Opper AI reposted this
Så tacksam för detta samarbete Andreas Jönsson, otroligt viktigt! evroc är en central del i den geopolitiska debatten.
Opper is the AI gateway for agents. One LLM router for 300+ frontier and open-weight models from Anthropic, OpenAI, Google, Mistral, Meta, xAI, and others, accessible through a single API with full OpenAI SDK compatibility. The LLM Gateway is the routing layer: change one line of code to switch providers, add intelligent fallbacks for uptime, and pin to EU-resident infrastructure when residency matters. All without rewriting your application or running your own inference stack. The AI Agent Control Plane sits above the gateway and gives teams full visibility and control over every AI call in production. Distributed tracing, online evaluation, scoring, prompt optimization, and per-call cost tracking. The same code that ships is the code you can debug, score, and improve over time. On top of that foundation, developers compose Opper's products for their own use case: an Agent SDK to build autonomous agents, a Task Completion API for structured and validated outputs, an Agent CLI that launches any agent on a single key, and AI Wallet, which lets end users bring their own AI. Trusted by 50,000+ developers and companies serving more than 10 million end users, from regulated fintech to consumer AI products. Get started at opper.ai Docs: docs.opper.ai
External link for Opper AI
Stockholm, Stockholm County 11137, SE
Västerängsvägen 51 a
Enebyberg, Stockholm County 182 47, SE
Opper AI reposted this
Så tacksam för detta samarbete Andreas Jönsson, otroligt viktigt! evroc är en central del i den geopolitiska debatten.
Opper AI reposted this
Gemini 3.5 Flash is now available in Opper 🔥 Agents need models that can keep up: plan the next step, call the right tool, coordinate with other agents, and keep going until the job is done. That’s why we’re excited to add support for Gemini 3.5 Flash in Opper. It works across the Playground, API, Agent SDK, and your coding agents. One line of code. Gemini 3.5 Flash everywhere you build with Opper.
Opper AI reposted this
Funderat på vilka backend system som finns i finansiella flöden? ISEC Group AB, så stolt över vårt samarbete! ping Andreas Bergh vilken resa =) den fortsätter vi
Opper AI reposted this
Another significant move for #Sovereign #AI ecosystem. Opper AI and INFERCOM partnership allows faster #inference access to European Developer ecosystem. 🤖 ❤️ 🦾
50,000 developers just got access to Europe's fastest sovereign inference. Infercom is now live on Opper AI. Opper is the AI gateway - one API, 300+ models, OpenAI SDK compatible. Change your base URL and you're on a different provider. Now you can route to Infercom: → MiniMax-M2.5 at 400+ tok/s → gpt-oss-120b for production at 700+ tok/s → Munich datacenter, full EU jurisdiction → No US CLOUD Act exposure No code changes. Select Infercom in the Opper console. For teams in regulated industries - finance, healthcare, legal, government - this is what sovereignty should look like: fast, simple, no asterisks. For agentic workloads burning millions of tokens: up to 10x faster than GPU inference. We've been building the fastest EU-hosted inference. Opper makes it accessible to everyone already building on their platform. #SovereignAI #Opper
Opper AI reposted this
50,000 developers just got access to Europe's fastest sovereign inference. Infercom is now live on Opper AI. Opper is the AI gateway - one API, 300+ models, OpenAI SDK compatible. Change your base URL and you're on a different provider. Now you can route to Infercom: → MiniMax-M2.5 at 400+ tok/s → gpt-oss-120b for production at 700+ tok/s → Munich datacenter, full EU jurisdiction → No US CLOUD Act exposure No code changes. Select Infercom in the Opper console. For teams in regulated industries - finance, healthcare, legal, government - this is what sovereignty should look like: fast, simple, no asterisks. For agentic workloads burning millions of tokens: up to 10x faster than GPU inference. We've been building the fastest EU-hosted inference. Opper makes it accessible to everyone already building on their platform. #SovereignAI #Opper
Opper AI reposted this
We've added INFERCOM to the Opper AI gateway. Infercom is a sovereign AI inference provider serving open-weight models on SambaNova RDU hardware. Their catalog runs across EU regions, German datacenters by default, as well as US and JP regions, with models including MiniMax-M2.5, gpt-oss-120b, Llama 3.3, and DeepSeek. For builders on Opper, this is another EU-sovereign option in the router. Pick Infercom in the Opper console and you're live: same API key, OpenAI SDK compatible, no code changes. For regulated workloads, EU-routed calls stay in German jurisdiction with no US CLOUD Act exposure. Compliance is aligned with GDPR, the German BDSG, the EU AI Act, and ISO 27001:2022. Full details on our blog: https://lnkd.in/e_vsAsSd
We've added INFERCOM to the Opper AI gateway. Infercom is a sovereign AI inference provider serving open-weight models on SambaNova RDU hardware. Their catalog runs across EU regions, German datacenters by default, as well as US and JP regions, with models including MiniMax-M2.5, gpt-oss-120b, Llama 3.3, and DeepSeek. For builders on Opper, this is another EU-sovereign option in the router. Pick Infercom in the Opper console and you're live: same API key, OpenAI SDK compatible, no code changes. For regulated workloads, EU-routed calls stay in German jurisdiction with no US CLOUD Act exposure. Compliance is aligned with GDPR, the German BDSG, the EU AI Act, and ISO 27001:2022. Full details on our blog: https://lnkd.in/e_vsAsSd
Opper AI reposted this
13M Daily Active Users. Instabridge absolutely crushing it! Carl Hasselskog haha, wow :)
Opper AI reposted this
"Coding will be a skill like, yeah, I know how to send a text message." He's right, so we shipped: npm i -g @opperai/cli - Run Claude Code, OpenClaw on 300+ models w/ Opper AI Plus Codex, OpenCode, Hermes, and Pi. Just switch agents and providers in one CLI. No more rate limits, just route to the same model on another provider. Use EU only when you're restricted. Run an open-weight for easy work and save $$.
Opper AI reposted this
Big deal: you can now run Claude Cowork with Opper AI, very useful if you keep hitting rate limits, want EU data residency, or save $$ by using open models. Here's how to set it up: https://lnkd.in/d6J4tTvp