What they do
NaN is a closed community inference cluster that shares GPUs so members can run open models through an OpenAI-compatible API without per-token usage caps.
$10 off the fastest Kimi K3 and GLM 5.3 from Synthetic
Provider details
NaN
Learn more about this provider, then browse the models currently listed under it.
nannan
Latest news about NaN
No articles yet. Fetch the latest news to show it here.
About NaN
How they were founded
Official materials identify NaN as Helmcode's inference community, led by Cristian Córdova and Borja Perez. Cristian Córdova says he started NaN to run serious open models without usage limits. The official pages reviewed here do not clearly disclose a founding year.
Quick Info
- Organization
- Helmcode
- Headquarters
- Canary Islands, Spain
- SDK package
- @ai-sdk/openai-compatible
- Synced at
- Sep 4, 2026
Models served
7 models available through NaN
These model results are sorted newest first so you can quickly see the latest options from this provider.
NaNqwen
Input
Output
NaNglm
Input
Output
Input
Output
NaNdeepseek-flash
Input
Output
NaNmimo
Input
Output
NaNqwen
Input
Output
NaNgemma
Input
Output