Skip to content
StackReplay
Models / NVIDIA

Nemotron 3 Ultra

NVIDIA · Model release

Catalog checked 2026-09-29

Context
1M
Reasoning
Yes
Included in
7 plans

API model id

nvidia/nemotron-3-ultra-550b-a55b
01 / Standard API priceUSD / 1M tokens

NVIDIA offers a free trial endpoint on build.nvidia.com and does not publish its own per-token API rate. The partner endpoints listed there set their own prices.

02 / Capabilities & limitsProvider specifications
Context window
1,000,000
Input
text
Output
text
Reasoning
Supported
Tool calling
Supported
Structured output
Not supported

Reasoning is turned on or off with enable_thinking in the chat template.

Before you chooseChecked 2026-09-29
Thinking
Reasoning is configurable on or off with enable_thinking in the chat template.
Released
June 4, 2026
API access
NVIDIA offers a free trial endpoint on build.nvidia.com that records inputs and outputs, which NVIDIA may use to improve its products. NVIDIA does not publish its own per-token rate; listed partner endpoints set their own prices.
API capabilities
Function calling is supported. Structured output is listed as not supported.
Output limit
A separate maximum output ceiling is not stated; the model card gives a context length of up to 1M tokens.
Data cutoff
Pre-training data cutoff September 2025; post-training data cutoff May 2026.
Open weights
The weights are downloadable. Use is governed by the OpenMDW License Agreement, version 1.1.
03 / Where you can use itPublished access · 7 subscriptions
Command Code Go$1 / month ↗Command Code GOAT$10 / month ↗Command Code Pro$20 / month ↗Command Code Max 10×$100 / month ↗Command Code Max 20×$200 / month ↗Ollama Cloud Pro$20 / month ↗Ollama Cloud Max$100 / month ↗
Pricing, assumptions & evidence

Missing token-category prices are not zero. Workload pricing applies exact recorded categories and admitted routes. No benchmark score or quality ranking is inferred from prices.

Aliases, routes and identity

Catalog ID nemotron-3-ultra

Model release (kind: release)

Developer: NVIDIA

nvidia/nemotron-3-ultra-550b-a55b

provider_id

nvidia/nemotron-3-ultra-550b-a55b

harness_alias