Use Tokun with Aider

Aider connects to Tokun through its OpenAI-compatible provider. Your Aider workflow stays the same, and requests use Tokun's pricing and model routing.

• A Tokun API key (starts with sk-) from the API keys page.
• A funded Tokun balance.
• Aider, installed (for example, with pip install aider-chat).
• A model ID, such as openai/gpt-5.5.

Aider reads its OpenAI-compatible provider from environment variables. Set these two, then pass the model with Aider's openai/ prefix:

export OPENAI_API_BASE="https://api.tokun.sh/v1"
export OPENAI_API_KEY="sk-..."      # your Tokun key
aider --model openai/gpt-5.5

Paste this prompt into your AI coding agent. It reads the setup guide at /llms.txt and sets up Aider for you. You only need to provide your API key.

Read https://tokun.sh/llms.txt and integrate Tokun into this project.

You are configuring Aider to use Tokun (OpenAI-compatible).

Tokun values:
- API key placeholder: TOKUN_API_KEY_HERE  (a Tokun key starts with sk-)
- Base URL: https://api.tokun.sh/v1
- Recommended model: openai/gpt-5.5

Apply via EITHER environment variables OR ~/.aider.conf.yml — the key names differ between the two:
- env vars:  OPENAI_API_BASE = https://api.tokun.sh/v1   and   OPENAI_API_KEY = <the user's Tokun sk- key>
- ~/.aider.conf.yml:  openai-api-base: https://api.tokun.sh/v1   and   openai-api-key: <the user's Tokun sk- key>
Then run: aider --model openai/gpt-5.5
Never print, log, or commit the full key.

Note: Aider/litellm reads "openai/<name>" as "OpenAI provider, model <name>", so "openai/gpt-5.5" sends the bare model name to Tokun, which normalizes it. If you are configuring the running shell, the env applies to NEW processes — start a fresh aider. If you cannot safely edit the profile, OUTPUT the export lines for the user.

Prefer a config file? Set openai-api-base and openai-api-key in ~/.aider.conf.yml, or keep the environment variables above. To roll back, unset them.

Pass the model with Aider's openai/ prefix, such as openai/gpt-5.5 or openai/gpt-5.4-mini. litellm strips the prefix, and Tokun normalizes the bare ID. For an Anthropic model through the same API, use openai/claude-opus-4-8. An unknown ID returns an error and is never swapped for a different model.

Official model pools

Official model pools appear in the model catalog and use a pool ID such as flash-pool. Choose an available pool from the live catalog; pool names and members are configured by Tokun administrators.

When the pool enables member selection, use pool-id/member-name, replacing the model's lab prefix with the pool ID. The selected member is the only model that can execute; the pool's pricing mode still applies. When selection is disabled, this form returns 400.

• Fixed token pricing uses the pool's input, output, cache and context-tier rates for every member, including a member you select yourself.
• Actual model pricing uses the serving member's price, frozen before the request. A retry to another member uses that member's frozen price.
• Fixed per-request pricing charges once after an upstream success response begins. Missing usage, a partial response or a client disconnect after that point still counts once. Failures before success and unsuccessful retries do not add charges.

Use a pool that lists the API format this client sends. Model pool settings in the live catalog control which members are shown and whether member selection is available.

• Quickstart
• Models and pricing
• Machine-readable docs (llms-full.txt)