Fresh paint, wet floors — we're rebuilding CostOfToken into a cross-provider price comparison. Some corners are still under construction; the full version is coming up soon.

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B pricing

Nemotron 3 Ultra is built for, frontier reasoning, orchestration, coding agents, deep research, and complex enterprise workflows. It delivers up to 5x faster inference and up to 30% lower cost for agentic workloads while supporting up to 1M token context. nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B from DeepInfra costs $0.500 per 1M input tokens and $2.20 per 1M output tokens. Cached input is $0.100 per 1M. Context window 262,144 tokens.

API id nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B · DeepInfra · source · updated 2026-11-10 · general-purpose

$0.500
Input / 1M tokens
$2.20
Output / 1M tokens
$0.100
Cached input / 1M
262K
Context window

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B specifications

Provider
DeepInfra
API id
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
Model type
general-purpose
Context window
262K tokens
Max output
not published
Currency
USD
Price source
Provider API
Last checked
2026-11-10

Tags

  • flagship

What nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B costs in practice

Estimated cost at common usage volumes
WorkloadInput tokensOutput tokensEstimated cost
Short chat turn1,000500$0.0016
Document summary50,0002,000$0.03
1M tokens in, 200K out1,000,000200,000$0.94

Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.

Common questions

How much does nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B cost per 1M tokens?
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B costs $0.500 per 1M input tokens and $2.20 per 1M output tokens on the standard tier. Cached input is $0.100 per 1M.
What is nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B's context window?
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B accepts up to 262,144 tokens in a single request.
Is there a cheaper DeepInfra model than nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B?
Yes. Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo is $0.300 per 1M input tokens versus $0.500 for nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B, with a 262,144 token context window.
Where does this nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B price come from?
From the OpenRouter catalogue, because DeepInfra does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from DeepInfra's own — verify before committing spend.

Head-to-head comparisons

Other DeepInfra models

See all DeepInfra pricing →