How do I reduce my Cursor API bill?

Cursor Pro's $20/mo covers 500 fast requests — past that you pay OpenAI / Anthropic per-call rates directly, which is why heavy users end up at $50-$200/mo. The fix is to point Cursor's Custom API at CodeRouter and set model to 'auto'. CodeRouter detects what phase of coding the request is (planning, implementation, debugging, test generation, docs) and routes to the cheapest capable model per phase — Opus only for planning, DeepSeek V4 Pro for implementation and test generation, Haiku for docstrings. Same Cursor IDE, same keyboard shortcuts, 70-90% lower monthly bill. Setup takes 2 minutes — just change base_url to https://www.coderouter.io/api/v1 and paste your cr_ API key.

What is the cheapest API for Claude Code / Aider / Copilot?

There isn't a single 'cheapest API' — the cheapest model depends on what the coding agent is doing. For planning and architecture, you still want Claude Opus 4.8 or Sonnet 4.6. For implementation, DeepSeek V4 Pro ($0.44/$0.87 per 1M) and Kimi K2.6 are 15-40x cheaper than Opus with near-equivalent code quality. For test generation, DeepSeek V4 Pro or GLM-5.2 is 15-50x cheaper. For docstrings and simple formatting, Haiku 4.5 ($1/$5) or Gemini 2.5 Flash ($0.30/M output) is 15-250x cheaper. CodeRouter is the gateway that picks per request automatically — aim a single base_url at https://www.coderouter.io/api/v1 from Claude Code, Aider, Copilot (via LiteLLM), Cursor, Windsurf, or any OpenAI-compatible agent.

Does DeepSeek V4 Pro work as well as Claude Sonnet for coding?

For implementation and test generation phases — yes, DeepSeek V4 Pro matches Claude Sonnet 4.6 on HumanEval, MBPP, and LiveCodeBench within 1-3 points. For multi-file refactoring and architecture planning, Sonnet still has an edge on long-context reasoning. DeepSeek V4 Pro costs $0.44 input / $0.87 output per 1M tokens after the July 2026 price cut, vs Sonnet's $3/$15 — roughly 7-17x cheaper. The right answer for most coding agents is not 'pick one forever' but 'use DeepSeek V4 Pro for the implement/test phases and Sonnet or Kimi K3 for the plan/refactor phases.' That's phase-aware routing in practice — CodeRouter decides per request in ~10ms.

What is phase-aware LLM routing?

Phase-aware LLM routing classifies each coding-agent request by what phase of software work it represents — planning, implementation, debugging, testing, refactoring, or documentation — and routes it to the cheapest model that can handle that specific phase. A 'write unit tests for this function' request goes to DeepSeek V4 Pro ($0.87/M output). A 'refactor this multi-file feature and plan the migration' request goes to Claude Opus 4.8 ($25/M output). This is different from picking one model for everything, and different from OpenRouter-style model-selection (which still requires you to choose manually). CodeRouter's classifier runs in ~10ms on the server, so the agent never notices the extra hop.

CodeRouter vs OpenRouter — which saves more money on coding?

OpenRouter is a model marketplace — it gives you access to 300+ models behind one API key, but you still pick which model to send each request to. Most Cursor / Aider / Claude Code users default to the premium model (Opus, GPT-5) for everything and end up paying full price. CodeRouter is a phase-aware router — set model to 'auto' and we pick the cheapest capable model per request based on the coding phase. CodeRouter also adds things OpenRouter doesn't: coding-specific capability scores per model (implementation, debug, test, refactor), per-end-user attribution for SaaS agent builders, and built-in quota + top-up billing. For pure coding workloads, typical CodeRouter savings are 70-90% vs picking one model on OpenRouter.

Will CodeRouter break my Cursor / Aider / Claude Code agent?

No. CodeRouter exposes a standard OpenAI-compatible chat completions endpoint (POST /api/v1/chat/completions) with the same request and response format your agent already uses — including streaming, tool use, and function calling. We implement the same JSON schema and stream format, so Cursor, Aider, Claude Code, Cline, Continue.dev, Windsurf, OpenClaw, and any LiteLLM-wrapped client work unmodified. If a routed model fails, the fallback chain tries up to 2 alternates automatically (on 429, 500-504, timeouts, missing keys). You can also pin an explicit model instead of 'auto' any time.

How do I set up CodeRouter with Cursor in 2 minutes?

1) Sign up free at https://www.coderouter.io/login and copy your API key (starts with cr_). 2) In Cursor, open Settings -> Models -> OpenAI API Key, and under 'Override OpenAI Base URL' paste https://www.coderouter.io/api/v1. Paste your cr_ key in the API Key field. 3) Add 'auto' to the Custom Models list and select it as your active model. That's it — phase-aware routing is live. Aider users set OPENAI_API_BASE and OPENAI_API_KEY env vars to the same values. Claude Code users set ANTHROPIC_BASE_URL to https://www.coderouter.io/api/v1 and ANTHROPIC_API_KEY to the cr_ key. Full guide at https://www.coderouter.io/setup.

Contact CodeRouter

Every enquiry below reaches the same inbox: support@coderouter.io. Naming the category in your subject line gets it to the right place faster.

Support and technical issues

Routing behaviour, integration problems, unexpected model selection, API errors.

Before writing, it is worth checking the LLM API error reference — it is indexed by exact error string and covers the errors we see most often.

Billing and account

Invoices, plan changes, top-ups, cancellation, refund requests.

Payments are processed by Stripe and subscriptions renew automatically unless cancelled before the renewal date. Refunds are handled case by case — see the terms.

Security disclosure

If you believe you have found a vulnerability, email us before disclosing it publicly.

Please include reproduction steps and do not include live credentials in the report.

Press and partnerships

Media enquiries, integration partnerships, and questions about how routing decisions are made.

What to include in a routing report

Routing issues are much faster to diagnose with these four things. Without them the first reply is usually a request for them.

The agent and version — Claude Code, Cursor, Aider, Cline, Continue.dev, Windsurf, OpenClaw or an SDK, and which version.
The exact error string, verbatim, including the HTTP status. Paraphrased errors frequently point at the wrong layer.
What you expected to be routed to, and what was actually selected — the dashboard shows the per-request model.
Whether it is reproducible, and if so the shortest request that reproduces it. Never include your API key.

Other channels

Product and routing changes are recorded on the changelog.
Setup and per-agent configuration is in the integration guide.
Data handling questions are answered in the privacy policy.