OpenRouter(@OpenRouterAI)

FLUX Video Edit from @bfl_ai is live on OpenRouter. Send a clip and a sentence: remove or replace o...

OpenRouter (@OpenRouter) — Fri, 11 Sep 2026 16:01:00 GMT

FLUX Video Edit from @bfl_ai is live on OpenRouter.

Send a clip and a sentence: remove or replace objects and characters, swap the setting, restyle it, or translate the dialogue with matched lip sync. No masks, no per-frame controls.

openrouter.ai/black-forest-l…

💬5🔄2❤️11👀4156📊6

Ling 3.0 Flash VL extends Ling 3.0 Flash from InclusionAI: stronger language performance, plus nativ...

OpenRouter (@OpenRouter) — Fri, 11 Sep 2026 13:04:52 GMT

Ling 3.0 Flash VL extends Ling 3.0 Flash from InclusionAI: stronger language performance, plus native visual perception and advanced visual agent capabilities.

💬0🔄0❤️4👀2325📊1

Ling 3.0 Flash VL is live on OpenRouter, served by @novita_labs. A 124B MoE with 5.5B active params...

OpenRouter (@OpenRouter) — Fri, 11 Sep 2026 13:04:49 GMT

Ling 3.0 Flash VL is live on OpenRouter, served by @novita_labs.

A 124B MoE with 5.5B active params, now with native image and video input plus visual agent capabilities. Hybrid instant and reasoning modes, with tool calling.

openrouter.ai/inclusionai/li…

💬11🔄12❤️80👀9179📊21

Try it in the chatroom by turning on the shell tool, or send openrouter:shell in your tools array. ...

OpenRouter (@OpenRouter) — Thu, 10 Sep 2026 14:58:17 GMT

Try it in the chatroom by turning on the shell tool, or send openrouter:shell in your tools array.

Read more at: openrouter.ai/blog/announcem…

💬0🔄0❤️3👀2076📊1

Pricing is designed to keep tracking simple by billing the computer entirely within the request. It...

OpenRouter (@OpenRouter) — Thu, 10 Sep 2026 14:58:14 GMT

Pricing is designed to keep tracking simple by billing the computer entirely within the request.

It's $0.0001 per active second, inclusive of file usage, with a 30-second minimum for cold container starts.

💬1🔄0❤️4👀2086📊2

New stateful server tool: Shell! Any model on OpenRouter can now run commands in a hosted Linux con...

OpenRouter (@OpenRouter) — Thu, 10 Sep 2026 14:58:05 GMT

New stateful server tool: Shell!

Any model on OpenRouter can now run commands in a hosted Linux container and use the new Files API to move files in and out. Available today in beta: `openrouter:shell`

Your browser does not support the video tag.

💬15🔄12❤️98👀20000📊29

5/ Get started: $ curl -fsSL https://t.co/vROsUW01Hr | bash $ ori <your favorite harness> Re...

OpenRouter (@OpenRouter) — Wed, 09 Sep 2026 19:10:16 GMT

5/ Get started:

$ curl -fsSL openrouter.ai/labs/ori/insta… | bash
$ ori <your favorite harness>

Read more at: https://t.co/Cr9rVTSoV9

💬2🔄0❤️1👀2418📊2

4/ Your existing Cline and Kilo config is left alone. Every request runs on your OpenRouter key with...

OpenRouter (@OpenRouter) — Wed, 09 Sep 2026 19:10:13 GMT

4/ Your existing Cline and Kilo config is left alone. Every request runs on your OpenRouter key with your org guardrails and one bill.

💬1🔄0❤️1👀2429📊1

1/ Four more Ori harnesses: @cline, @kilocode, #ohmypi, and @Muse Code now run on OpenRouter. $ ori...

OpenRouter (@OpenRouter) — Wed, 09 Sep 2026 19:10:04 GMT

1/ Four more Ori harnesses: @cline, @kilocode, #ohmypi, and @Muse Code now run on OpenRouter.

$ ori cline
$ ori kilo
$ ori omp
$ ori muse

Your browser does not support the video tag.

💬15🔄6❤️69👀15399📊23

In-Region Routing is available on Business and Enterprise plans Region can also be enforced per wor...

