Model catalogue
NVIDIA
Nemotron 3 Ultra (free)
nvidia/nemotron-3-ultra-550b-a55b:free
Specification
Published by the vendor; the platform bills at the target's declared price.
Nemotron 3 Ultra (free)
reasoning open weights toolsfreeNVIDIA nvidia/nemotron-3-ultra-550b-a55b:free
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
- Input $/1M
- free
- Output $/1M
- free
- Context
- 1M
- Max output
- 66K
- Released
- Jun 4, 2026
- Modalities
- text
Intelligence index-
Coding index49
Agentic index22
On this deployment
No routing target resolves to this model yet. Declare one and the router picks it up without retraining.
Not routable here yet
Add a target with metadata.model set to this id.
targets.yamlyaml
# targets.yaml - declare a target that runs Nemotron 3 Ultra (free)
targets:
- id: nemotron-3-ultra-550b-a55b-free
kind: llm
name: Nemotron 3 Ultra (free)
metadata:
model: nvidia/nemotron-3-ultra-550b-a55b:free # links the target to this catalogue entry
capabilities:
domains: [general]
supports_tools: true
context_window: 1000000
cost:
usd_per_1k_tokens: 0.000000Price among NVIDIA models
Input list price per million tokens; Nemotron 3 Ultra (free) is the cheapest of 10 listed.
- 1freeNemotron 3 Ultra (free)
- 2free
- 3free
- 4free
- 5free
- 6$0.05
- 7$0.08
- 8$0.09
- 9$0.20
- 10$0.63
More from NVIDIA
Other models by the same vendor in the catalogue.
- Nemotron 3.5 LightningAug 11, 2026$0.08 in
- Nemotron 3.5 Lightning (free)Aug 11, 2026free in
- Nemotron 3.5 Content SafetyJun 4, 2026$0.20 in
- Nemotron 3.5 Content Safety (free)Jun 4, 2026free in
- Nemotron 3 UltraJun 4, 2026$0.63 in
- Nemotron 3 Nano Omni (free)Apr 28, 2026free in
- Nemotron 3 SuperMar 11, 2026$0.09 in
- Nemotron 3 Super (free)Mar 11, 2026free in
- Nemotron 3 Nano 30B A3BDec 14, 2025$0.05 in