Skip to main content
Cursor is a practical way to bring Crazyrouter into your day-to-day coding workflow for chat, code explanation, refactoring suggestions, and general editing help.

​
Overview

With Cursor’s BYOK (Bring Your Own Key) flow, you can route part of your chat-model traffic through Crazyrouter and pay against your own token instead of bundling everything into Cursor usage.
  • recommended path: OpenAI-compatible mode
  • Crazyrouter base URL: https://crazyrouter.com/v1
  • auth format: sk-... token
  • best first-use features: Chat, Ask, and normal editing conversations
According to Cursor’s official documentation, custom API keys only work with standard chat models. Features that depend on specialized models, such as Tab Completion, continue using Cursor’s built-in models. That limitation comes from Cursor, not from Crazyrouter.

​
Best For

  • developers who want to use Crazyrouter tokens inside Cursor
  • teams that want better control over model choice, cost, and quota
  • users who want Cursor chat routed through Crazyrouter
  • setups where IDE, CLI, and automation tokens should be tracked separately

​
Protocol Used

Recommended protocol: OpenAI-compatible API When connecting Cursor to Crazyrouter, use this OpenAI-compatible base URL: 
https://crazyrouter.com/v1
Do not use:
  • https://crazyrouter.com
  • https://crazyrouter.com/v1/chat/completions

​
Prerequisites

ItemNotes
Crazyrouter accountCreate one at crazyrouter.com
Crazyrouter tokenCreate a dedicated sk-... token for Cursor
Cursor desktop appUpdate to a current stable version before setup
Allowed modelsMake sure the token allows at least 1 to 2 OpenAI-compatible chat models
Recommended starter allowlist:
  • gpt-5.4
  • claude-sonnet-4-6
  • gemini-3-pro-preview
If you also plan to configure Claude Code, Codex, or Cline, do not share the same token with Cursor. Separate tokens make quota control and debugging much easier.

​
Quick Start

1

Create a Cursor-specific token

In Crazyrouter, create a new token and name it something obvious like cursor. Start with a small allowlist such as gpt-5.4 and claude-sonnet-4-6.
2

Open Cursor settings

Open Cursor and go to Cursor Settings → Models.
3

Fill the OpenAI connection fields

In the OpenAI-related section, enter:
  • OpenAI API Key: your sk-...
  • Override OpenAI Base URL: https://crazyrouter.com/v1
If your Cursor build does not show Override OpenAI Base URL, your current version does not fully expose the custom OpenAI-compatible endpoint path yet. In that case, upgrade Cursor first or wait for improved support on the Cursor side.
4

Verify the key and pick a model

Click Verify. After it succeeds, enable one model for the first validation. gpt-5.4 is the safest starting point.
5

Run the first test

Open the chat panel and send a simple request such as Reply with only OK. If that succeeds, Crazyrouter is connected.
Use caseRecommended modelWhy
default baselinegpt-5.4verified successfully in production on March 23, 2026, and stable for the main Cursor OpenAI-compatible path
high-quality code and long-form workclaude-sonnet-4-6stronger for complex explanation, summaries, and code assistance
Gemini fallback pathgemini-3-pro-previewuseful as a second compatibility-validation path
Recommended rollout order: get gpt-5.4 working first, then test claude-sonnet-4-6 and gemini-3-pro-preview.

​
Token Setup Best Practices

SettingRecommendationNotes
dedicated tokenRequiredDo not share one token across Cursor and other tools
model allowlistRecommendedKeep only the models Cursor should actually use
IP restrictionSituationalUsually avoid it on laptops with changing egress IPs; consider it on fixed office networks
quota capStrongly recommendedGive Cursor its own budget
env separationRecommendedUse separate tokens for personal machines, team workstations, and CI
rotationRecommendedIf screenshots, recordings, or sync accidentally expose the token, rotate it quickly

​
Verification Checklist

  • Verify succeeds in Cursor Settings → Models
  • Override OpenAI Base URL is set to https://crazyrouter.com/v1
  • at least one Crazyrouter-backed model is selected
  • the first chat request succeeds
  • the matching request appears in Crazyrouter logs
  • token quota and model allowlist match your intended setup
  • you understand that Tab Completion and similar features may still bypass Crazyrouter

​
Common Errors And Fixes

SymptomLikely causeFix
Verify failswrong API key or wrong base URLre-check the sk-... key and https://crazyrouter.com/v1
401 unauthorizedinvalid, expired, or badly pasted tokengenerate a new token and paste the raw value again
403 or model not allowedthe model is not in the token allowlistallow that model in Crazyrouter token settings
404base URL was set to the root domain or a full endpoint pathuse exactly https://crazyrouter.com/v1
no models show up or the list looks wrongCursor BYOK refresh failed or the current version has compatibility issuesrestart Cursor, verify again, and update to the latest stable build if needed
chat works but Tab Completion does not use CrazyrouterCursor officially keeps specialized features on built-in modelsexpected behavior, not a Crazyrouter outage
custom models do not behave correctlyCursor’s custom OpenAI-compatible endpoint support is still inconsistentget gpt-5.4 working first, then test other models gradually
cost jumps unexpectedlyone token is shared across too many tools or the allowlist is too widenarrow the model set and give Cursor its own quota cap

​
Performance And Cost Tips

  • start with only gpt-5.4
  • use gpt-5.4 for the baseline coding and chat workflow
  • add claude-sonnet-4-6 or gemini-3-pro-preview only after the baseline path is stable
  • split Cursor, Claude Code, and Codex traffic across different tokens
  • if usage looks suspiciously high, inspect Crazyrouter logs and check whether long multi-turn context is driving costs

​
FAQ

​
Which base URL should I enter in Cursor?

Use https://crazyrouter.com/v1.

​
Why do some Cursor features still not go through Crazyrouter?

Because Cursor officially limits custom API keys to standard chat models. Specialized features such as Tab Completion continue using Cursor-managed models.

​
Which model should I use first?

Start with gpt-5.4. It is the latest OpenAI-compatible baseline already verified in production.

​
Can I use Claude or other non-OpenAI models directly?

You can try them, but first complete a clean OpenAI-compatible baseline setup. Whether a custom model works cleanly in your current Cursor version depends on Cursor’s compatibility implementation.

​
Chat works, but model selection keeps getting weird. What should I do?

Restart Cursor, verify again, and fall back to gpt-5.4 as the known-good baseline before expanding the config.
If your main goal is a stable coding workflow through Crazyrouter, Claude Code, Codex, and Cline are often more direct and controllable than Cursor’s custom endpoint path. Cursor is best treated as a chat-first and general editing integration.