OpenRouter · 官方公告

14小时前更新

HISTORY近 30 天历史柱高表示当天去重热搜数量

7106 7107 7208 7209 7210 72117213 7214 7215 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7428 7529 7530 7531 7501 7502 7603 76今天

10/06—11/04 有历史数据

01
Guardrails Now Separate Organization Limits from Workspace Defaults
Admins can now set organization-wide limits, give people different budgets and model access within them, and change each policy on its own. Existing guardrails keep working.
02
How we rebuilt provider routing for better, faster inference
Our default routing used to send most traffic to the cheapest provider for a model. The new routing algorithm constantly monitors the performance of every provider endpoint to optimize the balance of cost, speed, and reliability for each new request.
03
CSAM Screening Across OpenRouter
OpenRouter will screen all inference requests for child sexual abuse material (CSAM) as they pass through our service. Screening happens in flight, during request processing. Content flagged as potential CSAM may be retained for human review, with reporting and preservation where required by law.
04
Private Endpoints: Bring Your Fine-Tuned Models and Capacity to OpenRouter
Private Endpoints let Enterprise customers route their own fine-tuned models and dedicated deployments through OpenRouter, alongside the public catalog. Private endpoints are only visible within your organization, and requests go through the API your team already uses. Available by request on the Enterprise plan.
05
ElevenLabs is now on OpenRouter
ElevenLabs is now on OpenRouter with 9 Text to Speech and 2 Speech to Text models. Deliver speech with human-like emotion with Eleven v4, give your agent low-latency replies with v4 Turbo, and turn meetings into notes that show who said what with Scribe v2. Here's which model to pick, and one project built start to finish.
06
Model Router Benchmarks
We now benchmark model routers side by side across six suites. Our Router Index weighs quality, speed, and cost so you can decide if you need a router and pick the best one for your needs.
07
Manage and de-risk your API keys with new Security Center
We audited our own OpenRouter account and found over 1,000 active API keys for 85 employees, 168 of them hadn't been used in months. The new Security Center helps you manage and de-risk your API keys with one place to see every key, know which ones are risky and why, clean them up, and lock them to your own network.
08
Batch API: half-price inference by bundling requests
Send a whole workload in one POST, collect the results within 24 hours, and typically pay half the per-token price. Across 230k+ batches that completed over our two week beta period, the median finished in 7 minutes.
09
In-Region Routing: Route inference in the US or EU
US In-Region Routing is live, joining the EU. Send requests to us.openrouter.ai and their prompts and completions are decrypted only inside the United States and routed only to shared provider endpoints running there, across models from OpenAI, Anthropic, Google, NVIDIA, Thinking Machines, DeepSeek, Moonshot, and Qwen. Requests served by your own BYOK key go to your deployment's region, which you control.
10
Give any model a terminal and files
The shell server tool gives any model on OpenRouter a hosted Linux shell, and the Files API moves files in and out of it. Commands run in an isolated container, the model reads back stdout, stderr, and exit codes, and files the run writes can be downloaded afterward. Available today in beta on the Responses and Messages APIs.
11
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. Compare fill levels, finger counts, poster text, and edits side by side, with the price and generation time under each image.
12
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.
13
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 your terminal with the Analytics API.
14
Live Web Search Benchmarks: Pick the Right Engine, Depth, and Model for Your Agent
We published live leaderboards grading web search configurations across four task suites. Compare engines, search depth, and models by quality, cost, and speed before your agent makes its first search.
15
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 spectrum of tasks.
16
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. Install the ori CLI, log in once, and every supported harness runs with an optimized configuration out of the box.
17
Ori Eval: Find the Best Model for What You're Building
Choosing the model inside your product is often decided without a systematic method. Ori Eval answers the question with proof: it runs your agent on your own prompts, checks the tools it called, and grades the answers.
