Travel Junkie. Analytics Addict. Fútbol Fanatic.
San Francisco, California
Joined November 2010
- Tweets665
- Following255
- Followers221
- Likes488
sasha blumenfeld retweeted
Companies & users spending $100+/mo on OpenRouter now use a median of 6 model families, double a year ago.
A thread & video on model neurodiversity, and why it's accelerating 👇
sasha blumenfeld retweeted
Our new routing algorithm dramatically raises the floor for inference on open-weight models.
Early head-to-head results vs. the old router:
~20% faster time to first token
~20% higher throughput
~40% fewer fallbacks
~60% fewer rate-limit errors
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.
sasha blumenfeld retweeted
ElevenLabs x OpenRouter: Live-casting an LLM Battle Royale xitter.gq/i/broadcasts/1qKVmydgw…
Proud to work at OpenRouter. Now more than ever we need many voices, perspectives, and intelligence.
The future is multi-model.
The biggest lie in AI is that the future belongs to one winner.
Every technology wave starts with one company promising that one walled garden is all you'll ever need. And every time, market forces and creativity break the walls down.
I cofounded OpenSea and now OpenRouter around the opposite bet: humanity will refuse to be locked in.
Intelligence was never meant to belong to one lab, one model, or one gatekeeper.
The future of AI is open, plural, and yours to choose.
sasha blumenfeld retweeted
The biggest lie in AI is that the future belongs to one winner.
Every technology wave starts with one company promising that one walled garden is all you'll ever need. And every time, market forces and creativity break the walls down.
I cofounded OpenSea and now OpenRouter around the opposite bet: humanity will refuse to be locked in.
Intelligence was never meant to belong to one lab, one model, or one gatekeeper.
The future of AI is open, plural, and yours to choose.
sasha blumenfeld retweeted
Reminder to check our Security Center to audit your API keys.
The AI platform hacks around the internet yesterday were mostly targeting LLM API keys, which have liquid black markets that been developing for years.
Startups storing crypto wallet keys will also be at risk.
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.
Don’t know what I’m more happy about..getting to work with @Codydearkland again, or that @Railway agents just got more models to pick from. ✨✨
We're adding @OpenRouter support to Priority Boarding users in Railway
@OpenRouter lets you access wider models for all things agent, whether its our harness in a Cloud Agent, or our bots. Models like @grok 4.7, @Muse Spark 1.3 and more
What models do you want next?
Huge. Go try it out 🏃♀️
ElevenLabs is officially on OpenRouter.
You can now call 9 Text to Speech models, with up to 90+ languages, and 2 Speech to Text models with speaker labels and word-level timestamps.
All @ElevenLabs models are 50% off, only on OpenRouter, through October 19, 8am PT.
sasha blumenfeld retweeted
ElevenLabs is officially on OpenRouter.
You can now call 9 Text to Speech models, with up to 90+ languages, and 2 Speech to Text models with speaker labels and word-level timestamps.
All @ElevenLabs models are 50% off, only on OpenRouter, through October 19, 8am PT.
sasha blumenfeld retweeted
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.
sasha blumenfeld retweeted
What is a decision model?
Jev by @typesafeai answers yes/no and multiple-choice questions, with a confidence score. Much of software development are a sequence of decisions, and Jev is 10x cheaper and faster than an LLM.
Let’s understand this through practical examples:
sasha blumenfeld retweeted
Here's the DeepSWE result for Union Alpha, a stealth model we just launched.
Try it now! Works in every harness.
$ ori [code | your-fav-harness] --model=stealth/union-alpha
🥷 New stealth model: Union Alpha (@unionalphaai)
A multimodal model for research, coding, and agentic workflows.
- Free to use
- 256K context
- Tool calling
- Frontier-level general-purpose performance
Try it now and share your feedback:
openrouter.ai/stealth/union-…
sasha blumenfeld retweeted
Code mode's having a moment (some more litigiously than others). We're building it into Seer @sentry. It's faster, cheaper & acts for you.
Pointed it at 54 JS issues → triaged them all, clustered dupes, archived the 20 noisy ones with a comment each. Shipping soon 😇
sasha blumenfeld retweeted
Every app has a long tail of bugs. Seer is quietly clearing them from the @sentry CLI — 11 last week.
First to fall: sentry alert issues view crashed with a TypeError when a rule had no conditions. Seer shipped the guard.
→ github.com/getsentry/cli/pul…
![fix(alert): Handle missing conditions/actions in issue alert view by sentry[bot] · Pull Request...](https://pbs.twimg.com/card_img/2118193419570835456/UOGwG4SU?format=jpg&name=800x419)
sasha blumenfeld retweeted
I really wanted to add Ghostty from @mitchellh for long time in AgentHub, I finally had some time to do it!
sasha blumenfeld retweeted
Finally enabled Sentry + Cursor automation last night. Woke up this morning to around 30 PRs to review, but once I get through this initial wave of error log noise, the implications are pretty incredible; a fully self-debugging and self-healing application.
sasha blumenfeld retweeted
Really happy to finally share AgentHub 2.0! 🚀
This is a big update and by far the biggest release yet.
It includes:
- Claude Code + Codex in one native macOS app
- cmux-like session management with multiple panels
- Worktrees
- GitHub context
- MCP Apps
- Embedded iOS simulators
- Design mode
And much more, available for free and OSS here lnkd.in/gu2uQPB2
sasha blumenfeld retweeted
new short story just dropped 👇
and all we had to do was click merge
We just shipped a new issue type at @getsentry: AI-detected low-value spans. Here's what happened when we ran it on our own infrastructure (and how Seer fixed it and saved us ~$10k/year) 🧵
sasha blumenfeld retweeted
We just shipped a new issue type and it already saved us $10k/year in our own infrastructure 👀
Check out our new video from @TechSquidTV to learn more