For developers
Cursor with your own model: when it pays off
Cursor can work with your key and an OpenAI-compatible address. Here is when that brings real value and when you are better off with the built-in models.
Sanzhar Abdurakhmanov2 min read
When your own model pays off
- Your Cursor plan limits run out before the month ends
- You need a large context for a big project
- Paying Cursor overages is awkward from Kazakhstan or Russia
- You want one subscription for the editor, agents and scripts
Good to know
- Your model is used in chat and agent mode
- Cursor’s built-in autocomplete runs on its own models
- Models differ from the built-in ones, test on your tasks
One-minute setup
Create a key
In the Tenzo Cloud dashboard under API keys.
Set the address and key
Cursor → Settings → Models: paste the key into OpenAI API Key and enable Override OpenAI Base URL.
OpenAI API Key: tc-your-key Override OpenAI Base URL: https://tenzo-cloud.com/v1 Add model: qwen-3.8-maxPick the model
Enable the added model and select it in the chat.
How to tell if your own model pays off
Check how often last month you hit Cursor limits and how much you paid on top of your plan. If limits run out mid-month and overages are routine, your own model on a subscription is almost certainly cheaper.
One subscription also covers more than Cursor: the same key works for Claude Code in the terminal, scripts and bots.
Pricing
Qwen 3.8 Max
Operational1 stream 4+ streams, each 3 days $2.73₸1,150 $2.10₸880 7 days $5.33₸2,280 $4.10₸1,750 30 days $14.30₸6,180 $11₸4,750 GLM 5.3
Coming soon1 stream 4+ streams, each 3 days $2.86₸1,240 $2.20₸950 7 days $5.72₸2,470 $4.40₸1,900 30 days $15.73₸6,830 $12.10₸5,250
Price per stream. Volume discount: 2–3 streams pay 88%, 4 or more pay 77% of the single-stream price. Streams and periods stack. Prices sync from the dashboard automatically.
FAQ
Do I need a paid Cursor plan?
It depends on Cursor’s current rules for custom keys, check its docs. Tenzo Cloud models are paid separately with our subscription.
Which model should I pick?
Qwen 3.8 Max is the all-round choice with a large context and image support.
How do I get the built-in models back?
Turn off Override OpenAI Base URL in settings.
See also
- IntegrationsCursor with your own model: Qwen and GLM with no request limitsHow to use your own model in Cursor through an OpenAI-compatible address: Qwen 3.8 Max and GLM 5.3 with no request limits and no VPN. Step-by-step guide and common errors.Learn more
- ModelsQwen 3.8 Max API: a huge context with no token billQwen 3.8 Max over an OpenAI-compatible API and in a web chat: 256K token context, reads screenshots, a fixed price per stream. Prices in tenge, rubles or USD, 3 hours free.Learn more
- BlogContext window: how much code fits in 256K tokensWhat an LLM context window is, how many lines of code and pages of text fit in 128K and 256K tokens, and why a large context does not mean “send everything”.Learn more
- SolutionsAn LLM API for developers: OpenAI-compatible with no token limitsAn OpenAI-compatible LLM API for developers: Qwen, GLM and DeepSeek, streaming, restricted keys, no token limits and no VPN. Connect in a minute, 3 hours free.Learn more
Try it on your own work
Three free hours with every model, no card and no VPN. Connect Cursor, Claude Code or your own code in a minute.