# Claude usage-based pricing **URL:** \ **Category:** Help\ **Created:** [May 19, 2024, 9:10pm UTC](https://forum.cursor.com/t/claude-usage-based-pricing/5128 "2024-05-19T21:10:43Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![muhammetali](https://avatars.discourse-cdn.com/v4/letter/m/f08c70/32.png) [@muhammetali](https://forum.cursor.com/u/muhammetali)\ **Post date:** [May 19, 2024, 9:10pm UTC](https://forum.cursor.com/t/claude-usage-based-pricing/5128/1 "2024-05-19T21:10:43Z")
I know there is a 10k context limit in Cursor, but if I turn on the ‘usage-based pricing’ feature, will there still be this 10k limit, or do I have to enter an API key to get rid of the 10k limit? I love your application, but I wish you had a payment plan, such as a $30 long context plan, because we need serious context lengths when writing code, and sonnet and haiku are insufficient in this regard, claude 3 opus is the best ai tool for code, and 10 usage rights are insufficient! ---
**Author:** ![fun\_strange](https://avatars.discourse-cdn.com/v4/letter/f/8c91f0/32.png) [@fun\_strange](https://forum.cursor.com/u/fun_strange)\ **Post date:** [May 19, 2024, 10:20pm UTC](https://forum.cursor.com/t/claude-usage-based-pricing/5128/2 "2024-05-19T22:20:23Z")
Usage-based pricing won’t increase context length for Opus, but you could try this method: > [@\[Solved\] Please add claude-3-opus-200k and gpt-4-turbo-128k (and gpt-4-vision-128k) to Long Context Chat when on our own API key](https://forum.cursor.com/t/solved-please-add-claude-3-opus-200k-and-gpt-4-turbo-128k-and-gpt-4-vision-128k-to-long-context-chat-when-on-our-own-api-key/3948): > > It’s fantastic that you’ve implemented the long context chat feature! This is a great addition to the platform. To further enhance the user experience, could you please also add support for those Anthropic and OpenAI models? It should be a relatively straightforward change to include claude-3-opus-200k and gpt-4-turbo-128k (and gpt-4-vision-128k) when the “Anthropic API key” or “OpenAI API key” options are toggled. Edit: it seems to be possible, I’ve just added claude-3-opus-200k to models, and… (it costs around 3$ per Opus request with your own API key) ---
**Author:** ![muhammetali](https://avatars.discourse-cdn.com/v4/letter/m/f08c70/32.png) [@muhammetali](https://forum.cursor.com/u/muhammetali)\ **Post date:** [May 20, 2024, 6:50am UTC](https://forum.cursor.com/t/claude-usage-based-pricing/5128/3 "2024-05-20T06:50:10Z")
When you look at the cost, it seems quite expensive, it is very normal for companies to cut down on the length of the context, but gpt4o, which has a very low cost, can be added to the ‘long context chat’, or at least gpt4o-32k etc. a model. ---
**Author:** ![system](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/system/32/99069_2.png) [@system](https://forum.cursor.com/u/system)\ **Post date:** [June 18, 2026, 10:13am UTC](https://forum.cursor.com/t/claude-usage-based-pricing/5128/4 "2026-06-18T10:13:04Z")
Closed on June 18, 2026, 10:13am UTC