Calculate the cost of using NVIDIA-Nemotron-3-Ultra-550B-A55B from DeepInfra 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 DeepInfra, one of 136 chat models they offer. It is priced at $0.50 per 1M input tokens and $2.20 per 1M output tokens, ranking 1784 out of 3781 chat models by cost and cheaper than 52% of models in this category. NVIDIA-Nemotron-3-Ultra-550B-A55B supports vision, function calling, reasoning, prompt caching, structured output. Its 262K-token context window is in the top 45% 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 $0.50 per 1M input tokens and $2.20 per 1M output tokens, NVIDIA-Nemotron-3-Ultra-550B-A55B ranks 1784 out of 3781 chat models by input cost. It is more affordable compared to the median of $0.60 for chat models, and is cheaper than 52% of models in this category.
NVIDIA-Nemotron-3-Ultra-550B-A55B is one of 136 DeepInfra chat models, with support for vision, function calling, reasoning, prompt caching, structured output. its 262K-token context window places it in the top 45% of chat models.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs NVIDIA-Nemotron-3-Ultra-550B-A55B |
|---|---|---|---|---|
| eu.amazon.nova-2-lite-v1:0 | AWS Bedrock | $0.43 | $3.60 | -14% |
| gemma-4-31B-it | Sail | $0.40 | $0.60 | -20% |
| gemini-3-flash-preview | Vertex AI | $0.50 | $3.00 | 0% |
Similar chat models from other providers
No. NVIDIA-Nemotron-3-Ultra-550B-A55B costs $0.50 per 1M input tokens while eu.amazon.nova-2-lite-v1:0 costs $0.43 per 1M input tokens, making eu.amazon.nova-2-lite-v1:0 14% more affordable for input. However, NVIDIA-Nemotron-3-Ultra-550B-A55B may offer different capabilities or performance characteristics that justify the price difference.
NVIDIA-Nemotron-3-Ultra-550B-A55B input pricing is $0.50 per 1M tokens, which is 17% below the median of $0.60 for chat models. It ranks 1784 out of 3781 chat models by input cost, making it cheaper than 52% of models in this category. For output, it costs $2.20 per 1M tokens compared to the median of $1.75.
Among DeepInfra's 136 chat models, NVIDIA-Nemotron-3-Ultra-550B-A55B ranks 96 by input cost.
The most comparable chat models to NVIDIA-Nemotron-3-Ultra-550B-A55B are: eu.amazon.nova-2-lite-v1:0 from AWS Bedrock ($0.43/1M input tokens); gemma-4-31B-it from Sail ($0.40/1M input tokens); gemini-3-flash-preview from Vertex AI ($0.50/1M input tokens); gemini-3-flash-preview from Google Gemini ($0.50/1M 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 $0.50 and generating 1M output tokens costs $2.20.