Aider 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. Set the base URL and the key in your shell.
2. Start Aider in your project with the model name prefixed openai/: openai/deepseek-v4.1-flash-uncensored.
3. Ask anything. A reply that starts “Connected to” means the setup works.
4. Set OPENAI_API_KEY to your own key from the console and start Aider again.

export OPENAI_API_BASE=https://nokeep.ai/v1
export OPENAI_API_KEY=sk-nokeep-test

cd /path/to/your/project
aider --model openai/deepseek-v4.1-flash-uncensored

Keep the openai/ prefix: it is what sends the call to OPENAI_API_BASE. Without it Aider doesn’t recognise the model name and the call fails.

To keep your OpenAI variables for OpenAI, pass the two values as flags instead: --openai-api-base and --openai-api-key.

Limits, prices and edits

Aider warns that it doesn’t know this model’s context window or price. It works anyway, but two files in your home directory or the repository’s root fix the warning, the cost report and the edit format.

{
  "openai/deepseek-v4.1-flash-uncensored": {
    "max_tokens": 131072,
    "max_input_tokens": 1000000,
    "max_output_tokens": 131072,
    "input_cost_per_token": 4.5000000000000003e-7,
    "output_cost_per_token": 0.00000175,
    "litellm_provider": "openai",
    "mode": "chat"
  }
}

- name: openai/deepseek-v4.1-flash-uncensored
  edit_format: diff
  use_repo_map: true
  accepts_settings:
    - reasoning_effort
  extra_params:
    max_tokens: 32768

• edit_format: diff sends only the changed lines back, which is quicker and cheaper than whole files.
• use_repo_map gives the model a map of the repository, which a million-token context has plenty of room for.
• max_tokens is the cap on each reply. Without it, a reply stops at our default of 8,192 tokens.
• For GLM, copy both entries with openai/glm-5.3-flash-uncensored and its own numbers from Models.

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 Aider, start with --reasoning-effort high, or type /reasoning-effort high in a session. The settings file above lists reasoning_effort as a setting the model accepts, so Aider sends it without a warning.

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.