Nemotron 3 Ultra
by NVIDIA Expected Oct 2, 2026
Coming soonopen-weightslargetool-use
thairouter/nemotron-3-ultraOverview
NVIDIA's largest open Nemotron model, trained for enterprise agents with strong tool calling and long-form generation.
Context
131.1K
tokens
Max output
8.2K
tokens per reply
Input
TBA
per 1M tokens
Output
TBA
per 1M tokens
Expected Oct 2, 2026. Specs are provisional until the model is actually served; pricing is announced at launch.
Benchmarks
Reference scores published by the model's authors, not measured on ThaiRouter. Live numbers appear once the model is serving.
Intelligence Index
23
Artificial Analysis v4.3
API
OpenAI-compatible. Point your client at https://api.thairouter.ai/v1 and send this id.
curl https://api.thairouter.ai/v1/chat/completions \
-H "Authorization: Bearer $THAIROUTER_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "thairouter/nemotron-3-ultra",
"messages": [{"role": "user", "content": "สวัสดี"}]
}'Not serving yet. Requests with this id return 404 until launch.