18
Classifiers: Track What Your Agents Do and What It Costs
Define a taxonomy and a small model tags every generation in your workspace by department, task type, or agent complexity. Filter your logs and group your Activity analytics by the results.
19
A New Look for OpenRouter
Built from first principles and grounded in timeless Bauhaus philosophy, our new brand identity marks the beginning of our next chapter.
20
The OpenRouter MCP Server
Connect your coding agent to OpenRouter's live model catalog, benchmarks, docs, and test inference, all without leaving your editor.
21
Introducing the Unified Image API
A dedicated Image API with capability discovery across 60+ models from 12 providers. One endpoint tells your code what each model can do.
22
Subagent: Let Your Model Delegate the Busywork
The openrouter:subagent server tool lets a frontier model hand off self-contained tasks to a smaller, cheaper, faster worker model mid-generation. Summarize a doc, extract structured data, reformat text, all without burning frontier tokens.
23
Surpassing Frontier Performance with Fusion
A panel of budget models, fused through OpenRouter, outscored GPT-5.5 and Claude Opus 4.8 on 100 complex research tasks.
24
Advisor: Give Any Model a Lifeline to a Smarter One
The openrouter:advisor server tool lets a fast, cheap model consult a stronger one mid-generation. Run GPT-4o Mini for the routine work. Call Claude Fable when it actually matters.
25
May Release Spotlight
Speech and transcription APIs, Model Fusion, private models, enterprise workspace controls, and 20 new model launches including Gemini 3.5 Flash and Claude Opus 4.8.
26
Guardrails: Protect your Agents, Data, and Costs
Configurable security and governance tools for budget enforcement, zero data retention, model and provider restrictions, prompt injection defense, and data loss prevention.
27
OpenRouter Raises $113M Series B
OpenRouter has raised a $113M Series B led by CapitalG, with participation from NVentures, ServiceNow Ventures, MongoDB Ventures, Snowflake Ventures, Databricks Ventures, AMP PBC, and Pace Capital, alongside existing investors Andreessen Horowitz and Menlo Ventures.
28
Consistent Web Search and Fetch Across Every Model
Give any tool-calling model the ability to search the web and fetch page content on its own, with multiple search engines and fetch engines to choose from.
29
New Audio APIs for Speech and Transcription
Text-to-speech and transcription are now live on OpenRouter. Two new endpoints give you access to speech synthesis and audio transcription across multiple providers, under one API.
30
Response Caching: Zero Cost for Identical Requests
Introducing the new Response Caching header: enables caching identical API requests so responses come back in a tiny fraction of the time, at zero cost.
31
April Release Spotlight
Video generation, workspaces, an agent SDK, reranker models, and a wave of frontier model launches.
32
Create OpenRouter Accounts via CLI with Stripe Projects
Run `stripe projects add openrouter/api` to get an OpenRouter account, an API key, and Stripe billing, all from the command line. Your agents can do it too.
33
Introducing Workspaces
Organize your OpenRouter projects into separate environments, each with its own API keys, routing defaults, guardrails, and observability.
34
Announcing Video Generation
Video generation is now live on OpenRouter. One API gives you access to the top video models.
35
Auto Exacto: Adaptive Quality Routing, On by Default
Auto Exacto re-evaluates providers every 5 minutes across throughput, tool-call telemetry, and benchmark scores. For requests that include tools, it's on by default.
36
February Release Spotlight
Benchmarks on model pages, a new free model router, and improved cost transparency between providers.
37
OpenRouter Outages on February 17 and 19, 2026
What happened and what have we done to prevent this happening again?
38
January Release Spotlight
Prioritize fast LLMs, explore providers, customize the auto router, load skills in the SDK, and big performance improvements.
39
December Release Spotlight
Response Healing for structured outputs, chatroom notifications, long-context model rankings, and we're #1 on Brex's fastest-growing AI infra list!
40
Response Healing: Reduce JSON Defects by 80%+
Today we're launching Response Healing, a new feature on OpenRouter that automatically fixes malformed JSON responses from LLMs before they reach your application
41
Provider Variance: Introducing Exacto
