# OpenRouter updates

Every OpenRouter update in one feed — release notes, features and changes, straight from the source.

16 updates

- ## [How we rebuilt provider routing for better, faster inference](<https://creatorstoolbox.com/blog/openrouter-how-we-rebuilt-provider-routing-for-better-faster-inference>)

The new default router weighs price, speed and reliability, cutting capacity errors 67% and lifting throughput 16.3% for a 6.0% cost increase.

2026-10-28

- ## [CSAM Screening Across OpenRouter](<https://creatorstoolbox.com/blog/openrouter-csam-screening-across-openrouter>)

OpenRouter will screen every inference request in flight, including Zero Data Retention traffic, and may retain flagged content for human review.

2026-10-27

- ## [Private Endpoints: Bring Your Fine-Tuned Models and Capacity to OpenRouter](<https://creatorstoolbox.com/blog/openrouter-private-endpoints-bring-your-fine-tuned-models-and-capacity>)

Available by request as an Enterprise add-on, it serves fine-tuned models and reserved capacity under the same slugs, with public providers as optional backup.

2026-10-14

- ## [ElevenLabs is now on OpenRouter](<https://creatorstoolbox.com/blog/openrouter-elevenlabs-is-now-on-openrouter>)

All OpenRouter customers get 50% off the 11 ElevenLabs models through October 19 at 8am PT, with no separate ElevenLabs plan required.

2026-10-07

- ## [Model Router Benchmarks](<https://creatorstoolbox.com/blog/openrouter-model-router-benchmarks>)

The Router Index scores each router from 0 to 10, weighting quality 60%, speed 20% and cost 20% by default, with an adjustable slider.

2026-10-02

- ## [Manage and de-risk your API keys with new Security Center](<https://creatorstoolbox.com/blog/openrouter-manage-and-de-risk-your-api-keys-with-new-security-center>)

Available on every OpenRouter plan, it scores key risk and archives up to 500 keys at once, while the IP allowlist is limited to Enterprise admins.

2026-09-28

- ## [Batch API: half-price inference by bundling requests](<https://creatorstoolbox.com/blog/openrouter-batch-api-half-price-inference-by-bundling-requests>)

Batches process within 24 hours at roughly half the per-token price, with a median completion time of 7 minutes across 70+ models.

2026-09-22

- ## [In-Region Routing: Route inference in the US or EU](<https://creatorstoolbox.com/blog/openrouter-in-region-routing-route-inference-in-the-us-or-eu>)

US and EU routing keeps prompts and completions in-region on Business and Enterprise plans, including DeepSeek, Kimi and GLM models.

2026-09-09

- ## [Give any model a terminal and files](<https://creatorstoolbox.com/blog/openrouter-give-any-model-a-terminal-and-files>)

The beta ships on the Responses and Messages APIs, with sandbox time billed at $0.0001 per second.

2026-09-08

- ## [Image Benchmarks: See the Capabilities of Every Model](<https://creatorstoolbox.com/blog/openrouter-image-benchmarks-see-the-capabilities-of-every-model>)

We ran 39 image models through 15 deliberately hard prompts and put every result on one page.

2026-08-21

- ## [OpenRouter is Joining Stripe](<https://creatorstoolbox.com/blog/openrouter-openrouter-is-joining-stripe>)

Today, we are excited to announce that we are joining forces with Stripe, to power the next wave of GDP growth globally.

2026-08-19

- ## [Understand your AI usage: every agent, model, and request](<https://creatorstoolbox.com/blog/openrouter-understand-your-ai-usage-every-agent-model-and-request>)

See what your team spent on every model, save the charts you keep rebuilding, click any bar to land in the logs behind it, and query the same data from…

2026-08-17

- ## [Live Web Search Benchmarks: Pick the Right Engine, Depth, and Model for Your Agent](<https://creatorstoolbox.com/blog/openrouter-live-web-search-benchmarks-pick-the-right-engine-depth-and-model-for->)

We published live leaderboards grading web search configurations across four task suites.

2026-08-12

- ## [Model Routing Powered by Wisdom of the Market](<https://creatorstoolbox.com/blog/openrouter-model-routing-powered-by-wisdom-of-the-market>)

Our new Auto router is informed by the model decisions of millions of people, and it outperforms conventional task-based classifiers across a wide…

2026-08-10

- ## [Ori Harness: The Best Way to Use OpenRouter with Any Harness](<https://creatorstoolbox.com/blog/openrouter-ori-harness-the-best-way-to-use-openrouter-with-any-harness>)

Using OpenRouter with your favorite harness usually means ad-hoc scripts or a wall of environment variables.

2026-08-04

- ## [Ori Eval: Find the Best Model for What You're Building](<https://creatorstoolbox.com/blog/openrouter-ori-eval-find-the-best-model-for-what-you-re-building>)

Choosing the model inside your product is often decided without a systematic method.

2026-08-03

[Open OpenRouter updates on Creators Toolbox](<https://creatorstoolbox.com/updates/openrouter>)

---
Canonical source: https://creatorstoolbox.com/updates/openrouter