Inference & infra AI tools

Inference providers, GPU clouds and serving stacks. Together, Fireworks, Groq, Modal, Baseten and more.

Deploy Next.js and AI apps with the AI SDK, AI Gateway and previews on every push.

Free · $204.0(1)used by 819 builders+ Stack Open ↗

Managed access to Claude, Nova, Llama and more inside AWS, with AgentCore.

Usage4.0(1)used by 197 builders+ Stack Open ↗

Edge inference, AI Gateway and the Agents SDK on Cloudflare's network.

Free · usage3.0(1)used by 56 builders+ Stack Open ↗

Very fast inference on LPU chips.

Free · usage3.0(1)used by 4 builders+ Stack Open ↗

One API for hundreds of models across providers.

Usage (pass-through)3.0(1)used by 4 builders+ Stack Open ↗

Serverless GPUs for inference and batch jobs.

Usageused by 2 builders+ Stack Open ↗

Affordable GPU cloud and serverless endpoints.

Usageused by 2 builders+ Stack Open ↗

Production inference platform for custom and open models.

Usageused by 1 builders+ Stack Open ↗

Low-latency inference for open and custom models.

Usageused by 1 builders+ Stack Open ↗

Fast inference and fine-tuning for open models.

Usageused by 1 builders+ Stack Open ↗

This week's events