Thrilled to announce that Koyeb has entered into a definitive agreement to join @mistralai.bsky.social to build the future of AI infrastructure.

Koyeb will bring its platform, technology, and team to accelerate Mistral Compute offering. 🎉

AI Developer Meetup on Agents & Evaluation · Luma Join us for an evening of talks and demos from leading AI engineers for developers eager to learn more and build with AI. This event is an opportunity to…

Hey Paris AI devs! 🚀 Just 1 week to go until our AI Dev Meetup with amazing speakers from @arizeai and @Docker!

Don't miss out on an evening focused on building, running, evaluating, and scaling AI Agents in production. 🌐 🤖

Secure your spot now! 🔗 luma.com/n9h7uqiq

The Infrastructure Behind Strapi Cloud: Serverless, High-Performance, Built on Koyeb - Koyeb Discover how Strapi Cloud deploys thousands of projects daily with Koyeb's serverless infrastructure, sustains their forever-free tier with scale-to-zero, and eliminates infrastructure management overhead.

Read the full story about how @strapijs is leveraging Koyeb's serverless infrastructure to deploy thousands of fully-managed Strapi instances daily, sustain their forever-free tier with scale-to-zero, and more 👇
www.koyeb.com/blog/the-in...

🚀 Thrilled to power @strapijs Cloud! With Koyeb’s high-performance serverless infra, Strapi:

🔐 Runs a massive multi-tenant fleet securely
⚡ Deploys fully-managed Strapi instances in minutes
🌱 Sustains a generous free tier
🏃‍♀️ Lets their team focus on building Strapi

Koyeb Sandboxes: Fast, Scalable, Fully Isolated Environments for AI Agents and More - Koyeb Today, we are announcing the public preview of Koyeb Sandboxes. Perfect for AI agents, code generation, and any dynamic workloads, Koyeb Sandboxes offer blazing-fast deployments and exceptional performance for your AI workloads.

🤖 Looking to run AI-generated code? Make it safe, fast, and serverless with Koyeb Sandboxes:

🌐 Spin up 1 → 1000s of sandboxes
⚡ Fully isolated & pay-as-you-go
🧑‍💻 Python & JS SDKs available

Build, run, and scale with the best AI infrastructure
www.koyeb.com/blog/koyeb-...

AI Developer Meetup on Agents & Evaluation · Luma Join us for an evening of talks and demos from leading AI engineers for developers eager to learn more and build with AI. This event is an opportunity to…

🚀 Join us in Paris on Feb 19 for an evening of talks and demos from leading AI engineers! Catch talks from:

Dat Daryl Ngo - AI Architect @arizeai
JL de Morlhon - VP SWE @Docker
Jen Person - DevRel Engineer @gokoyeb

RSVP (space is limited) 👉 luma.com/n9h7uqiq

Koyeb: High-performance Infrastructure for APIs, Inference, and Databases Deploy intensive applications across GPUs, CPUs, and Accelerators in minutes - scale in 50+ locations.

Ready to build the future of AI & cloud? Join us 🙌

We're hiring:
🔸 Software Engineers
🔸 Fullstack Engineer
🔸 Frontend Engineer
🔸 Founding Sales/CS

Know someone who'd like one of these roles? Do us both a solid and tag them below! 🌐 🚀

Apply today: www.koyeb.com/careers

Koyeb Serverless GPUs: Slashing Prices on A100, H100, and L40S by up To 24% - Koyeb Today, we’re announcing a major price drop of up to 24% for NVIDIA A100, H100, and L40S GPU instance types.

On top of that, we slashed prices for A100, H100, and L40S GPUs!

Build and deploy AI with high-performance serverless infrastructure 🧑‍💻🚀
www.koyeb.com/blog/koyeb-...

🆕 H200, B200, and RTX Pro 6000 Serverless GPUs are live on Koyeb!

Run and scale your AI workloads with the best serverless infrastructure. Experience the powerhouse combo of @nvidia's high-performance GPUs and Koyeb's seamless serverless platform 🔥

Choosing a GPU for your LLM - What to consider when benchmarking We ran GPU benchmarks on 3 different LLMs deployed on Koyeb → https://shorturl.at/cFkyWIn this video, we cover what values we measured in our benchmark, why ...