OpenRouter (@OpenRouter) — Wed, 09 Sep 2026 14:57:27 GMT

In-Region Routing is available on Business and Enterprise plans

Region can also be enforced per workspace, team, or API key with Guardrails. Full details: openrouter.ai/blog/announcem…

💬0🔄0❤️5👀2038📊1

This also opens up Chinese open-weight models for teams with data residency requirements. Examples:...

OpenRouter (@OpenRouter) — Wed, 09 Sep 2026 14:57:26 GMT

This also opens up Chinese open-weight models for teams with data residency requirements.

Examples: DeepSeek V4 Pro, Kimi K3, and GLM 5.2 are served from US data centers by @baseten, @FireworksAI_HQ, and @Azure. GLM 5.2 is also available in the EU via @MistralAI.

💬1🔄0❤️8👀2094📊2

US In-Region Routing is now generally available, alongside EU routing. Requests to https://t.co/Qe4...

OpenRouter (@OpenRouter) — Wed, 09 Sep 2026 14:57:25 GMT

US In-Region Routing is now generally available, alongside EU routing.

Requests to us.openrouter.ai are decrypted inside the US and processed there at every step, from TLS termination to the provider!

eu.openrouter.ai does the same for the EU

💬12🔄10❤️130👀20141📊27

Start generating through the Images API today: https://t.co/o2VCkW7azQ

OpenRouter (@OpenRouter) — Wed, 09 Sep 2026 01:55:40 GMT

Start generating through the Images API today:
openrouter.ai/docs/guides/ov…

💬1🔄0❤️4👀2741📊2

GPT Image 2.5 Sunburst brings extra precision and tighter control across edits, with longer generati...

OpenRouter (@OpenRouter) — Wed, 09 Sep 2026 01:55:37 GMT

GPT Image 2.5 Sunburst brings extra precision and tighter control across edits, with longer generation times. Built for production-ready campaign creative and polished product imagery.

openrouter.ai/openai/gpt-ima…

💬1🔄0❤️6👀3215📊2

GPT Image 2.5 Flare is the default for most work. Built for creator and social content, product expe...

OpenRouter (@OpenRouter) — Wed, 09 Sep 2026 01:55:33 GMT

GPT Image 2.5 Flare is the default for most work. Built for creator and social content, product experiences, visual search, rapid prototyping, and high-volume generation.

openrouter.ai/openai/gpt-ima…

💬2🔄0❤️6👀1514📊3

GPT Image 2.5 is live on OpenRouter, in two models from @OpenAI. It brings sharper detail, more fai...

OpenRouter (@OpenRouter) — Wed, 09 Sep 2026 01:55:28 GMT

GPT Image 2.5 is live on OpenRouter, in two models from @OpenAI.

It brings sharper detail, more faithful reference photos, and up to 50% lower latency than GPT Image 2.

Your browser does not support the video tag.

💬14🔄6❤️75👀10750📊22

Nex-N2.5-Mini: the lighter of the two, text only, with the same tool calling and reasoning effort co...

OpenRouter (@OpenRouter) — Tue, 08 Sep 2026 21:00:33 GMT

Nex-N2.5-Mini: the lighter of the two, text only, with the same tool calling and reasoning effort controls.

openrouter.ai/nex-agi/nex-n2…

💬0🔄0❤️5👀2728📊1

Nex-N2.5-Pro: takes text and image input, so the visual feedback loop runs through the API. https:/...

OpenRouter (@OpenRouter) — Tue, 08 Sep 2026 21:00:30 GMT

Nex-N2.5-Pro: takes text and image input, so the visual feedback loop runs through the API.

openrouter.ai/nex-agi/nex-n2…

💬1🔄0❤️10👀3379📊3

Nex AGI's agentic N2.5 family is live on OpenRouter: Nex-N2.5-Pro and Nex-N2.5-Mini. Both are built...

OpenRouter (@OpenRouter) — Tue, 08 Sep 2026 21:00:27 GMT

Nex AGI's agentic N2.5 family is live on OpenRouter: Nex-N2.5-Pro and Nex-N2.5-Mini.

Both are built to turn goals into working, verified outcomes, with agentic coding as the core strength. Tool calling and adjustable reasoning effort on both.

