nvidia/nemotron-3-ultra-550b-a55bNebius AI
- api
- chat
- hosting
- EU
- model lab
- NVIDIA
- weights
- open
- added
- June 2026
- model id
- nebius/nvidia/nemotron-3-ultra-550b-a55b
capabilities 3/8
2 providers serve nemotron-3-ultra-550b-a55b. This page is one of them. Compare all endpoints
- input
- $1.00
- output
- $3.00
- cache write
- -
- cache read
- -
worked cost
| volume | cost |
|---|---|
| 100K in + 10K out | $0.13 |
| 1M in + 100K out | $1.30 |
| 10M in + 1M out | $13.00 |
Requesty charges what the upstream provider charges, with no markup and no per-request fee. Prompt caching and smart routing cut the effective cost further on repeated context. Gateway pricing
- median ttft
- 2.64s
- median tok/s
- 224.0
- blended /1M
- $1.02
- cache hit
- 19.5%
- answered
- 65.50%
Weekly aggregates from production traffic routed through Requesty to this endpoint. A metric with no qualifying sample is left out rather than filled in. Compare against the other providers
no published scores for this exact variant. region deployments and highspeed tiers usually share the base model's results
- retention
- none
- trains on prompts
- no
- hosted in
- EU
Terms are the provider's, not Requesty's: routing a request here puts it under them. Nebius Privacy Policy
Need every request to stay in one jurisdiction? EU hosting routes only through EU-hosted providers.
nebius/nvidia/nemotron-3-ultra-550b-a55bthis id pins the nebius ai deployment, with no routing and no failover. the managed id on the canonical page routes across all 2 providers instead
from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create( model="nebius/nvidia/nemotron-3-ultra-550b-a55b", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ],) print(response.choices[0].message.content)
Change the base url to https://router.requesty.ai/v1, use your Requesty key, set the model to the id above. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog. Browse all models
Nemotron 3 Ultra is a 550B hybrid MoE model from NVIDIA, optimized for the most demanding multi-agent AI and complex reasoning tasks.
questions 5
How much does nvidia/nemotron-3-ultra-550b-a55b cost?
What is the context window of nvidia/nemotron-3-ultra-550b-a55b?
What can nvidia/nemotron-3-ultra-550b-a55b do?
How do I use nvidia/nemotron-3-ultra-550b-a55b with the OpenAI SDK?
Can I run nvidia/nemotron-3-ultra-550b-a55b through Requesty?
more from nebius ai 8
| endpoint | ctx | in /M |
|---|---|---|
| kimi-k3 | 1.0M | $3.00 |
| glm-5.2 | 1M | $1.40 |
| nvidia/nemotron-3-nano-omni | 300K | $0.06 |
| deepseek-v4-pro-0424 | 164K | $1.75 |
| moonshotai/kimi-k2.6 | 256K | $0.95 |
| zai-org/glm-5.1 | 200K | $1.40 |
| qwen/qwen3.5-397b-a17b | 128K | $0.60 |
| minimaxi/minimax-m2.5 | 128K | $0.30 |
call nvidia/nemotron-3-ultra-550b-a55b through one endpoint
One key for this endpoint and 600+ other models. No markup on provider prices, automatic failover when a provider degrades, and prompt caching built in. Methodology