OrcaRouter 🐳 (@OrcaRouter) header
OrcaRouter 🐳 (@OrcaRouter) profile picture

The AI Gateway built for Privacy & Security 🐳 0% Markup. BYOK. Adaptive Routing. Firewall. Guardrails. Cyber by @OrcaCyberHQ → https://nitter.cf/t.co/JN416veVHi

Joined April 2026
Photo by OrcaRouter 🐳 (@OrcaRouter)Photo by OrcaRouter 🐳 (@OrcaRouter)Photo by OrcaRouter 🐳 (@OrcaRouter)Photo by OrcaRouter 🐳 (@OrcaRouter)Photo by OrcaRouter 🐳 (@OrcaRouter)Photo by OrcaRouter 🐳 (@OrcaRouter)Photo by OrcaRouter 🐳 (@OrcaRouter)Photo by OrcaRouter 🐳 (@OrcaRouter)Photo by OrcaRouter 🐳 (@OrcaRouter)Photo by OrcaRouter 🐳 (@OrcaRouter)
OrcaRouter 🐳 retweeted
Code Blue 2026にスポンサーとして出展させていただいております。 たくさんの方にブースにお越しいただき、熱気を実感できました。 また明日もおりますのでぜひ、ブースまでお越しください!
2
4
295
OrcaRouter 🐳 retweeted
Replying to @OrcaRouter
@OrcaRouter 's Orcacyber Zero 1.5 model is now listed on platform.audn.ai It performs really well on cybergym we thought it would be great to add it to the model roster.
1
5
791
OrcaRouter 🐳 retweeted
【スポンサーブース紹介📸】 ✨ Special Sponsor OrcaRouter様 OrcaRouterは、200以上のLLM・生成AIモデルをひとつのゲートウェイから利用できるAI推論ゲートウェイです! モデルの切り替えやルーティング、可観測性、ガバナンスまで、AIエージェント時代のモデルアクセス基盤をまとめて扱えるのが特徴です。 会場では、実際の使い方やAIエージェント開発について直接お話しできる機会です🙌 ぜひブースへお立ち寄りください👀 ServerlessDays Tokyo 2026を支えていただき、ありがとうございます! ※お写真はお客様と熱いトーク中のワンシーンを頂戴しました #serverlessjp
1
3
1
8
1,292
OrcaRouter 🐳 retweeted
opencodex is in the one-click list in ORACROUTER now
Your AI tools. One click away. 🐳 OrcaRouter now supports one-click connection templates directly from your API Keys. Connect Gemini CLI, Goose, OpenHands, LobeChat, LibreChat, Zed, Chatbox, Jan, OpenCodex, and more — without manually configuring endpoints. Create a key → pick your tool → connect.
1
1
7
1,528
OrcaRouter 🐳 retweeted
📣FlashLabs社 小林氏 登壇決定🚀AIエージェントが増える今、「どのAIモデルを、どう使い分ける?」が新たな課題に。200以上のモデルを扱う「OrcaRouter」の実運用データから、モデルアクセスの最適化を解説🔥 #TiUD2026 Day1 は見逃せない! #TIDB @OrcaRouter @OrcaRouterJP👉ow.ly/QCka50ZO7f7
1
1
3
820
OrcaRouter 🐳 retweeted
Route across LLM providers — without hard-coding a model for every request. OrcaRouter Lite is an open-source, single-workspace LLM router for builders who want a self-hosted server with an optional managed fallback. It helps you keep one OpenAI-compatible interface while routing requests by capability and cost across the providers you configure. Key features: • Automatic model routing – `model="auto"` picks the cheapest configured model that meets tool, vision, or JSON-mode requirements • OpenAI-compatible API – reuse OpenAI SDK calls and stream responses through standard SSE formatting • Self-hosted BYOK – run it locally with your own provider keys, encrypted at rest • Managed fallback – add hosted OrcaRouter to cover models your local keys do not and provide failover when local providers fail • Built-in dashboard – manage providers, routing, keys, spend, latency, and savings from one page It’s open-source (MIT license). Link in the reply 👇
29
4
32
3,691
OrcaRouter 🐳 retweeted
Ever wanted an AI that sees images AND answers without filters? Meet Qwen3.8-27B, a vision-language model in GGUF format. It's abliterated for uncensored outputs, perfect for red-teaming and creative exploration. 4.3K downloads and counting! #AI #LLM
6
22
1
245
27,728
OrcaRouter 🐳 retweeted
💸 Want $10/30M tokens to bench Qwen3.8-27B in the cloud? First 500 devs. ~155 tok/s thinking off, ~66 thinking on. 🚀 @OrcaRouter API only. Base and uncensored. About 30M tokens, roughly 250 average novels. Thinking off, streamed, warm: 155.3 / 155.9 tok/s (2x48 tok). Prefill 2094 tok/s on 904. TTFT 0.32 s on a 30-token prompt. Cold first token 3.04 s. Thinking on: 66.3 tok/s (1x64 tok, mostly reasoning). Prefill 697 tok/s on 944 on the one unqueued hit. Later calls sat 37 to 118 s in queue before token 1. That wait is not tok/s. They also just shipped uncensored FP8 weights for red-team and security research. Link in the first reply. New accounts only. 1 per developer. No card. 18 days after claim. Authorized use only. This is NOT a referral link!! I do not get credits if you claim it. Just trying to help the OSS community out! If you have compute, share this with someone who does not. orcarouter.ai/redeem/I-LOVE-…
4
2
1
16
4,724
OrcaRouter 🐳 retweeted
Integration alert! @OrcaRouter is now available as a ChatGenerator in Haystack. Use OrcaRouterChatGenerator to swap between standard LLMs, and multimodal models through a unified interface - no pipeline rewiring needed. It acts as a flexible proxy layer that handles tool routing, conversation, and multimodal inputs seamlessly, letting you experiment with different models or providers without changing your agent code. 🐍 pip install orcarouter-haystack 🔗 haystack.deepset.ai/integrat…
1
2
5
670
OrcaRouter 🐳 retweeted
NocoBase now supports @OrcaRouter as an LLM provider. 🎉 Connect 200+ models with one API key, then use them across AI fields, AI employees, and workflows. Without switching providers! NocoBase users can also claim free credits here: orcarouter.ai/redeem/NOCOBAS… Enjoy!
2
4
604
OrcaRouter 🐳 retweeted
The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees. The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance. Access to all other Claude models is not affected. We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible. Read our full statement: anthropic.com/news/fable-myt…
12,107
24,983
28,878
86,538
93,537,858