Free for a limited time ↓

openrouter.ai/nex-agi

💬19🔄7❤️107👀11010📊29

Inception cut the price at GA: $0.04 per million input tokens and $0.15 per million output. That's 5...

OpenRouter (@OpenRouter) — Tue, 08 Sep 2026 19:21:50 GMT

Inception cut the price at GA: $0.04 per million input tokens and $0.15 per million output. That's 5x below the preview price, and 6x below Mercury 2 on input.

It's now the least expensive model in the top 10 of that leaderboard, with roughly 2x the context of Mercury 2.

260K context, tool calling, structured outputs, and configurable reasoning effort.

💬0🔄0❤️8👀2806📊1

Mercury 2.5 from @_inception_ai is now generally available on OpenRouter. It's the fastest model on...

OpenRouter (@OpenRouter) — Tue, 08 Sep 2026 19:21:47 GMT

Mercury 2.5 from @_inception_ai is now generally available on OpenRouter.

It's the fastest model on our Fastest Models leaderboard that doesn't require specialized hardware.

A diffusion LLM: it decodes tokens in parallel rather than one at a time. The gain is largest on code-heavy prompts.

Use it here: openrouter.ai/inception/merc…

💬15🔄24❤️168👀12434📊36

Omarchy is the first operating system built from the ground up for agents. Omarchy is using OpenRou...

OpenRouter (@OpenRouter) — Mon, 07 Sep 2026 20:55:32 GMT

Omarchy is the first operating system built from the ground up for agents.

Omarchy is using OpenRouter to route all sponsored tokens.

DHH@dhh

The Omacom Foundation has raised another half a million dollars! Thanks so much to @OpenRouter, @PayWithFour, and 500 awesome individual patrons 🙏 

That brings our total in pledges and donations to approximately $15.5 million.
omarchy.org/news/2026/09/o…p

💬25🔄46❤️1496👀86758📊138

Are you joining us? 👀

OpenRouter (@OpenRouter) — Fri, 04 Sep 2026 22:35:43 GMT

Are you joining us? 👀

Katie Kirsch@katiekirsch

our @a16z team is co-hosting an event with @OpenRouter in SF on sep 18th!

"the new model dilemma: switch or stay?"

it's a lunch & learn for founders and technical leaders building with AI

featuring openrouter's head of data & analytics, and head of finance & bizops

space is limited; RSVP here! luma.com/openro-kcis

💬2🔄1❤️26👀13311📊3

MAI-Image-2.6-Flash: comparable quality for fast, high-volume production at less than half the flags...

OpenRouter (@OpenRouter) — Fri, 04 Sep 2026 22:00:14 GMT

MAI-Image-2.6-Flash: comparable quality for fast, high-volume production at less than half the flagship price. Microsoft reports 2.8x faster generation than GPT-Image-2-Medium.

openrouter.ai/microsoft/mai-…

💬1🔄1❤️6👀3358📊2

MAI-Image-2.6: built for high-quality generation and precise, controllable editing. Microsoft report...

OpenRouter (@OpenRouter) — Fri, 04 Sep 2026 22:00:11 GMT

MAI-Image-2.6: built for high-quality generation and precise, controllable editing. Microsoft reports #2 on Arena for both text-to-image and editing, plus #1 for editing on Artificial Analysis.

openrouter.ai/microsoft/mai-…

💬1🔄0❤️6👀4870📊3

Microsoft's strongest image model yet is now on OpenRouter, with a faster production variant from @M...

OpenRouter (@OpenRouter) — Fri, 04 Sep 2026 22:00:08 GMT

Microsoft's strongest image model yet is now on OpenRouter, with a faster production variant from @MicrosoftAI.

