OpenRouter Now Powers Inference on Hugging Face
OpenRouter now handles model inference routing for Hugging Face Inference Providers. Additionally, OpenRouter can now send execution traces directly to Hugging Face Storage Buckets.
Also shipped Nov 16, 2026OpenRouter in November 2026 →
Deferred tier for asynchronous model calls on the Interactions API
Google Cloud announced general availability for the Deferred tier on the Gemini Enterprise Agent Platform. It offers a 50% discount compared to Standard PayGo rates for asynchronous Gemini model calls, providing a 24-hour completion window and 7-day state retention.
DeepSeek-V4.1-Flash-1017 is available in Public Preview
DeepSeek-V4.1-Flash-1017 is available in public preview as a fully managed model in Vertex AI Model Garden. The updated model features improved reasoning, coding, agentic, and visual capabilities, supporting multimodal inputs with up to 1M context tokens.
OpenAI CSAM Image Classifier is now available at no cost for approved organizations
OpenAI made its CSAM Image Classifier available at no cost to approved organizations. The tool returns separate classification signals for potential child sexual abuse material and potential AI-generated CSAM to assist human review processes.
Budget limit increased to 40,000 budgets per account
GitHub increased the maximum budget limit for GitHub Enterprise Cloud accounts from 10,000 to 40,000 budgets. The limit applies automatically on github.com and GHE.com to support organizations managing spending across many users and cost centers.
Workforce Identity Federation is GA for Looker Google Cloud core instances
Workforce Identity Federation is now generally available as the primary authentication method for Looker (Google Cloud core) instances using public secure, private, or hybrid connections. It can be configured using the Google Cloud console or gcloud CLI during instance creation or updates.
GitHub Copilot models deprecated on November 16, 2026
GitHub deprecated Claude Opus 4.8, Claude Opus 5, and GPT-5.6 Terra across most GitHub Copilot features. Alternative models including Claude Opus 5.5 and GPT-6 variants are automatically enabled for Copilot Enterprise and Business subscriptions under standard settings.
More from OpenRouterEvery OpenRouter release →
Tighter Access Controls for Management Keys
OpenRouter added tighter access controls for management keys, enabling keys to be configured as read-only, restricted to a single workspace, or both.
Introducing the Extractions API
The new Extractions API allows developers to extract typed fields from documents and images. It supports returning values, spans, and confidence scores for numbers, dates, lists, and estimates.
Introducing the New Auto and Auto Code Routers
OpenRouter released the Auto Router and Auto Code router. These tools evaluate factors like live pricing, provider health, and benchmarks to select an appropriate model based on governance policies.
Guardrails Now Separate Organization Limits from Workspace Defaults
Admins can now configure organization-wide limits independently from workspace defaults. This allows for granular control over budgets and model access.
How we rebuilt provider routing for better, faster inference
OpenRouter updated its provider routing algorithm to continuously monitor endpoint performance, optimizing speed, cost, and reliability for inference requests.
CSAM Screening Across OpenRouter
OpenRouter introduced automated in-flight screening of all inference requests to detect child sexual abuse material during request processing.
Private Endpoints: Bring Your Fine-Tuned Models and Capacity to OpenRouter
OpenRouter introduced Private Endpoints for Enterprise customers, allowing teams to route fine-tuned models and dedicated deployments through the standard OpenRouter API with organization-only visibility.
ElevenLabs is now on OpenRouter
OpenRouter added ElevenLabs models to its catalog, offering nine Text-to-Speech models, including Eleven v4 and v4 Turbo, alongside two Speech-to-Text models like Scribe v2.