Nemotron 3 Ultra 550B A55B

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

Maker: NVIDIA, United States
Released: 2026-06-04
Knowledge cutoff: 2025-09
Family: nemotron
Weights: open
Tasks: text.chat, text.reasoning, code
Cheapest offering: OpenRouter, about $0 for a typical text.chat call

Try it in the sandbox Use it from the API

Offerings

Provider	Model id at the provider	Status	Price per 1M tokens	Per-unit prices	Limits	Capabilities (level)
Fireworks AI	`accounts/fireworks/models/nemotron-3-ultra-nvfp4`	deprecateddeprecated 2026-11-07	Input: $0.6 Output: $2.4 Cache read: $0.12 Since 2026-11-03 · models.dev, MIT	none	Context: 262,144 tokens Max output: 128,000 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `tool_choice` claimed
OpenRouter	`nvidia/nemotron-3-ultra-550b-a55b`	ga	Input: $0.6 Output: $2.4 Cache read: $0.12 Unverified: sources disagree by more than 5%Since 2026-11-03 · models.dev, MIT	none	Context: 262,144 tokens Max output: 182,520 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed
OpenRouter	`nvidia/nemotron-3-ultra-550b-a55b:free`	ga	Input: $0 Output: $0 Since 2026-11-03 · models.dev, MIT	none	Context: 1,000,000 tokens Max output: 65,536 tokens	`input.text` claimed `output.text` claimed `tools` claimed `reasoning` claimed
Together AI	`nvidia/nemotron-3-ultra-550b-a55b`	deprecateddeprecated 2026-08-27	Input: $0.6 Output: $3.6 Cache read: $0.2 Since 2026-11-03 · models.dev, MIT	none	Context: 512,300 tokens Max output: 512,300 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed

Quality scores

No quality score for this model yet.

Aliases

Other names the API accepts for this model.

accounts/fireworks/models/nemotron-3-ultra-nvfp4
nvidia/nemotron-3-ultra-550b-a55b:free

Use it from the API

Look this model up, or ask for the best model for its task on the providers that offer it. See the quickstart and the API reference.

Look up this model

curl 'https://rhumbdata.com/v1/models/nvidia/nemotron-3-ultra-550b-a55b' \
  -H "Authorization: Bearer $RHUMB_KEY"

Resolve text.chat on its providers

curl 'https://rhumbdata.com/v1/resolve?task=text.chat&providers=fireworks,openrouter,together' \
  -H "Authorization: Bearer $RHUMB_KEY"

Built from catalog version 2026-11-04.3 of 2026-11-04. Prices are list prices per 1M tokens unless marked otherwise; every score shows its source's notice (see Attributions).