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 V3 for 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 4.7 or Sonnet 4.6. For implementation, DeepSeek V3.2 ($0.28/$0.42 per 1M) and Qwen 3 Coder are 30-50x cheaper than Opus with near-equivalent code quality. For test generation, DeepSeek V3 or Haiku 4.5 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 V3 work as well as Claude Sonnet for coding?

For implementation and test generation phases — yes, DeepSeek V3.2 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 V3 costs $0.28 input / $0.42 output per 1M tokens, vs Sonnet's $3/$15 — roughly 30-50x cheaper. The right answer for most coding agents is not 'pick one forever' but 'use DeepSeek V3 for the implement/test phases and Sonnet 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 V3 ($0.42/M). A 'refactor this multi-file feature and plan the migration' request goes to Claude Opus 4.7 ($75/M). 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.

Direct · pay-as-you-go · $5 free · the only plan with explicit model control

Pick the model. Pay the bill. No magic.

Direct is the only CodeRouter plan that lets you pick the exact model per request. Smart-routing plans (Starter, Solo, Pro, Studio, Team) silently rewrite explicit model names to auto — that's the product. If you genuinely need to control which model handles each call, Direct is for you. Pay provider list + 15%. No subscription, no quotas, $5 free credit on signup.

Start with $5 free →See pricing

No credit card required · $5 credit on signup

vs. the alternatives

	CodeRouter Direct	OpenRouter	Direct provider API
Signup free tier	$5 credit	None	None
Per-request markup	15%	5% + 5.5% topup fee	0%
Coding models	17 curated	300+ (noisy)	1 vendor only
Usage dashboard	Yes	Basic	Varies
Auto-retry + fallback	Yes	No	No

How it works

Step 1

Sign up, get $5

One click. No credit card. $5 balance lands in your account ready to use.

Step 2

Pick a model (or don't)

Set a default in settings, or pass `model:` in each request. Default is DeepSeek V3 — cheapest capable option.

Step 3

Pay as you go

Each request burns balance at provider list × 1.15. Top up $10+ anytime, auto-reload optional.

Supported models

All charged at provider list price + 15%. Browse the full list at /models.

claude-opus-4.7claude-sonnet-4.6claude-haiku-4.5gpt-5.5gpt-5.4gpt-5-minigemini-3-progemini-3-flashgemini-2.5-progemini-2.5-flashdeepseek-v4-prodeepseek-chatdeepseek-reasonerkimi-k2.6qwen-maxqwen-plusqwen-turboglm-5.1glm-4-plus

Quick questions

How is this different from the Smart plan?▾

Smart auto-routes every request to the cheapest capable model based on phase + agent + complexity (typically 70-90% cheaper than always picking Opus). On Smart, your client's `model:` field is IGNORED — even if you send `model="claude-opus-4.7"`, we silently rewrite it to auto and route to whatever phase routing picks. Direct is the opposite: your `model:` field is honored, you pay provider list + 15%, no routing decisions on our side. Pick Smart when you want savings, pick Direct when you want control.

Why didn't my Smart plan request use the model I asked for?▾

Because that's the whole point of Smart routing. Your client (Cursor / Claude Code / Codex) probably hardcoded a specific model in its config — we silently rewrite to auto so the routing pipeline runs. Check the response header `X-CodeRouter-Auto-Override` for the original model you requested, and `X-CodeRouter-Model` for the one we actually routed to. If you genuinely need the exact model you specified, switch to Direct.

Can I switch between Smart and Direct?▾

Yes, both directions, any time, self-serve. Smart → Direct from /dashboard/direct. Direct → Smart by picking a Smart plan in /dashboard/subscription (Stripe handles proration). Your prepaid balance carries over either way. The $5 signup credit is account-scoped — granted once when you add a card, regardless of which mode you start in. Switching modes never re-claims it.

What if my balance runs out?▾

Requests return 429 until you top up. No surprise charges, no BYOK fallback — balance at $0 = hard stop. Minimum top-up is $10.

How do you calculate the 15%?▾

Every completed request: actual provider cost × 1.15 deducted from balance. 'Actual cost' is input tokens × provider list price + output tokens × provider list price, minus any cache discount provider gave us (we pass the discount through, then mark up the discounted rate).

Pick the model. Pay the bill. No magic.

No credit card required · $5 credit on signup

Start with $5 free →