OpenRouter Pareto Code: cost-optimized coding router
Melvin Vivas · X post · 2026-05-10 · Open on X
Topics: LLMOps, Deployment & Monitoring, AI Dev Tools & Productivity, LLM Fundamentals · Level: intermediate
Summary
OpenRouter launched Pareto Code, a free, experimental router for coding requests. You set min_coding_score in your request, and it sends the request to the cheapest code-capable model that meets that score, using Artificial Analysis rankings. The creator calls it a game-changer for cutting coding costs.
Key points
- Pareto Code is a free, experimental coding router from OpenRouter.
- Set the
min_coding_scoreparameter in your request to define your quality bar. - It routes to the cheapest code-capable model that meets that bar.
- Models are ranked using Artificial Analysis benchmarks.
- The Pareto frontier of cost vs. quality updates in real time as new models arrive.
Resources mentioned
- OpenRouter · tool · openrouter.ai · free
A single OpenAI-compatible API that routes requests to hundreds of models from many providers, with one bill and model fallbacks.
Also in: Stealth Model 'Space Bunny' Revealed as MiniMax M3.1 Flash (Melvin Vivas on X · notes), NVIDIA Nemotron 3.5 Super VL now on OpenRouter (Melvin Vivas on X · notes), OpenRouter serves image models, including FLUX 3 Image Klein (Melvin Vivas on X · notes), Comparing Opus 5.5, GPT-6 Astra and Grok 4.7 on OpenRouter (Melvin Vivas on X · notes) and 53 more - OpenRouter Pareto Code · tool · openrouter.ai · free
Free, experimental router that picks the cheapest coding model meeting your min_coding_score. - Artificial Analysis · website · artificialanalysis.ai · free
Independent benchmarking site that compares LLMs on intelligence index, price, cost per task and the cost-vs-intelligence Pareto frontier.
Also in: Liquid AI releases d1-ultra decision model (Melvin Vivas on X · notes), Is AI Getting Cheaper? How to Measure LLM Cost Per Task and Per Intelligence Level (Melvin Vivas on X · notes), ElevenLabs Eleven v4 & v4 Turbo: Emotive, Multilingual Text-to-Speech Models (Melvin Vivas on X · notes), Be Skeptical of Model Leaderboards: Muse Spark vs Astra (Melvin Vivas on X · notes) and 3 more
Try this
- Try setting min_coding_score in OpenRouter requests to lower coding costs.
More in LLMOps, Deployment & Monitoring
- Unsloth MTP GGUFs make Qwen3.6 run 1.4x faster locally
- Cheap TTS serving: Qwen3-TTS on vLLM-Omni at $3 per 1M characters
- LM Studio MLX v1.8.1: Vision Model Batching and Better Caching
- Speeding Up Gemma 4 Inference: MTP (3x) vs. DFlash Speculative Decoding (6x)
- Self-Host a Coding Model on QuickPod with llama-swap and Use It in Claude Code
- Runpod Flash Reaches GA: Deploy AI Workloads from Python