Answers
What's the cheapest API for Cursor?
The cheapest coding-capable API you can plug into Cursor today is DeepSeek-V4-Flash at $0.084 input / $0.168 output per 1M tokens ($0.101/1M blended at a 4:1 split) through an OpenAI-compatible endpoint — 82.7 on Terminal-Bench 2.1 against Claude Opus 4.8's 85.0 on the same published harness. When a task needs more depth, MiniMax-M2.7 costs $0.18 / $0.72 per 1M. Cursor accepts either by overriding the OpenAI base URL; no plugin needed.
| Model | Input / 1M | Output / 1M | Blended (4:1) | vs cheapest |
|---|---|---|---|---|
| DeepSeek-V4-Flashvia Mingles Router | $0.084 | $0.168 | $0.101 | — |
| MiniMax-M2.7via Mingles Router | $0.18 | $0.72 | $0.288 | 2.9× |
| Claude Sonnet 5 | $2.00 | $10.00 | $3.60 | 35.7× |
| GPT-5.4 | $2.50 | $15.00 | $5.00 | 49.6× |
Vendor list prices; sources: Anthropic — Claude pricing, OpenRouter — models & pricing, DeepSeek — DeepSeek-V4-Flash-0731 model card. Prices verified October 13, 2026.
Set it up in Cursor (60 seconds)
- Get a free key at router.mingles.ai/app — no card.
- Cursor → Settings → Models → paste the key as your OpenAI API key.
- Override the OpenAI base URL with
https://router.mingles.ai/v1. - Add a custom model:
deepseek-ai/DeepSeek-V4-Flash-0731(orMiniMaxAI/MiniMax-M2.7for the tasks that need more depth).
Full walkthrough with screenshots on the agents hub.
The honest caveats
- Cursor Pro bundles editor features we don't replace — a cheap key replaces the model bill, not the subscription's tab-completion models.
- Frontier models keep a lead of a couple of points on hard reasoning benchmarks (AIME, GPQA). For agent loops and code edits the published gap is within one point.
- Two main models, not three hundred. If you need vision or a specific frontier model, use both endpoints side by side.
FAQ
▸Does Cursor work with a custom OpenAI-compatible API?
Yes. In Cursor: Settings → Models → add your API key and override the OpenAI base URL with https://router.mingles.ai/v1, then add the model id (e.g. deepseek-ai/DeepSeek-V4-Flash-0731). Cursor treats it like any OpenAI endpoint — chat, inline edits and agent mode all work.
▸Is a cheap model good enough for coding in Cursor?
DeepSeek-V4-Flash scores 82.7 on Terminal-Bench 2.1 on its published model card — Claude Opus 4.8 scores 85.0 under the same harness. When a task needs more depth, MiniMax-M2.7 matches GPT-5.3-Codex on SWE-Bench Pro per its own card. The honest gap is the hardest repo-scale work, where frontier models keep a clear lead.
▸Is this cheaper than Cursor Pro?
Different thing: Cursor Pro ($20/mo) bundles the editor features with model credits. Bringing your own key means you pay for exactly the tokens you use — the Mini plan is $9/mo for an allowance worth ~220M DeepSeek-V4-Flash tokens — but heavy Claude/GPT usage inside Cursor Pro can also hit its own caps. Many users run both: Pro for the editor, a cheap key for the heavy agent loops.
▸Is there a free tier to test with?
Yes — a free API key with a weekly allowance (~3.9M tokens on DeepSeek-V4-Flash), no card required. Enough to run Cursor for an evening and decide with your own code.