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.

About CodeRouter

CodeRouter is an independent phase-aware LLM router for AI coding agents. You point your coding agent at one OpenAI-compatible endpoint; for each request we detect what the agent is actually doing — planning, implementing, debugging, testing or documenting — and forward it to the cheapest model that is capable of that specific job.

The problem we exist to solve

Coding agents send every request to whichever model you configured. That means an architectural decision and a one-line docstring cost the same. In a normal day of agent work the expensive requests are a minority, but they set the price for all of them.

Routing per request is the whole product. Everything else on this site — the model table, the integration guides, the error reference — exists to support that one decision.

How a model gets chosen

Phase detection. We classify the incoming request from its messages, tool definitions and conversation shape into a coding phase. Requests we cannot classify fall back to a conservative default rather than guessing.
Capability filter. Models are scored per coding phase, not with one general-purpose score. A model strong at implementation may be excluded from planning. Requests that need vision, long context or thinking mode are restricted to models that actually support them.
Cost ordering. Among models that clear the capability bar for that phase, the cheapest is chosen.
Health and failover. Providers that error or degrade enter a cooldown so one upstream outage does not cascade into your session.

The current model list and per-phase scores are public on the models page, and the routing behaviour for each supported agent is documented in the integration guide.

What CodeRouter is not

Not a model marketplace. A marketplace gives you many models and leaves the choice to you. Our position is that the per-request choice is the part worth automating.
Not a model provider. We do not train or host models. Requests are forwarded to upstream providers.
Not affiliated with the tools we support. CodeRouter is not affiliated with, endorsed by, or sponsored by Anthropic, Cursor, OpenRouter, Aider, GitHub Copilot, Windsurf, Cline or any other tool named on this site. All product names and trademarks belong to their respective owners.

How we make money

CodeRouter charges for usage of the routing service. We do not sell your data, and we are not paid by model providers to prefer their models — routing order is determined by the per-phase capability scores and price, both of which are published on the models page. Pricing is on the pricing page.

On savings claims

Where this site cites a 70–90% reduction, that figure describes mixed coding workloads routed to lower-cost models instead of sending every request to a premium model. Your actual savings depend on your workload mix — an agent that spends most of its time on architectural reasoning will save less than one doing bulk implementation. The dashboard shows your own per-request routing and spend rather than an estimate.

Development and support

CodeRouter has been in continuous development since April 2026. Notable routing, model and billing changes are recorded on the changelog.

Support and business enquiries: support@coderouter.io. More on what to send and what to include is on the contact page.