Nvidia Nemotron 3 Ultra 550B A55B
NVIDIA-Nemotron-3-Ultra-550B-A55BPricing
List prices at W&B Inference, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.50 | $2.15 | |
| Cached input 80% off input | $0.10 | 80% off input |
What it costs a month
At W&B Inference list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$275
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$221
- Coding agent1,000 requests a day, 40K in / 2K out, cached$393
- Overnight batch20,000 requests a day, 4K in / 0.4K out$1,716
Where to run it
3 hosts serve Nvidia Nemotron 3 Ultra 550B A55B. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
W&B InferenceInference NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.50 / $2.15 | NVIDIA-Nemotron-3-Ultra-550B-A55B | |
DeepInfraInference NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.50 / $2.20 +1% vs headline | NVIDIA-Nemotron-3-Ultra-550B-A55B | |
BasetenInference NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.60 / $2.40 +15% vs headline | NVIDIA-Nemotron-3-Ultra-550B-A55B |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Features
- Prompt caching
- Open weights
- License: NVIDIA Open Model LicenseRuntimes: TGI, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than W&B Inference.
Smaller NVIDIA models
No cheaper NVIDIA model keeps its key capabilities.
Other frontier labs
- 7% less
- 49% less
- 78% less
- 78% less
Open-weight picks
- 4% less
- 6% less
- 13% less
- 25% less
Call it
Using W&B Inference's API.
from litellm import completion
response = completion(
model="wandb/NVIDIA-Nemotron-3-Ultra-550B-A55B",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Nvidia Nemotron 3 Ultra 550B A55B cost?
On W&B Inference, Nvidia Nemotron 3 Ultra 550B A55B costs $0.50 per million input tokens and $2.15 per million output tokens. Cached input costs $0.10 per million tokens.
Which APIs offer Nvidia Nemotron 3 Ultra 550B A55B?
Nvidia Nemotron 3 Ultra 550B A55B runs on 3 APIs: W&B Inference, DeepInfra and Baseten.
What is Nvidia Nemotron 3 Ultra 550B A55B's context window?
262K tokens, with up to 262K tokens in one reply.
Is Nvidia Nemotron 3 Ultra 550B A55B being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Nvidia Nemotron 3 Ultra 550B A55B?
Models that cost less and keep most of what it can do: Gemini 3.5 Flash Lite on Google AI Studio (7% less), GPT-5.4 Nano on OpenAI (49% less) and Motif 3 on ai& (4% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Nvidia Nemotron 3 Ultra 550B A55B's API model id?
Use NVIDIA-Nemotron-3-Ultra-550B-A55B with W&B Inference.
Sources
Raw catalog entry for NVIDIA-Nemotron-3-Ultra-550B-A55B on W&B Inference
{
"supports_reasoning": true,
"max_output_tokens": 262144,
"max_input_tokens": 262000,
"input_cost_per_token": 5e-7,
"output_cost_per_token": 0.00000215,
"cache_read_input_token_cost": 1e-7,
"supports_prompt_caching": true,
"litellm_provider": "wandb",
"mode": "chat",
"supports_vision": false,
"source": "https://wandb.ai/site/pricing/tokens/"
}