The unified interface for LLMs. 400+ models (incl. 50+ free), the best prices, explorable data, private chat, & a unified API. openrouter.ai/discord
- Tweets 5,696
- Following 386
- Followers 151,712
- Likes 5,948
Pinned Tweet
Introducing typesafe/jev-router: a cache-aware model router powered by Jev and @typesafeai
The Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost.
Here's how it works 👇🏻
111
154
2,083
1,320,019
.@OpenRouter co-founder Alex Atallah, in his first podcast since Stripe acquired the company, joins @Replit co-founder Amjad Masad and a16z's Erik Torenberg on why the future of AI is independence and specialization.
In this conversation, Alex walks through how the Stripe deal unfolded, why he wasn't originally looking to sell, and why "payments and inference are going to blend together."
Pre-OpenRouter, the typical AI workflow had one model provider to choose from, and little pressure on that provider to lower prices. Now enterprises are diversifying across labs and open-weight models, and every board is asking about AI costs and benchmarks.
Amjad argues if your company depends on one AI lab, it can turn into your competitor. So Replit is building the layer that lets enterprises use any model and any cloud, without being locked into either.
Alex and Amjad are split on personal agents – Amjad runs one agent across his whole company and loves the cross-domain joins, while Alex says general agents cause you to sacrifice understanding, and argues 10 specialized chiefs of staff beats one superagent.
0:45 How the Stripe deal unfolded
5:05 Why mixing models beats one model
7:25 Forcing the labs to compete on price
8:50 Enterprises want open-weight models
10:30 Every board asks about AI every month
12:25 Why companies must own their intelligence
14:15 Replit as the independence layer
15:10 Everyone is building the same agent
16:35 Why Amjad built bring-your-own-cloud
18:10 Amjad's agent that runs his whole company
19:55 Why 10 specialized agents beat one
23:35 Machines, not humans, should specialize
27:30 Guardrails for agents talking to agents
31:10 Models training their own replacements
33:45 Most tasks don't need a frontier model
40:50 Training small models on Qwen 8B
43:25 The Rust cycle is coming for AI
45:10 Fusion models: frontier quality at half the cost
YouTube: piped.video/ekK8urKHPMQ
@alexatallah @OpenRouter @amasad @eriktorenberg
32
43
427
483,704
New: Model Router Benchmarks
Compare 7 routers side by side on quality, speed, and cost across 6 benchmarks. Use them now, including Jev Router, Unbiased Pareto, NVIDIA Switchyard, and more.
openrouter.ai/benchmarks/rou…
18
15
199
30,497
We present a Router Index score per benchmark, weighted 60% quality, 20% time per task, and 20% cost.
You can drag a slider on the page to change the weights to find the leaders that fit your priorities.
1
3
3,159
Learn more about the different types of routers and why we're doing this on our blog: openrouter.ai/blog/announcem…
5
3,170
Tip: quickly access all your recent AI sessions across all agents and, of course, all models
Right from the profile dropdown 👇 openrouter.ai/logs?tab=sessi…
20
3
74
9,658
Seedream 5.0 Flash from @ByteDanceSeed_ is now live on OpenRouter
The fast, cost-efficient tier of Seedream 5.0, built for high-volume generation and interactive editing at low latency
openrouter.ai/bytedance-seed…
20
1
95
13,827
FLUX 3 Image from @bfl_ai is now live on OpenRouter
Black Forest Labs' new flagship image model: text-to-image and multi-reference editing, rendered natively up to 4K
Introducing FLUX 3 Image.
Control every pixel.
Make precise multi-turn edits without changing any other pixel.
Lay out the image exactly how you want using bounding boxes.
Generate in up to 4K to preserve details.
Use up to 10 references to compose an image.
Commercial Weights available for companies running image generation at scale.
Open Weights version of FLUX 3 Image is launching in the coming weeks.
20
5
109
13,238
Give it up to 10 reference images and describe the scene in one prompt. FLUX 3 decides where each one goes and renders the whole frame together.
1
3
2,800
Pick an aspect ratio anywhere from 21:9 to 9:21, or use auto, at 768, 1K, 1.5K, 2K or 4K.
See more:
openrouter.ai/black-forest-l…
1
2,341
D1 from @liquidai is live on OpenRouter.
It's a competitive decision model: send your app's state and yes/no, choice, or score questions, and get back typed answers with a probability for every option. Zero data retention.
$0.04/M input, $0 output, 65K context
openrouter.ai/liquid/d1
24
24
227
33,748
We audited our own OpenRouter account and found 1,000+ active API keys for 85 employees. Many hadn’t been used in months. 🫣
So we built the Security Center. It shows every key across your workspaces and flags which ones are risky and why. You can disable, archive, or cap up to 500 at once.
32
12
487
37,011
The key safety tab let's you see all your API keys across workspaces. Filter by risk, owner, or inactivity. You can set limits on keys, disable them, or archive them one at a time or in bulk.
1
1
8
2,713
MAI-Voice-2.1 from @MicrosoftAI is live on OpenRouter.
MAI's highest-fidelity, most expressive text-to-speech model yet:
• Studio-grade, natural speech.
• Same voice can speak in 23 languages while maintaining native accent.
• $22 per 1M characters
Built for audiobooks, podcasts, narration, and brand audio.
openrouter.ai/microsoft/mai-…
16
3
82
15,100