OpenRouter ✓

@OpenRouter @typesafeai https://t.co/itOhpWE42K

0:08

2.4K views · 13 likes · 0 reposts · 0 replies Open on X →

Build something with Jev on OpenRouter and tag @jjacky. We are giving $20 in credits to the top 10 most creative and interesting projects. Read more at: https://t.co/mSiDo3K3O0 28.4K views · 109 likes · 5 reposts · 3 replies Open on X →

Jev tells you how sure it is. Ask which queue a ticket belongs in and you get "billing 84%, technical 16%", not just "billing". And you can ask several questions about the same input in one call. 27.5K views · 89 likes · 1 reposts · 3 replies Open on X →

You ask in one of three shapes: 1. Noul: yes or no, returned as a probability. "Is this customer about to churn?" 2. Choice: one option from a set you define. "Which of these five queues does this go to?" 3. Score: a number on a scale you define. "How urgent is this, 1 to 5?" 130.3K views · 411 likes · 12 reposts · 6 replies Open on X →

The kind of jobs it is built for: - Route a support ticket to the right team - Decide if a message breaks your content rules - Flag which signups look like fraud - Choose the next step for an agent - Decide if a workflow should pause for a human And more 21.2K views · 192 likes · 2 reposts · 1 replies Open on X →

Jev is built for the decisions that software makes millions of times a day. Its pricing is also tuned for that: - $0.042 per million input tokens, output tokens free - Answers in 70 to 500 ms end to end - On TypeSafe's published workflows, up to 190x faster and 440x cheaper than 23.5K views · 181 likes · 3 reposts · 7 replies Open on X →

Jev by @typesafeai is now on OpenRouter, in beta. Jev is a System One model. Instead of generating text, it takes your app's state plus a typed question and returns a typed decision with a probability attached. There is no JSON prompting, parsing layer, and nothing to validate h

0:13

443.9K views · 3.3K likes · 237 reposts · 114 replies Open on X →

@OpenRouter @unionalphaai Bro 256k Context in big 2026 is a crime 😭 https://t.co/PdvhyMcPXe 9.9K views · 72 likes · 2 reposts · 7 replies Open on X →

"256K Context" https://t.co/Vu1YGou29v

0:02

12.5K views · 2 likes · 0 reposts · 1 replies Open on X →

Notes for this stealth model: 💰 It is free 🔑 This time, the provider does not train on your prompts or completions 34.8K views · 277 likes · 4 reposts · 8 replies Open on X →

🥷 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: https://t.co/SZbdoGOkdb 1M views · 2.7K likes · 192 reposts · 226 replies Open on X →

OpenRouter ✓@OpenRouter3 Sep

Join us for In Production, a new series showcasing what companies are actually building and shipping with AI. Founders from @olam_labs, @browser_use, and @userlens_hq will demo what they’re building, share lessons from production, and unpack the models powering their products ht 7.8K views · 36 likes · 5 reposts · 7 replies Open on X →

OpenRouter ✓@OpenRouter3 Sep

Microsoft MAI-Transcribe 2 is live on OpenRouter! Ranked #1 on FLEURS, it supports speech-to-text across 60 languages with automatic language ID, code switching, speaker diarization, and word-level timestamps. Use it now: https://t.co/CoFRrkruw5 18.6K views · 199 likes · 6 reposts · 13 replies Open on X →

OpenRouter ✓@OpenRouter3 Sep

Introducing video benchmarks: compare video models side by side, on a variety of challenges. Seedance 2.5 excels at physics and prompt adherence. The newly released MiniMax H3 Max is setting a new bar on speed and cost. https://t.co/nmhN9b98yp https://t.co/mxC1YGb3sF 33.4K views · 282 likes · 16 reposts · 15 replies Open on X →

Muse Spark 1.3 is now available on OpenRouter! Built for long-running agentic, multi-agent, and coding workflows. It tracks what it learns, handles conflicting inputs, and asks for clarification or confirmation when needed. Use it now: https://t.co/vKNEn6KtVD 21.8K views · 367 likes · 15 reposts · 18 replies Open on X →

Intelligence, now served over ice ⚡️🧊 7.7K views · 27 likes · 1 reposts · 2 replies Open on X →

@GoogleDeepMind Gemini 3.8 Flash also supports agentic video processing. Set processing: "agentic" on the video part and the model navigates the timeline itself instead of sampling every frame at a fixed rate. Works on earlier Gemini Flash models too. Learn more in our docs: 3.3K views · 9 likes · 1 reposts · 0 replies Open on X →

what's your favorite drink? I know - Intelligence on Ice by @OpenRouter. (aka iced caramel latte, free OpenRouter credits inside) grab one today at @UseCorgi Cafe in SF or NY. post a pic for a shot at more credits + merch 💚 https://t.co/9jm95fS2UU 8.1K views · 33 likes · 2 reposts · 7 replies Open on X →

@OpenRouter @GoogleDeepMind Big upgrade. Gemini 3.8 Flash is looking seriously capable. 388 views · 1 likes · 0 reposts · 0 replies Open on X →

Gemini 3.8 Flash from @GoogleDeepMind is live on OpenRouter. At 3.7 Flash’s intro price, it beats its predecessor on every benchmark shown: coding, finance, legal, video, and science. Use it now: https://t.co/TQTNcIlfDW https://t.co/dR6UJZ2HQd 22.2K views · 415 likes · 33 reposts · 25 replies Open on X →

MiniMax H3 Max is now live on OpenRouter: faster and cheaper than H3. Same prompt, side by side: ready in ~30 seconds instead of ~3.5 minutes, and $0.40 for the clip instead of $0.65. https://t.co/PAFSqiFe28 17.4K views · 202 likes · 7 reposts · 10 replies Open on X →

OpenRouter ✓@OpenRouter1 Sep

@OpenRouter @_inception_ai @OpenRouter note that Celeris-1 now supports reasoning, and is faster than Mercury 2 according to public benchmarks https://t.co/kSnwuqZfgM

620 views · 18 likes · 1 reposts · 0 replies Open on X →

OpenRouter ✓@OpenRouter1 Sep

2/ Use it now: https://t.co/XhEeymoGbi 7.2K views · 52 likes · 2 reposts · 0 replies Open on X →

OpenRouter ✓@OpenRouter1 Sep

1/ The fastest reasoning LLM is now live exclusively on OpenRouter. Mercury 2.5 Preview from @_inception_ai reaches 1,107 tokens/sec through parallel token generation, with tunable reasoning, parallel tool calls, and schema-aligned JSON. Built for latency-sensitive workloads. h

0:06

97.2K views · 554 likes · 28 reposts · 46 replies Open on X →

@OpenRouter https://t.co/xd6Uwn0fpM

34.6K views · 395 likes · 7 reposts · 75 replies Open on X →

Elaboration on the headline figure: - Luna grew by 13.8x - Terra by 5.6x - Sol by 1.1x 9.2K views · 47 likes · 0 reposts · 0 replies Open on X →

More insights on the impact of these discounts in the full piece: https://t.co/9mjQz0zBgu 11K views · 26 likes · 1 reposts · 2 replies Open on X →

Importantly, many of the users with Terra/Luna usage during the discount window kept using the models after the discounts were retired. Overall tokens post-discount were actually higher on a daily average basis than during the window (mostly thanks to a few whales) https://t.co/

14.4K views · 64 likes · 0 reposts · 1 replies Open on X →

Some of the additional tokens were from older OpenAI models. But the bulk of the increase were net new tokens + stealing share from competitors. https://t.co/eAv21x5xHW

23.7K views · 96 likes · 0 reposts · 2 replies Open on X →