Aider pricing: free CLI, API billing, and the cheapest route

Aider, the open-source AI coding assistant for the terminal, costs $0. It is Apache-2.0 software, and aider.chat offers no plans, tiers, seats, or hosted service—the “cost of Aider” is effectively the API bill for the model you call through it. To estimate your budget, use tokens per session multiplied by your provider's rate. The setting most likely to inflate that figure is Aider's default behavior when it encounters an unknown model ID—two lines fix it, as explained below.

First, a distinction, because search results mix them together: another company that sells accounting close software for firms is also called Aider and publishes a monthly minimum price. Those prices belong to that product. This page covers only the CLI at aider.chat, distributed as the aider-chat package from the Aider-AI/aider repository.

What Aider charges—and what you are actually billed

Aider's FAQ states that the tool is released as open-source software under Apache 2.0. The homepage, FAQ, installation page, and LLM pages contain no pricing, plans, or subscription language (verified October 1, 2026). All billing happens on the other side of the endpoint.

Check the release cadence before standardizing on it for a team. The repository is not archived and has 49,309 stars, but the last commit on main was May 22, 2026 (GitHub API, October 1, 2026). The two official “latest version” listings also differ: PyPI lists 0.86.2, published February 12, 2026; GitHub Releases stops at v0.86.0, dated August 9, 2025. pip install installs the PyPI version. For Python versions, the >=3.10,<3.13 in the 0.86.2 package metadata is the condition pip actually enforces, rather than the broader statement on the installation page.

The setting that most affects your API costs

This is the part price tables don't show. Aider chooses the edit format, repository map (repo map), and caching behavior by matching the model ID against a built-in table. It matches the full string after --model, including its prefix. If nothing matches, the defaults are edit_format: whole, use_repo_map: false, cache_control: false, and weak_model_name: null, according to the advanced model settings page.

In the source for release 0.86.2, matching happens in two steps: first an exact match against 313 full names, such as gemini/gemini-3-pro-preview and openai/gpt-5.2; only if nothing matches does it try substring rules, including sonnet-4-5, haiku-4-5, and gpt-4.1. For an OpenAI-compatible gateway, the model ID must be passed as openai/<id>. All 40 entries in the table with a openai/ prefix are OpenAI's own model names. So openai/claude-sonnet-4-6 matches neither step, and Aider works by rewriting whole files, with the repository map disabled: the model re-outputs every edited file in full on every turn, and output tokens are the expensive side of the bill.

Two lines fix this. Aider reads this file from the home directory, Git root, or current directory; the key is the full name passed to --model:

# name muss exakt dem String entsprechen, den Sie an --model übergeben (inkl. Präfix)
- name: openai/claude-sonnet-4-6
  edit_format: diff
  use_repo_map: true

For a one-time run, add --edit-format diff at launch. Conversely, openai/claude-haiku-4-5 matches the substring haiku-4-5 and automatically gets diff format and the repository map. This is a coincidence in the name and could change between Aider versions, so verify it rather than relying on it.

One more easily overlooked effect: Aider calls the API in three roles—the main model, an Editor model for --architect mode, and a Weak model for commit messages and conversation-history summaries (see the options reference). If the ID is unknown, the source sets both Weak and Editor to the main model, so all three roles are billed at the highest rate. Specify a cheaper ID with --weak-model to avoid this (the openai/ prefix is required here too).

Finally, an unknown ID also hides cost reporting. Without input_cost_per_token, Aider prints token counts without a cost line, and the warning page says it “assumes the model is free.” Restore it with a metadata file:

{
  "openai/claude-sonnet-4-6": {
    "input_cost_per_token": 0.0000021000,
    "output_cost_per_token": 0.0000105000,
    "litellm_provider": "openai",
    "mode": "chat"
  }
}

Even with metadata, Aider's amount is its own calculation from reported tokens, with cache factors for one provider hard-coded. Use it as a reference, then compare it with the provider's usage records.

A sample cost estimate per session

The following is token arithmetic, not measured task costs or a billing cap. It assumes a session sends 200,000 uncached input tokens and receives 12,000 output tokens in diff format. The whole-file column assumes the same work produces 40,000 output tokens because edited files are returned in full—an illustrative ratio, not a measurement. Rates are current prices per million tokens from the Kunavo catalog.

Under these assumptions, the edit format alone moves the cost of the same task for Claude Sonnet 4.6 from $0.546 to $0.840. Fix the settings before comparing provider rates. Commit-message and summary traffic (assumed 30,000 input and 2,000 output tokens) costs $0.084 on Claude Sonnet 4.6, versus $0.028 when you set Claude Haiku 4.5 as the Weak model.

Multiply by your sessions per day to turn this into a budget. Kunavo catalog amounts are a billing floor, not a ceiling: when the upstream provider reports costs, you are charged whichever is higher—the catalog amount or upstream cost × the applicable margin. Cache fees and external tools are not included in this example.

“Cheapest API” means two different things

Aider publishes the only verifiable task-cost reference available for this tool: the Polyglot benchmark has each model solve the same 225 Exercism problems across six languages under the same conditions and records the cost. We cite it here as cost evidence, not as a model recommendation; an independent comparison of models in Aider has not yet been run.

Read from the leaderboard data file. Two caveats matter more than the ranking: the latest entry is October 3, 2025, so models released after that date have never been measured here. The cost column has no price list or date, so it reflects the cost of that run at the time, not a rate available today. These models are cited as benchmark evidence; DeepSeek is not in the Kunavo catalog. The lower-cost option in the estimate table above is Claude Haiku 4.5.

The practical takeaway: o3-pro cost five times as much as gpt-5 (high) and scored lower, so a higher rate does not guarantee completion. A lower rate does not guarantee the lowest total either: a cheap model that needs three attempts may cost more than an expensive one that finishes in one. Choose the least expensive model that completes the task with an acceptable review burden, then verify it using the amount your account actually recorded for that task. Aider's /tokens is, according to the command reference, the token count in the current chat context, not the total billed so far.

Which route fits when

Two limits of the gateway route. A gateway without its own module connects through the documented compatible route, described on the OpenAI-compatible API page: OPENAI_API_BASE, OPENAI_API_KEY, and the required openai/ prefix on the model ID. The documentation does not describe a setting to override the Anthropic-format base URL, and the string ANTHROPIC_API_BASE does not appear in the 0.86.2 source. Do not expect prompt-cache discounts on this route either. The caching page limits caching to specific provider families, requires --cache-prompts to be explicitly enabled, and says cache statistics and costs are unavailable during streaming. This page has not tested whether caching works on the compatible route.

Using Aider with Kunavo, and how to pay from Germany

Kunavo publishes a setup guide for this client. It is a configuration reference, not a compatibility test: Aider has not been run against the Kunavo endpoint, and everything above comes from Aider's released source and documentation. Keep a working route, run one well-scoped task, and check the amount recorded in your account.

Payment is made by prepaid top-up, without a subscription. The minimum top-up is $10 — a minimum amount for funding the balance, not a price per task or a plan. Checkout is handled by Stripe: cards (Visa, Mastercard, American Express), Apple Pay, Google Pay, and Link; SEPA Direct Debit is currently not offered, while a debit card linked to a current account works normally. The balance does not expire. Details are available under Billing; when you are ready, create an account. The full English version of this guide is Aider pricing.

Frequently asked questions

Aider's repository, package, documentation, and leaderboard data were checked on October 1, 2026. Behavior descriptions are based on the source for the official v0.86.2 release. Kunavo rates come from the live catalog, and all dollar examples are illustrative token calculations, not measured task costs.