MAI-Image-2.6 and 2.6-Flash support multi-image editing, web grounding, dynamic aspect ratios, and up to 1.5K output. More below ↓

openrouter.ai/microsoft

💬7🔄6❤️84👀12121📊17

And read our model guide to make the most out of Astra: https://t.co/aiGIxzRIHB

OpenRouter (@OpenRouter) — Fri, 04 Sep 2026 20:27:19 GMT

And read our model guide to make the most out of Astra: openrouter.ai/docs/cookbook/…

💬1🔄0❤️10👀3490📊3

Read from OpenAI: https://t.co/VyPo9jOX1d

OpenRouter (@OpenRouter) — Fri, 04 Sep 2026 20:27:16 GMT

Read from OpenAI: openai.com/index/gpt-6-as…

💬2🔄0❤️12👀4666📊3

GPT-6 Astra is live now on OpenRouter! Reaction from internal testing: "It's incredibly steerable, ...

OpenRouter (@OpenRouter) — Fri, 04 Sep 2026 20:27:13 GMT

GPT-6 Astra is live now on OpenRouter!

Reaction from internal testing: "It's incredibly steerable, you can mold it to be whatever you want. A very different experience from any other model. It's like truly Personalized Intelligence"

Use it now: openrouter.ai/openai/gpt-6-a…

💬25🔄26❤️295👀22345📊56

Excited to host the first edition with @CapitalG at their beautiful SF office. Spots are limited....

OpenRouter (@OpenRouter) — Thu, 03 Sep 2026 16:58:26 GMT

Excited to host the first edition with @CapitalG at their beautiful SF office.  

Spots are limited. Request yours: luma.com/openro-8qy3

💬0🔄0❤️4👀4479📊1

Join us for In Production, a new series showcasing what companies are actually building and shipping...

OpenRouter (@OpenRouter) — Thu, 03 Sep 2026 16:58:25 GMT

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 and where OpenRouter fits into their stack.

Plus, our @alexatallah will demo OpenRouter live. Bring your spiciest questions!

💬7🔄6❤️47👀12260📊14

Microsoft MAI-Transcribe 2 is live on OpenRouter! Ranked #1 on FLEURS, it supports speech-to-text a...

OpenRouter (@OpenRouter) — Thu, 03 Sep 2026 14:43:18 GMT

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: openrouter.ai/microsoft/mai-…

💬20🔄21❤️505👀128722📊134

Generate your own prompts and compare across cost and generation time. https://t.co/ws0aB9Yicb

OpenRouter (@OpenRouter) — Thu, 03 Sep 2026 13:00:44 GMT

Generate your own prompts and compare across cost and generation time.

openrouter.ai/benchmarks/med…

💬0🔄1❤️5👀3740📊1

Prompt: "a fixed side-on shot of exactly eight upright black dominoes in a straight evenly spaced ro...

OpenRouter (@OpenRouter) — Thu, 03 Sep 2026 13:00:39 GMT

Prompt: "a fixed side-on shot of exactly eight upright black dominoes in a straight evenly spaced row on a white surface. The leftmost domino tips right and the whole row falls in a single left-to-right chain until all eight are flat."

Your browser does not support the video tag.

💬4🔄0❤️14👀5206📊5

Introducing video benchmarks: compare video models side by side, on a variety of challenges. Seedan...

OpenRouter (@OpenRouter) — Thu, 03 Sep 2026 13:00:31 GMT

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.

openrouter.ai/benchmarks/med…

Your browser does not support the video tag.

💬22🔄20❤️378👀51772📊69

Muse Spark 1.3 is now available on OpenRouter! Built for long-running agentic, multi-agent, and cod...

OpenRouter (@OpenRouter) — Wed, 02 Sep 2026 20:03:35 GMT

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: openrouter.ai/meta/muse-spar…

💬18🔄16❤️373👀23824📊54

Muse Spark 1.3 Contributor is also live, and is the cost-efficient tier. Use it now: https://t.co/R...

OpenRouter (@OpenRouter) — Wed, 02 Sep 2026 20:03:35 GMT

Muse Spark 1.3 Contributor is also live, and is the cost-efficient tier.

Use it now: openrouter.ai/meta/muse-spar…

💬1🔄1❤️29👀5168📊4

Muse Spark 1.3 Contributor is the cost-efficient tier. Use it now: https://t.co/R4yVY7wgdU

OpenRouter (@OpenRouter) — Wed, 02 Sep 2026 19:57:01 GMT

Muse Spark 1.3 Contributor is the cost-efficient tier.

