’s calls to a server that has its start cached. DeepSeek takes it; GLM drops it.
• images lets you add screenshots to a DeepSeek thread. GLM reads text only.

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 Zed, add "reasoning_effort": "high" to the DeepSeek entry. Zed then shows a thinking toggle in the agent panel and sends that effort when it is on. Use low, high or max; minimal, medium and xhigh also work and run at the nearest of those.

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.