Pick the right model for the job — and the price

🎯Goal. Use Aider with whichever LLM fits your task and budget — frontier, cheap, or free local.

1. 1Aider works with virtually any LLM. Swap models with the --model flag: aider --model sonnet for Claude Sonnet, or point it at OpenAI o3 / o4-mini / GPT-4.1, Gemini 2.5 Pro, or DeepSeek R1 / V3.
2. 2Need zero token cost? Aider can run against free local models via Ollama — useful for routine edits when you don't want to spend on an API.
3. 3Consult Aider's public model leaderboard (the polyglot benchmark, which tests LLMs on 225 challenging Exercism exercises across C++, Go, Java, JavaScript, Python and Rust). It reports each model's success rate alongside its cost, so you can pick a cheaper model that still does the job.

✓You'll see. The same Aider workflow running on different models, with the leaderboard helping you trade off accuracy against token cost.

💳Cost. Aider itself is free and open-source (Apache 2.0) — you pay only your model provider's per-token costs. Aider reports the token count and dollar cost of each interaction in the terminal (use /tokens to see the running total for the current context), so you can watch spend live regardless of which model you choose.

💡Takeaway. Aider's strength is freedom of choice: match the model to the task and budget, and let the leaderboard tell you which is worth it.