{"slug": "digitalocean-inference-router-enhancements-performance-tuned-routing-no-rules-to", "title": "DigitalOcean Inference Router Enhancements: Performance Tuned Routing, No Rules to Write", "summary": "DigitalOcean launched its Inference Router in Public Preview, a managed routing layer that sends each request to the model that performs best for the job, validated by public benchmarks, with no presets or custom routers required. DigitalOcean said internal testing across software engineering, reasoning and agentic work showed Inference Router had higher accuracy than Claude Opus 5.5 and GPT-6 Astra at about 22% lower cost, drawing on frontier models from Anthropic and OpenAI plus open source models including Kimi, GLM and DeepSeek. The router is free during Public Preview, with users billed only for the models that serve each request, and DigitalOcean plans to let customers bring their own evaluation rubrics to steer routing.", "body_md": "Every few weeks, a new model steps up and claims best-in-class at something. The launch chart makes the case, the link makes the rounds, and your team is back to the question nobody has time for: should we switch?\n\nThe answer takes a week of evals, side-by-side tests and debate, and by the time your team lands on one, the next contender is already on the scoreboard. It’s a race you can’t win manually. And the launch charts only tell part of the story. They show where a model is strongest, not where it isn’t.\n\nToday, we’re enhancing the DigitalOcean Inference Router so it makes that call for you. No presets to select, no custom routers to build. Send your prompt, set the model to `inference-router`, and choose a preference if you want one. The router sends each request to the model that performs best for that job, validated by public benchmarks.\n\nUnder the hood, inference-router draws on the entire DigitalOcean Model Catalog: frontier models from Anthropic and OpenAI, open source models like Kimi, GLM, and DeepSeek, all one request away. Every new model gets the same test. The ones that measure up are added to the router.\n\nAnd because every request goes to the model that fits the job, you stop paying frontier prices for work a leaner model handles just as well. In our internal testing across software engineering, reasoning and agentic work, Inference Router had higher accuracy than Claude Opus 5.5 and GPT-6 Astra, at about 22% lower cost.\n\nWith Inference Router, you stop:\n\nThe Inference Router Getting Started page on DigitalOcean cloud console shows the benchmarks behind each use case, how the router scores against the best single model, and which models it’s choosing between. It updates whenever we add a model or rerun an evaluation.\n\nHere is how some of the models behind the router score on some of the benchmarks we use:\n\n*Scores are from DigitalOcean’s internal evaluations as of October 12th, 2026. Results vary with configuration and may differ from public leaderboards.*\n\nWe measure models across a wide variety of tasks and evaluate how well they did, along with the cost and latency. That evidence decides who wins each task.\n\nWhen a request arrives, the routing model reads it, matches it to the right task, and weighs your preference to pick the best model. The router is intrinsically cache-aware and knows to hold onto a model to re-use its cache unless a switch pays for itself.\n\nAs all the heavy lifting happens before your request arrives, you don’t have to manage the configuration manually. When a newly released model does better on a specific task, you benefit automatically.\n\nThe router is initially trained on the following task categories:\n\nWhile the Inference Router measures well on public benchmarks & our internal evals, that doesn’t tell you how well it does on yours. So while we are starting with a generally optimized router, soon you’ll be able to bring in your own rubric. Bring your evaluation set, and your definition of success decides which model wins.\n\nInference Router is managed end to end by DigitalOcean, so most requests won’t need any input from you.\n\nWhen you want to influence the choice, use `budget` to nudge the router to prefer lower cost models or quality for when success is critical. However, we expect `routing_preference: balanced` (the default) to work for most customers.\n\nPreferences are the first dial. Soon, your own evaluation set will steer the router too, and when a new model ships, we’ll re-run them so you stay on the best fit. Want early access? Request it from the Getting Started page through the DigitalOcean Console.\n\nInference Router is available today in Public Preview. There is no additional cost to use it during Public Preview; you’re billed for the models that serve each request.\n\n```\ncurl https://inference.do-ai.run/v1/chat/completions \\\n  -H \"Authorization: Bearer $MODEL_ACCESS_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"model\": \"inference-router\",\n    \"preference\": \"balanced\",\n    \"messages\": [{\"role\": \"user\", \"content\": \"Fix the failing test in ...\"}]\n  }'\n```\n\n", "url": "https://wpnews.pro/news/digitalocean-inference-router-enhancements-performance-tuned-routing-no-rules-to", "canonical_source": "https://www.digitalocean.com/blog/inference-router-enhancements", "published_at": "2026-10-13 13:00:00+00:00", "updated_at": "2026-10-15 04:57:52.542814+00:00", "lang": "en", "topics": ["ai-infrastructure", "ai-products", "large-language-models", "ai-tools", "mlops"], "entities": ["DigitalOcean", "Inference Router", "Anthropic", "OpenAI", "Claude Opus 5.5", "GPT-6 Astra", "Kimi", "DeepSeek"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/digitalocean-inference-router-enhancements-performance-tuned-routing-no-rules-to", "markdown": "https://wpnews.pro/news/digitalocean-inference-router-enhancements-performance-tuned-routing-no-rules-to.md", "text": "https://wpnews.pro/news/digitalocean-inference-router-enhancements-performance-tuned-routing-no-rules-to.txt", "jsonld": "https://wpnews.pro/news/digitalocean-inference-router-enhancements-performance-tuned-routing-no-rules-to.jsonld"}}