aiqbench takeAI Products

The article is about the API cost of running Claude Code, an AI coding agent, across models, so AI is central. It reports median per-session costs by model (Opus, Sonnet, Haiku) and attributes most of the spend to cached context re-read on each turn. For readers, the practical points are that model choice drives cost by a wide margin and that prompt caching and session length matter. The medians come from one platform's usage data, so they show typical patterns rather than guaranteed costs.

Sources coveringOpenRouter, Latent Space, arXiv, Google Cloud Blog

How Much Does Claude Code Cost? Real Session Costs by Model

OpenRouterOctober 30, 20269 min read

Claude Code is free to install, and what you pay for is the model it calls. We publish the median cost of real Claude Code sessions on OpenRouter by model and session length. This post shows those costs, why the first request costs the most, what a month of use comes to, and how to lower the bill.

Claude Code is free to install. What you pay for is the model it calls. If you run Claude Code on an API key, a short session of 2 to 9 turns with Claude Opus 5.5 costs $0.31 at the median, and a long session of 10 to 49 turns costs $1.39. The same sessions with Claude Sonnet 5.5 cost $0.16 and $0.60. Those medians come from real Claude Code sessions on OpenRouter in the 30 days to October 18, 2026. Claude Code was the top app in our daily app ranking on October 21, so there’s a lot of usage behind them. Below, we use that data to show what a session costs on each model, then how to run Claude Code on OpenRouter so you can pick the model for each session, see what it cost, and cap your spend. Claude Code is free. You pay for the model it calls, either through a Claude subscription or per token on an API key. On an API key, a 2-to-9-turn…

Excerpt shown under the publisher's RSS terms · 171 words · full text and figures are on the publisher's site

Read at OpenRouter ↗Ask about this article