Running AI workloads in production? 👇

We share insights and hands-on tutorials on YouTube covering:
• AI infra & GPU benchmarking
• Running models efficiently at scale
• Using tools like @claudeai SDK, @OpenAI SDK & Codex, and more

🎥 Check it out: www.youtube.com/watch?v=j0U...

Use Ollama to Test Multiple Code Generation Models With Koyeb Sandboxes - Koyeb This tutorial walks through how to build a complete pipeline that creates isolated environments, generates code, and executes the generated code.

What if you could generate code with AI models and execute it safely without ever installing anything on your local machine? 🧑‍💻

Follow our tutorial to set up a production-ready system for secure AI code generation and execution 🚀
www.koyeb.com/tutorials/u...

Authentication: Announcing 2FA, MFA and Passkeys on Koyeb - Koyeb Today, we are excited to announce a new and improved authentication experience for all Koyeb customers, bringing stronger security and smoother access to your Koyeb accounts.

Get started today 👇
www.koyeb.com/blog/authen...

Up your security game with our new advanced authentication features! 🛡️

🔐 Multi‑Factor Auth
🔐 Two‑Factor Auth
🔐 Passkeys support

Simple. Secure. Serverless. 🧑‍💻🚀

🤖 Codex, developed by @OpenAI, helps you write features, answer questions about your codebase, squash bugs, and review PRs.

Learn how to use a Koyeb Sandbox to securely run its dynamically generated code 🧑‍💻

Changelog #109: Partial Updates Now Valid Using the PATCH Endpoint of the Koyeb API, New Tutorial Using Ollama with Koyeb Sandboxes, and more Hello, and welcome to this week’s changelog update! Let’s dive into what’s new: Partial Updates Now Valid Using the PATCH Endpoint of the Koyeb API You can now provide a partial body with just the updates you want to make to a Service when using the Koyeb API’s PATCH endpoint (PATCH /v1/services/{id}). Prior to this change, you had to provide the entire service definition, making the endpoint effectively identical to PUT. New Tutorial: Use Ollama to Test Multiple Code Generation Models wi...

Read the full update over on the Koyeb Community 👇
community.koyeb.com/t/changelog...

AI Dev Meetup on Coding Agents with OpenAI and LangChain - Koyeb Koyeb's first AI Dev Meetup of 2026 focused on coding agents. We heard from engineers at Koyeb, OpenAI, and LangChain about building, optimizing, and using coding agents.

We kicked off our first AI developer meetup of 2026 with @OpenAI & @LangChain! It was a great night bringing the AI dev community together to share ideas and learn from some of the most exciting builders in the space

Read the recap for the highlights 👇
www.koyeb.com/blog/koyeb-...

Choosing a GPU for your LLM - What to consider when benchmarking We ran GPU benchmarks on 3 different LLMs deployed on Koyeb → https://shorturl.at/cFkyWIn this video, we cover what values we measured in our benchmark, why ...

Our GPU benchmarks for LLMs are frequently used as a reference by developers deciding which hardware to select for their model.

Watch our latest video to learn what we measure, why it matters, and what numbers to pay attention to depending on your use case.
www.youtube.com/watch?v=j0U...

Use Ollama to Test Multiple Code Generation Models With Koyeb Sandboxes - Koyeb This tutorial walks through how to build a complete pipeline that creates isolated environments, generates code, and executes the generated code.

Want to know which models perform best for your use case? 🧑‍🔬

In this tutorial, you’ll learn how to run @ollama in Koyeb Sandboxes to generate code using multiple AI models simultaneously, allowing you to easily compare results across models 🧪
www.koyeb.com/tutorials/u...

You can now provide a partial body with just the updates you want to make to a Service when using the Koyeb API’s PATCH endpoint (PATCH /v1/services/{id}).

Prior to this change, you had to provide the entire service definition, making the endpoint effectively identical to PUT.

