NVIDIA · Text
NVIDIA Nemotron 3 Ultra 550B API pricing
NVIDIA Nemotron 3 Ultra 550B is in the catalog and available on request: ask and it is normally enabled within a business day, at the price shown.
- Context window
- 1M tokens
- Type
- Text
- Capabilities
- tools · reasoning
- Availability
- On request
- Model id
- nvidia/nvidia-nemotron-3-ultra-550b-a55b
What you pay
- Input, per 1M tokens
- $0.63
- Output, per 1M tokens
- $3.13
vendor listyou pay
List price, no platform fee. Billed per request from prepaid credits; every response reports the cost.
Use it
Point the OpenAI SDK at OSMEXO and use nvidia/nvidia-nemotron-3-ultra-550b-a55b
The base URL and the key are the only changes. Streaming, tool calls, structured output and vision behave as they do upstream, and every response carries the billed cost beside the list price.
Python · openai sdk
from openai import OpenAI
client = OpenAI(
base_url="https://api.osmexo.com/v1", # was the vendor's URL
api_key="osm-...",
)
r = client.chat.completions.create(
model="nvidia/nvidia-nemotron-3-ultra-550b-a55b",
messages=[{"role": "user", "content": "Hello"}],
)
Trust
Check it is the real NVIDIA Nemotron 3 Ultra 550B, with your own key
The same battery we run before a route goes live: tokenizer fingerprint, knowledge cutoff, hidden-prompt probe and exact-output tasks, scored 0 to 100 against the vendor’s own API. One OpenRouter key verifies any text model; a direct NVIDIA key works too. Exit code 0 means the same model.
bash · verify with your own vendor key
curl -fsSLO https://dashboard.osmexo.com/verify.mjs
OSMEXO_API_KEY=osm-... VENDOR_API_KEY=sk-or-... node verify.mjs --model nvidia/nvidia-nemotron-3-ultra-550b-a55b --vendor openrouter
Questions
About NVIDIA Nemotron 3 Ultra 550B on OSMEXO
- How much does NVIDIA Nemotron 3 Ultra 550B cost through OSMEXO?
- $0.63 per 1M input tokens and $3.13 per 1M output tokens, billed per request from prepaid credits. That is NVIDIA’s list price; there is no platform fee on top. The price on this page refreshes from the catalog every few minutes.
- Is this the same NVIDIA Nemotron 3 Ultra 550B as calling NVIDIA directly?
- Yes. Every route for NVIDIA Nemotron 3 Ultra 550B is probed against the vendor’s own API before it serves anyone: tokenizer fingerprint, knowledge cutoff, a hidden-prompt probe and exact-output tasks, scored 0 to 100 with 85 as the approval threshold. You can run the same check from your machine with your own vendor key; the command is on this page.
- How do I call NVIDIA Nemotron 3 Ultra 550B with the OpenAI SDK?
- Point the official OpenAI SDK at https://api.osmexo.com/v1 with your OSMEXO key and use the model id nvidia/nvidia-nemotron-3-ultra-550b-a55b. Streaming, tool calls, structured output and vision work as they do upstream. Coding agents such as OpenCode, Cline, Roo Code, Continue and Aider take the same base URL and key.
- Why is NVIDIA Nemotron 3 Ultra 550B “on request”?
- The model is in the catalog but not yet enabled for every key, usually because its routes are still being verified or a vendor key is pending. Ask from the contact form or the dashboard and it is normally enabled within a business day.
More from the catalog
Related models
- Cosmos Predict (image-to-video)$0.80 per request · on request
- NVIDIA Nemotron 3 Nano 30B$0.0750 /M input · on request
- NVIDIA Nemotron 3 Super 120B$0.30 /M input · on request
- NVIDIA Nemotron 3.5 Lightning 30B$0.0700 /M input · on request
- NVIDIA Nemotron Cascade 2 30B$0.14 /M input · on request
- NVIDIA Nemotron Nano 12B v2 VL BF16$0.20 /M input · on request