OpenCode 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. In OpenCode, run /connect, scroll to Other and choose it.
2. Enter nokeep as the provider id.
3. Paste sk-nokeep-test as the API key. OpenCode stores it for that id.
4. Add the provider below to opencode.json in your project, or to ~/.config/opencode/opencode.json for every project.
5. Run /models and pick DeepSeek V4.1 Flash Uncensored.
6. Send any message. A reply that starts “Connected to” means the setup works.
7. Run /connect again with the same id and paste your own key from the console.

{
  "$schema": "https://opencode.ai/config.json",
  "model": "nokeep/deepseek-v4.1-flash-uncensored",
  "provider": {
    "nokeep": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "nokeep",
      "options": {
        "baseURL": "https://nokeep.ai/v1"
      },
      "models": {
        "deepseek-v4.1-flash-uncensored": {
          "name": "DeepSeek V4.1 Flash Uncensored",
          "limit": {
            "context": 1000000,
            "output": 32768
          }
        },
        "glm-5.3-flash-uncensored": {
          "name": "GLM 5.3 Flash Uncensored",
          "limit": {
            "context": 128000,
            "output": 32768
          }
        }
      }
    }
  }
}

The provider id in /connect and the key under provider must match: nokeep in both.

To read the key from the environment instead of /connect, add "apiKey": "{env:NOKEEP_API_KEY}" under options.

Settings worth knowing

• limit.context tells OpenCode how much room is left, so it can compact the conversation before it overflows. A custom model has no limit unless you set one.
• limit.output is sent as the token cap on each reply. 32,768 fits long edits; DeepSeek allows up to 131,072.
• The top-level model makes DeepSeek the default, in the provider/model form.
• Tool calls work as they are: OpenCode sends its tools in the OpenAI format and DeepSeek answers with calls.

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 OpenCode, add a variant that sends an effort, then switch to it with the variant_cycle keybind when a task needs thought. Merge this into the provider above.

{
  "provider": {
    "nokeep": {
      "models": {
        "deepseek-v4.1-flash-uncensored": {
          "variants": {
            "think": {
              "reasoningEffort": "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.