Changelog 109 is here!
🧑‍💻 Partial Updates via PATCH Endpoint of the Koyeb API
📖 New Tutorial: Use @ollama to Test Multiple Code Generation Models w/ Koyeb Sandboxes
🎥 New Video: Choosing a GPU for Your LLM
🔁 AI Dev Meetup on Coding Agents w/ @OpenAI & @LangChain Recap

👇🧵

Use Ollama to Test Multiple Code Generation Models With Koyeb Sandboxes - Koyeb This tutorial walks through how to build a complete pipeline that creates isolated environments, generates code, and executes the generated code.

In our latest tutorial, we build a pipeline that:

⚙️ Spins up GPU sandboxes on-demand
🦙 Runs @ollama
🧪 Generates code using multiple different AI models
✅ Executes code safely & cleans up automatically

Check it out and get started 👇 www.koyeb.com/tutorials/u...

💻 What if you could generate AI code and run it safely without touching your local machine?

Meet Koyeb Sandboxes + Ollama: ephemeral, GPU-powered environments for testing multiple AI models securely.

Serverless AI Infrastructure Going into 2026: Sandboxes, GPUs, and More - Koyeb Gear up for 2026 with Koyeb's proven AI infrastructure. Last year, we shipped serverless GPUs, Koyeb Sandboxes for AI code execution, light sleep scale-to-zero, and so much more that help teams build and deploy AI faster than ever.

📅 In 2026 AI goes from demos to production.

Is your stack ready?
🧪 Secure sandboxes for AI-generated code
⚡ 250ms cold starts
📈 Autoscaling
⚙️ High-performance GPUs you can afford to experiment with

Built for what's next 👉 www.koyeb.com/blog/server...

Koyeb MCP Server: Interact with your Koyeb Resources in Natural Language - Koyeb Today we're announcing the Koyeb MCP Server in public beta to let you interact with your Koyeb resources in natural language.

🚀 Manage your Koyeb infrastructure with natural language:

🤖 Deploy apps, update configs, check logs and more
🔌 Works with @claudeai, @cursor_ai, @windsurf & any MCP client
⚡ One-line setup with npx

Get started 👉 www.koyeb.com/blog/koyeb-...

TCP Proxy: Expose TCP Ports Publicly - Koyeb Today we're announcing the TCP Proxy in public preview, a new way to expose TCP Ports publicly.

💡 TCP Proxy is available on Koyeb

🔌 Expose any TCP port to the public internet
🖥️ SSH into your services, connect database clients directly
⚡ One checkbox in the dashboard or via CLI

Try it now 👉 www.koyeb.com/blog/tcp-pr...

Changelog 108 is live!
⚙️ New @nvidia Serverless GPUs: RTX Pro 6000, H200, B200
🚮 Koyeb Sandboxes: Auto-deleton & Lifecycle Management
✅ JavaScript SDK for Koyeb Sandboxes
🧑‍💻 New Tutorial: Using @OpenAI Apps SDK with Koyeb

Discover what's new on Koyeb 👇

Koyeb Sandboxes: Fast, Scalable, Fully Isolated Environments for AI Agents and More - Koyeb Today, we are announcing the public preview of Koyeb Sandboxes. Perfect for AI agents, code generation, and any dynamic workloads, Koyeb Sandboxes offer blazing-fast deployments and exceptional performance for your AI workloads.

Get started today 👉 www.koyeb.com/blog/koyeb-...

💡 Running AI-generated code? Make it safe, fast, and serverless with Koyeb Sandboxes:
🌐 Spin up 1 → 1000s of sandboxes
⚡ Fully isolated & pay-as-you-go
🧑‍💻 Python & JS SDKs available

Build, run, and scale with the best infrastructure for AI.

🚀 Build your AI stack in minutes, not weeks.

With Koyeb One-Click Models & AI Apps, deploy production-ready AI on high-performance serverless infrastructure in the the click of a button.

⚡ No infra management
⚡ No setup
⚡ Just ship

👉 app.koyeb.com/one-clicks

Deploy Remote MCP Servers to Koyeb using Streamable HTTP Transport - Koyeb Learn how to build and deploy Remote Model Context Protocol (MCP) servers to Koyeb using Streamable HTTP transport.

🚀 Want to deploy remote MCP servers without managing your own infrastructure?

With Koyeb, you can spin up high-performance, fully serverless MCP servers in seconds.

Scalable, pay-as-you-go, and globally distributed 🌐💨
www.koyeb.com/tutorials/d...