OpenRouter
@OpenRouter
The unified interface for LLMs. 400+ models (incl. 50+ free), the best prices, explorable data, private chat, & a unified API.
389 Following 158.1K Followers
Your app just found its voice. Over 2,900 of them, actually 🎙️
HeyGen Voice Turbo is free on OpenRouter until November 30. $0, no credits, 39 languages.
Read more about our approach:
We just shipped our biggest improvement to our provider router since the founding of OpenRouter.
Before, we prioritized mostly based on price. The new router now rewards the best quality inference for the actual cost of a request, so requests stay cheap but are also fast and reliable.
Providers that deliver more value automatically win more traffic, so every provider has a reason to keep improving. And every time a provider gets better, so does your inference on OpenRouter.
Show more
Fewer tokens, same work. Particle-1 from @particle_api uses 28–52% fewer output tokens than DeepSeek V4.1 Flash across four coding benchmarks, per Particle. Now on OpenRouter.
Don't bet your company on just one source of intelligence when everyone else is using many.
Choose all kinds of brilliant
1 trillion tokens a day on @OpenRouter!!
We've announced OpenRouter's first major APAC partnership: KT Telecom, Korea's largest telecom company.
Around 80 media outlets took part. KT will become a provider of sovereign Korean models on OpenRouter. Launch will be anchored by KT Mi:dm K 3.0 Pro, Upstage Solar and Motif, with plans to expand 10-15 models in 2027.
OpenRouter will power KT's Token Factory, which will be available to KT's enterprise clients.
Show more
We have investigated this and have not found evidence of unauthorized access to our data, or validation of any of the claims in the post.
We will continue the investigation and monitor for any signs of abuse. If a leak is verified or abuse is detected we will take action and notify customers.
Show more
Top models being used on security tasks, by spend %: GLM 5.3 & Kimi K3
Grok 4.7 is the top closed-weight model
⚡ @OpenRouter tip #2#
Use ~anthropic/claude-opus-latest as your model on OpenRouter and you are always on the newest Opus. When the next one ships, your code picks it up with no change.
There are aliases like this for most model families. What a few point to today:
~anthropic/claude-opus-latest → Claude Opus 5.5
~openai/gpt-luna-latest → GPT-6 Luna
~google/gemini-flash-latest → Gemini 3.8 Flash
~moonshotai/kimi-latest → Kimi K3
Show more
Use the Security Center to manage security across all models:
- turn on key spend alerts 🔔
- remove unused keys
- set a periodic spend limit on uncapped keys
- set a max key lifetime on ALL keys
… and more!
Show more
Today we're launching the first-ever gateway Security Center.
@OpenRouter now lets you audit all your keys in one place, see which ones are safe to remove, browse keys by level of risk, and control an IP allowlist.
Show more
Flint from @Recursive_SI is now on OpenRouter!
Recursive's first model: an open-weight 40B MoE (~2.5B active) built for coding agents by their autoresearch system, the Eureka Machine. 262K context, reasoning and tool calling.
Recursive reports 54.9% on Terminal-Bench 2.1, 89.7% on SWE-bench Pro v2 and 74.2% on SWE-bench Verified.
Free to use at launch.
Try it now:
Show more
Introducing Flint, @Recursive_SI’s first model: a fast local coding model built with our automated research system, the Eureka Machine.
• Best-in-class fast local coding
• Up to 2x faster than comparable models: 125+ tokens/sec on a MacBook Pro, 150+ on RTX Spark
• Built from scratch in under 4 months
Private, unmetered intelligence on your own machine. Open weights available now on @huggingface, run it locally on your favorite framework or try it for free on @opencode or @pidotdev.
Show more
Cache rates across the AI landscape have gotten markedly better in 2026.
We saw an 85% median cache rate in agentic requests across OpenRouter last month, up from 65% in the beginning of the year. And the vast majority of providers now serve agentic cache at 70% or higher.
Show more
Agentic usage is up 34x since the start of February 2026.
Agentic usage is also now about 8x higher than human usage across OpenRouter on a weekly basis.
Mercury 3 is live on OpenRouter!
@_inception_ai's new diffusion model generates 1,000+ tok/s with 1M context, 4x more than Mercury 2.5. Inception reports it beats GPT-6 Luna and Haiku 5.5 on IFBench, GPQA Diamond, and SWE-Bench Atlas.
50% off at launch: $0.10/M in, $0.35/M out
Show more
Stealth model reveal 🐰
Space Bunny was OpenRouter’s #1# model for 10 straight days, processing 56.7T tokens! The most of any stealth model we’ve run.
Space Bunny hopped off OpenRouter on Oct 5. It's back today as @MiniMax_AI's M3.1 Flash, and it's free for the next 72 hours.
Show more
A few months ago, we built a self-improving security agent called Sentinel to help protect OpenRouter users. It runs 24/7 across all activity to look for activity anomalies, signs of end-user account takeover, user key theft, and more.
It continuously makes improvements based on signals from our trust and safety team, with a 0.05% action reversal rate (similar to false positive rate) this month. Anyone app can leverage its protection by implementing OpenRouter OAuth:
And if you want to be a part of real autoresearch in action, join us!
Show more
Gave my coding agent every frontier model on @OpenRouter and let a router pick the best one for each step.
Guess which model ended up doing most of the work
Today, we are launching OpenRouter Armor in beta.
Tool calls allow agents to interact with the world, and regex-based filtering often isn't enough to detect unwanted tool calls.
Armor uses @typesafeai's Jev model to guard against out of policy tool calls before your agent executes them, with better performance than Claude Code's auto classifier at a fraction of the cost.
Show more
We're live on OpenRouter with DeepSeek v4.1-1017
Clear improvements on agentic coding across the board
