OpenRouter

4.8K posts

OpenRouter banner
OpenRouter

OpenRouter

@OpenRouter

Discover and use the latest LLMs. 500+ models (incl. 50+ free), explorable data, private chat, & a unified API. https://t.co/qJG5mKrigL

参加日 Temmuz 2023
374 フォロー中100.6K フォロワー
固定されたツイート
OpenRouter
OpenRouter@OpenRouter·
Today we’re announcing our $113M Series B led by @CapitalGVC. Over the last 6 months, weekly volume on OpenRouter grew from 5T to 25T tokens as AI rapidly shifts from experimentation into production. We’re excited for what comes next.
OpenRouter tweet media
English
154
148
2.6K
346.9K
OpenRouter
OpenRouter@OpenRouter·
Now you can use your OpenRouter models directly inside @ComfyUI workflows!
ComfyUI@ComfyUI

ComfyUI just added @OpenRouter support. Instead of being locked into a single LLM, you can now access 20+ models directly inside Comfy. More flexibility, less friction, same workflow. Links to the workflows below👇

English
7
12
120
10.9K
OpenRouter
OpenRouter@OpenRouter·
OpenAI models stream the diff incrementally via delta events. All other models return the complete patch as a single output. You can control the behavior with the `engine` parameter: auto (default), native, or openrouter Your app receives a clean, structured patch to apply, and reports back on the next turn. Docs: openrouter.ai/docs/guides/fe…
English
0
0
8
2.6K
OpenRouter
OpenRouter@OpenRouter·
OpenRouter now supports "apply_patch," a server tool that lets any model propose file edits using V4A diffs through the Responses API. The model generates a patch (create, update, or delete a file). OpenRouter validates the diff syntax server-side.
OpenRouter tweet media
English
10
5
143
12.7K
OpenRouter
OpenRouter@OpenRouter·
Read more in @StepFun_ai’s launch post:
StepFun@StepFun_ai

⚡️ Step 3.7 Flash is here: The new frontier is agent efficiency. #1 ClawEval-1.1 (67.1), #1 SimpleVQA Search (79.2), #2 SWE-PRO (56.3), 95.3 on V* Python. Open weights under Apache 2.0. Built for agentic, coding, search, and multimodal workflows — balancing speed, cost, and reliable execution. - 400 TPS. 198B sparse MoE, ~11B active. 256K context, 3 reasoning levels. - Understands UIs, charts, docs, images — then writes code or calls tools to act on what it sees. - Web + visual search reaches further: more sources, deeper follow-up. - Reliable tool use — less drift, fewer broken toolcalls. 98%+ on τ²-bench across all difficulty levels. - Works with Claude Code, KiloCode, Hermes Agent, OpenClaw, and protocols like MCP. - Runs locally on Mac Studio M4 Max, DGX Spark, AMD AI Max+ 395. GitHub: github.com/stepfun-ai/Ste… HuggingFace: huggingface.co/stepfun-ai/Ste… GGUF: huggingface.co/stepfun-ai/Ste… ModelScope: modelscope.cn/models/stepfun… API: platform.stepfun.ai Blog: static.stepfun.com/blog/step-3.7-…

English
0
0
3
8.3K
OpenRouter
OpenRouter@OpenRouter·
Step 3.7 Flash from @StepFun_ai is live on OpenRouter. A multimodal (image/video/text) MoE that activates just 11B of 196B params. Tuned for coding, agentic workflows, and structured outputs, with selectable reasoning levels to trade off speed, cost, and depth.
OpenRouter tweet media
English
8
11
314
23.2K
OpenRouter
OpenRouter@OpenRouter·
Today we’re announcing our $113M Series B led by @CapitalGVC. Over the last 6 months, weekly volume on OpenRouter grew from 5T to 25T tokens as AI rapidly shifts from experimentation into production. We’re excited for what comes next.
OpenRouter tweet media
English
154
148
2.6K
346.9K
OpenRouter
OpenRouter@OpenRouter·
Opus 4.8 is live on OpenRouter! Same price as 4.7 with gains across agentic coding, reasoning, and computer use. Around 4x less likely than 4.7 to let code flaws pass unremarked. Opus 4.8 Fast Mode is also live - now only 2x the cost for 2.5x the speed.
OpenRouter tweet media
English
16
15
453
16.2K
OpenRouter
OpenRouter@OpenRouter·
TIP: You can use Flex and Priority tiers for supported models (OpenAI, Google Vertex, & more) Pricing available on each model page. Docs: openrouter.ai/docs/guides/fe…
OpenRouter tweet media
English
3
6
135
16.6K
OpenRouter がリツイート
Claire
Claire@cnorth_13·
If you’re burning a lot of money on Claude API tokens, use OpenRouter Fusion to find cheaper models to accomplish the same goal. I used it to save money on my own personalized Morning Brew agent. Now it’s only costing me $0.01 to run every day. Here’s what I did:
English
2
2
28
5.2K
OpenRouter がリツイート
Luckey Faraday
Luckey Faraday@luckeyfaraday·
Kimi K2.6 is free on @OpenRouter This is the best model for design after Opus 4.7 Take advantage of this
Luckey Faraday tweet media
English
3
10
156
9.6K
OpenRouter がリツイート
Cody Blakeney
Cody Blakeney@code_star·
I’ve become a huge fan of @OpenRouter very quickly. It really wouldn’t be possible to even consider testing or talking to all the models coming out recently without them. Frankly I’ve been surprised by just how useable so many of them have felt inside of coding harnesses.
English
11
4
98
12.8K
OpenRouter がリツイート
Alex Atallah
Alex Atallah@alexatallah·
A common example of the cost savings people realize when they switch to @OpenRouter
Alex Atallah tweet media
English
12
10
170
15.8K
Ronak Malde
Ronak Malde@rronak_·
Today, @MichaelElabd, @QuantumArjun, and I are excited to announce Trajectory. We are a research lab and product company building the platform for Continual Learning. Our platform unlocks the signal already sitting in product usage, so companies can continuously post-train large-scale agentic models that outperform the frontier. @trajectorylabs We’ve raised $15M from @Conviction, @BessemerVP, @radicalvcfund, @jeffdean, @drfeifei and more. We’re partnering with some of the best AI-native companies: @ClayRunHQ @Harvey, @DecagonAI, @mercor_ai, @RogoAI to power their agentic systems, some of which we are already in production with. We’ve brought together a world class research team from DeepMind, OpenAI, Apple, Meta Superintelligence, Amazon AGI, Scale AI, and an elite product team from Stripe and Figma. AI will never again start on day one. Every correction, every retry, every edit will make products smarter. This is Continual Learning.
English
244
143
1.3K
1.7M
OpenRouter がリツイート
Warp
Warp@warpdotdev·
You can now connect your @OpenRouter URL directly to the Warp Agent. OpenRouter unlocks a world of models including Anthropic, OpenAI, Gemini, DeepSeek, Kimi, and more, all with better prices and uptime. Set your URL, model, and an alias to easily switch using /model.
English
10
9
123
14.6K

ディスカバー

@ComfyUI @StepFun_ai @a16z @MenloVentures @nvidia @ServiceNow @MongoDB @Snowflake