NVIDIA: Nemotron 3 Ultra

550B / 55B

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).

Context
262K
Max output
183K
Input price
$0.6/1M tokens
Output price
$2.4/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming

Details

Model IDnvidia/nemotron-3-ultra-550b-a55b
Provider OpenRouter
Creator NVIDIA
Family—
License—
Status—
Typechat
Input modalitiestext
Output modalitiestext
Open weight—
Parameters550B / 55B
Architecture—
Context window262K tokens
Max input—
Max output183K tokens
Reasoning tokens—
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$0.6
Output
$2.4
Cache write
—
Cache read
$0.12
Batch in
—
Batch out
—

API

GET/v1/models/openrouter/nvidia/nemotron-3-ultra-550b-a55b

NVIDIA: Nemotron 3 Ultra

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

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).

Changes · 17 entries
nvidia/nemotron-3-ultra-550b-a55bcreateca7a400Nov 2, 2026, 03:02 AM
nvidia/nemotron-3-ultra-550b-a55bupdateceebcb8Oct 12, 2026, 06:56 AM
max_output_tokens16384→182520
pricinginput$0.5→$0.6output$2.2→$2.4cached input$0.1→$0.12
nvidia/nemotron-3-ultra-550b-a55bupdate2b89bf1Oct 2, 2026, 06:39 AM
max_output_tokens182520→16384
pricinginput$0.6→$0.5output$2.4→$2.2cached input$0.12→$0.1
nvidia/nemotron-3-ultra-550b-a55bupdate3170597Sep 19, 2026, 06:34 AM
max_output_tokens32768→182520
pricinginput$0.625→$0.6output$3.125→$2.4cached input$0.188→$0.12
nvidia/nemotron-3-ultra-550b-a55bupdate40decdeSep 16, 2026, 06:38 AM
max_output_tokens182520→32768
pricinginput$0.6→$0.625output$2.4→$3.125cached input$0.12→$0.188
nvidia/nemotron-3-ultra-550b-a55bupdate20b7699Sep 14, 2026, 06:48 AM
max_output_tokens32768→182520
pricinginput$0.625→$0.6output$3.125→$2.4cached input$0.188→$0.12
nvidia/nemotron-3-ultra-550b-a55bupdate0d4ae28Sep 4, 2026, 06:37 AM
max_output_tokens182520→32768
pricinginput$0.6→$0.625output$2.4→$3.125cached input$0.12→$0.188
nvidia/nemotron-3-ultra-550b-a55bupdated79e481Sep 3, 2026, 06:38 AM
max_output_tokens32768→182520
pricinginput$0.625→$0.6output$3.125→$2.4cached input$0.188→$0.12
nvidia/nemotron-3-ultra-550b-a55bupdate77b8547Sep 2, 2026, 06:42 AM
max_output_tokens16384→32768
pricinginput$0.5→$0.625output$2.2→$3.125cached input$0.1→$0.188
nvidia/nemotron-3-ultra-550b-a55bupdatee3d7dedAug 31, 2026, 04:13 AM
context_window512288→262144
pricinginput$0.6→$0.5output$3.6→$2.2cached input$0.2→$0.1
nvidia/nemotron-3-ultra-550b-a55bupdate39b8745Jul 31, 2026, 06:11 AM
pricinginput$0.5→$0.6output$2.2→$3.6cached input$0.1→$0.2
nvidia/nemotron-3-ultra-550b-a55bupdatedbe2d73Jul 31, 2026, 06:07 AM
pricinginput$0.6→$0.5output$3.6→$2.2cached input$0.2→$0.1
nvidia/nemotron-3-ultra-550b-a55bupdate97fe10eJul 25, 2026, 09:55 AM
pricinginput$0.5→$0.6output$2.2→$3.6cached input$0.1→$0.2
nvidia/nemotron-3-ultra-550b-a55bupdatebf78dcfJul 25, 2026, 05:49 AM
context_window1000000→512288
pricinginput$0.6→$0.5output$3.6→$2.2cached input$0.2→$0.1
nvidia/nemotron-3-ultra-550b-a55bupdate20c73acJul 17, 2026, 02:34 AM
pricinginput$0.5→$0.6output$2.2→$3.6cached input$0.1→$0.2
nvidia/nemotron-3-ultra-550b-a55bupdateab879c8Jun 18, 2026, 08:32 AM
pricingoutput$2.5→$2.2cached input$0.15→$0.1
nvidia/nemotron-3-ultra-550b-a55bcreated68a4f1Jun 10, 2026, 02:10 AM