Use it now: openrouter.ai/meta/muse-spar…

💬0🔄0❤️2👀312

The updated Muse Spark 1.3 is now available on OpenRouter. Built for long-running agentic, multi-ag...

OpenRouter (@OpenRouter) — Wed, 02 Sep 2026 19:56:58 GMT

The updated 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.

openrouter.ai/meta/muse-spar…

💬1🔄1❤️13👀1166📊2

Intelligence, now served over ice ⚡️🧊

OpenRouter (@OpenRouter) — Wed, 02 Sep 2026 17:15:50 GMT

Intelligence, now served over ice ⚡️🧊

Dasha@dasha_shunina

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 💚

💬3🔄1❤️42👀12629📊6

Gemini 3.8 Flash also supports agentic video processing. Set processing: "agentic" on the video par...

OpenRouter (@OpenRouter) — Wed, 02 Sep 2026 16:28:33 GMT

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: openrouter.ai/docs/guides/ov…

💬0🔄1❤️10👀3697📊2

Gemini 3.8 Flash from @GoogleDeepMind is live on OpenRouter. At 3.7 Flash’s intro price, it beats i...

OpenRouter (@OpenRouter) — Wed, 02 Sep 2026 15:56:03 GMT

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: openrouter.ai/google/gemini-…

💬25🔄34❤️419👀23687📊71

Get started with MiniMax H3 Max today. https://t.co/l9UzyOyWKy

OpenRouter (@OpenRouter) — Wed, 02 Sep 2026 15:33:03 GMT

Get started with MiniMax H3 Max today.

openrouter.ai/docs/guides/ov…

💬0🔄0❤️9👀3232📊1

Text-to-video, or start from a single keyframe. Clips of 5 to 15 seconds, 480p at $0.05/second and ...

OpenRouter (@OpenRouter) — Wed, 02 Sep 2026 15:33:00 GMT

Text-to-video, or start from a single keyframe.

Clips of 5 to 15 seconds, 480p at $0.05/second and 768p at $0.08, in six aspect ratios from 21:9 to 9:16.

openrouter.ai/minimax/hailuo…

💬2🔄0❤️17👀4037📊4

MiniMax H3 Max is now live on OpenRouter: faster and cheaper than H3. Same prompt, side by side: re...

OpenRouter (@OpenRouter) — Wed, 02 Sep 2026 15:32:58 GMT

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.

Your browser does not support the video tag.

💬15🔄14❤️328👀28349📊57

Apply here: https://t.co/vDHHnmaCGy Share proof of exceptionality and creativity: communities you'v...

OpenRouter (@OpenRouter) — Tue, 01 Sep 2026 20:05:33 GMT

Apply here: jobs.ashbyhq.com/openrouter/44e…

Share proof of exceptionality and creativity: communities you've built, events you've run, things you made that people loved.

💬1🔄0❤️6👀3656📊2

We're hiring a Community Lead. Our Discord has 60k+ members and is one of the most active AI commun...

OpenRouter (@OpenRouter) — Tue, 01 Sep 2026 20:05:30 GMT

We're hiring a Community Lead.

Our Discord has 60k+ members and is one of the most active AI communities anywhere. We're looking for its primary steward: run events and challenges, build our mod and ambassador programs, and bring what the community cares about back to the team.

jacky@jjacky

we're hiring a community lead at openrouter!!!!! 

this is the role we needed a year ago

here's what we're looking for and why you should be excited about it! 

link to apply: jobs.ashbyhq.com/openrouter/44e…

🧵

Your browser does not support the video tag.

💬15🔄4❤️87👀15840📊19

On pricing: Fable 5.1 keeps Fable 5 pricing at $10/M input tokens and $50/M output tokens. Prompt c...

OpenRouter (@OpenRouter) — Tue, 01 Sep 2026 18:29:03 GMT

On pricing: Fable 5.1 keeps Fable 5 pricing at $10/M input tokens and $50/M output tokens.

Prompt cache reads drop to $0.25/M tokens, 75% below the old cache-read rate.

Read more:

Claude@claudeai

We’re introducing Claude Fable 5.1 and Claude Mythos 5.1.

They're the world’s most advanced models for coding and knowledge work.

Your browser does not support the video tag.

💬3🔄0❤️19👀5305📊4