Calculate the cost of using NVIDIA-Nemotron-3-Ultra-550B-A55B from Wandb for your AI applications
Pricing data last updated:
Mode: Chat
Max: 262,144 tokens
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
NVIDIA-Nemotron-3-Ultra-550B-A55B is a chat model from Wandb, one of 35 chat models they offer. It is priced at $0.75 per 1M input tokens and $2.75 per 1M output tokens, ranking 1892 out of 3254 chat models by cost and cheaper than 41% of models in this category. NVIDIA-Nemotron-3-Ultra-550B-A55B supports prompt caching. Its 262K-token context window is in the top 37% among chat models.
Note: Use the interactive calculator above to estimate costs for your specific usage patterns.
Use the maximum token limits shown above to understand the model's capacity. This model can handle up to 262,144 input tokens.
At $0.75 per 1M input tokens and $2.75 per 1M output tokens, NVIDIA-Nemotron-3-Ultra-550B-A55B ranks 1892 out of 3254 chat models by input cost. It is more expensive compared to the median of $0.52 for chat models, and is cheaper than 41% of models in this category.
NVIDIA-Nemotron-3-Ultra-550B-A55B is one of 35 Wandb chat models, with support for prompt caching. its 262K-token context window places it in the top 37% of chat models.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs NVIDIA-Nemotron-3-Ultra-550B-A55B |
|---|---|---|---|---|
| amazon.nova-pro-v1:0 | AWS Bedrock | $0.80 | $3.20 | +7% |
| anthropic.claude-3-5-haiku-20241022-v1:0 | AWS Bedrock | $0.80 | $4.00 | +7% |
| apac.amazon.nova-pro-v1:0 | AWS Bedrock | $0.84 | $3.36 | +12% |
Similar chat models from other providers
Yes. NVIDIA-Nemotron-3-Ultra-550B-A55B costs $0.75 per 1M input tokens compared to amazon.nova-pro-v1:0's $0.80 per 1M input tokens, making it 7% more affordable. Both are chat models and share support for vision, function calling, prompt caching, structured output.
NVIDIA-Nemotron-3-Ultra-550B-A55B input pricing is $0.75 per 1M tokens, which is 45% above the median of $0.52 for chat models. It ranks 1892 out of 3254 chat models by input cost, making it cheaper than 41% of models in this category. For output, it costs $2.75 per 1M tokens compared to the median of $1.50.
Among Wandb's 35 chat models, NVIDIA-Nemotron-3-Ultra-550B-A55B ranks 31 by input cost.
The most comparable chat models to NVIDIA-Nemotron-3-Ultra-550B-A55B are: amazon.nova-pro-v1:0 from AWS Bedrock ($0.80/1M input tokens); anthropic.claude-3-5-haiku-20241022-v1:0 from AWS Bedrock ($0.80/1M input tokens); apac.amazon.nova-pro-v1:0 from AWS Bedrock ($0.84/1M input tokens); gpt-5.4-mini from Azure ($0.75/1M input tokens). These alternatives were selected based on similar capabilities, pricing, and provider diversity. You can compare any of these models in detail using the Bifrost Model Library.
NVIDIA-Nemotron-3-Ultra-550B-A55B is priced based on input and output tokens. Use the interactive calculator at the top of this page to estimate costs for your specific workload. Enter your expected input and output tokens volume and the calculator will show the total cost breakdown. For reference, processing 1M input tokens costs $0.75 and generating 1M output tokens costs $2.75.