resources
Comparisons, guides and long-form material
Everything we publish about LLM inference, agent sandboxes, cluster architecture and data sovereignty in Europe. Built to read slowly and cite well.
comparisons
Comparisons with other platforms
Honest tables: pricing, latency, certifications. When to pick us and when not.
GPU Flow vs OpenAI
Pricing, invoicing, data residency, SDK. Full table + FAQ with citable data.
read publishedGPU Flow vs Modal
US serverless GPU vs ready LLM inference in Europe. Pricing, data residency and when to pick each.
read publishedGPU Flow vs Replicate
US model marketplace vs a European drop-in LLM token API. Catalogue, invoicing and data residency.
readguides
Technical guides
How to migrate from OpenAI/Anthropic, how to connect Claude Code to the API, how to pick model and Sandbox size.
Migrate from OpenAI to GPU Flow in 15 minutes
Change two lines of the OpenAI SDK, pick the equivalent model and keep streaming, tools and reasoning.
read publishedConnect Claude Code to Token Factory
Point Claude Code at your European inference with three environment variables, or boot it pre-wired in a Sandbox.
read publishedChoosing a Sandbox: CPU, RAM, storage
When CPU is enough, when you need a GPU, how much RAM and storage. And how idle auto-suspend saves you.
readblog
Notes and articles
What we learn operating NVIDIA B200 GPUs over InfiniBand and DDN EXAScaler. Honest, no inflated marketing.
Why we measure in TTFT, not tokens/second
Time to first token is what your user feels. Why we prioritise it and how we lower it.
read publishedData sovereignty: what it actually means in 2026
The buzzword vs concrete guarantees: jurisdiction, sub-processors, certifications your DPO can read.
read