NVIDIA Nemotron · LLM API pricing
Nemotron 3 Ultra 550B A55B API pricing: cheapest provider
2 providers sell Nemotron 3 Ultra 550B A55B. GMI Cloud is cheapest; the most expensive charges 1.2× as much for the same model.
- Cheapest$1.25per 1M · GMI Cloud
- Input · output$0.80 / $2.60per 1M tokens
- Price gap1.2×across 2 providers
- Context1Mmax tokens
Standard list prices in USD from each provider's pricing page · last price change Nov 8, 2026 · How we collect and rank prices
Ranked for your volume
Nemotron 3 Ultra 550B A55B monthly cost by provider
Change the monthly tokens and the ranking updates instantly, using each provider's standard list price.
More requirements: caching, context, features, provider
Cheapest provider for your volume
GMI Cloud
2 options · most expensive $60.00, 1.2× this price
| Provider | Estimated / month | Input / 1M | Output / 1M | Cached input / 1M | Context |
|---|---|---|---|---|---|
1 | $50.00 | $0.80 | $2.60 | $0.10 | 262K |
2 | $60.00 | $1.00 | $3.00 | $0.12 | 1M |
Order depends on listed price for your volume only. No provider pays for its position.
What this estimate leaves out
Input volume includes the cached share, not an additional token volume. This is a list-price estimate, not a quote: cache-write charges, cache eligibility/TTL, batch discounts, long-context surcharges, regional pricing and taxes are excluded. Check the provider's terms for your workload before switching.
Price history
Cheapest blended price: $1.35 on Sep 28, 2026, now $1.25 at GMI Cloud (-7%).
Show all 3 steps with sources
- Sep 28, 2026: $1.35 at Together AI
- Oct 28, 2026: $1.50 at Nebius Token Factory
- Nov 8, 2026: $1.25 at GMI Cloud
Every step is a confirmed list-price change; links go to each provider's pricing page. All price changes
Switch to the cheapest OpenAI-compatible provider
Already using the OpenAI SDK? Change the base URL, key and model name.
Show the code
from openai import OpenAI
import os
client = OpenAI(
base_url="https://api.tokenfactory.nebius.com/v1",
api_key=os.environ["NEBIUS_API_KEY"],
)
response = client.chat.completions.create(
model="nvidia/Nemotron-3-Ultra-550b-a55b",
messages=[{"role": "user", "content": "Hello"}],
)Compare Nemotron 3 Ultra 550B A55B with another model
Or compare against any other model
Before you pick a provider
Context windows differ by provider, from 262K to 1M tokens. A cheaper host may not accept your longest prompts.
2 of 2 providers list a cached-input price. Repeated system prompts or documents can cost much less there than the standard input rate shown above.