Does the same model perform differently across different providers?
42
October 2025 BYOK platform fee update
An October 2025 update to OpenRouter's “Bring Your Own Key” (BYOK) platform fee.
43
The First-Ever Image Model Is Up on OpenRouter
SOTA image generation, character consistency, and multi-image outputs—now live with Gemini 2.5 Flash Image Preview.
44
GPT-5 is now live
GPT-5 is here on OpenRouter — long-context, built for complex reasoning and code workflows.
45
Audio Inputs and PDF URLs for Apps
Add voice input and send PDFs by URL, on any model.
46
New Privacy-Focused Provider Drop: Venice
Venice joins OpenRouter as a new provider, offering its flagship uncensored model for private, powerful, and non-restrictive AI.
47
Updates to Our Free Tier: Sustaining Accessible AI for Everyone
Introducing new models to sustain accessible AI inference.
48
New Stealth Model: "Cypher Alpha"
Try Cypher Alpha — a free, general-purpose stealth model with built-in tool-calling.
49
Introducing Presets: Manage LLM Configs from Your Dashboard!
Centralize your LLM logic, iterate faster, and clean up your code. Presets are now live on OpenRouter.
50
Dev & BYOK Updates: Uptime API + Smarter Key Management
Track model uptime via API and get more control over your BYOK setup including usage limits and testable keys.
51
Simplifying Our Platform Fee
We’re rolling out a simpler and more transparent platform fee structure:
52
GIF Prompts, Omni Search, Tool Caching, and BYOK Flags
Faster workflows, smarter tooling, and smoother image support—GIFs, provider search, Anthropic tool-call caching, and BYOK confirmation are all now live.
53
New Features: Reasoning Streams, Crypto Invoices, End-User IDs & More
Stream reasoning summaries, protect your rate limits, pay with crypto, and lock down your keys—now all live on OpenRouter.
54
Passkeys, DevEx Upgrades, and a New Guide for TypeScript Agents
Secure your account with passkeys, explore provider slugs, and build agents faster with fresh docs.
55
New Provider Drop: Cerebras Is Here
A provider built for speed and scale—from wafer to token. See what becomes possible when memory bottlenecks disappear.
56
Better Insights, Faster Metrics, and New Developer Power Tools
Deeper usage insights, sharper perf metrics, and new dev tools to speed up your workflow.
57
Privacy Clarity, New Providers, OAuth Upgrade, and Gemini Gets Parallel Tools
A couple quality-of-life improvements for developers!
58
Universal PDF Support
OpenRouter now supports PDF processing for every model.
59
Smarter Charts, Inline SVGs, and Live Usage Accounting
Smarter analytics, smoother previews, and instant cost visibility—all now live on OpenRouter.
60
Quasar Alpha and Optimus Alpha Reveal
Quasar Alpha and Optimus Alpha, which both topped the charts during testing, were early test versions of...
61
"Stealth" model: Optimus Alpha
Announcing our second "stealth" model Optimus Alpha
62
“Stealth” model: Quasar Alpha
Announcing our first-ever “stealth” model, Quasar Alpha
63
Never Pay for Empty AI Responses Again
Introducing Zero Token Insurance for All Models
64
Deep Research & Many New Models
The first deep research tool available through the OpenRouter API is live, with full citations directly in the API response.
65
Introducing Nitro and Floor Price Shortcuts
We're rolling out new sorting shortcuts to give you more control over how OpenRouter selects providers
66
Introducing Cloudflare as a new provider
Clouldflare is live now with a new to OpenRouter Gemma model + popular Llama models.
67
Reasoning Tokens for Thinking Models
Understand model thought processes with reasoning tokens
68
Introducing Web Search via the API
Bring all of your requests up to speed with the latest information by incorporating web search results.
69
Standardized finish reasons
Models now return standardized finish reason values, aligned with OpenAI-style conventions.
70
Happy New Year! Introducing a new Auto Router
To start off 2025, we have an upgrade to the Auto Router, and a partnership with NotDiamond
71
Holiday launches: Web Search & Price Cuts
Web search is available for free in the OpenRouter Chatroom.
72
Bring Your Own API Keys
Combine your provider limits and/or cloud credits with OpenRouter, and unify your analytics.
73
Crypto Payments API
The first way to script on-chain payments for any LLM 💸
74
Structured Outputs & Free Gemini Flash 2.0
Structured outputs for OpenAI 4o and Fireworks models + Gemini Flash 2.0
75
Price Drops and Llama 3.3 70b
Price drops and six models, and providers for Llama 3.3 70b
76
Author Pages & Amazon Nova
The new Nova family of models from Amazon has arrived.