Try Bifrost Enterprise free for 14 days.
Request access

nvidia.nemotron-super-3-120b Cost Calculator - Bedrock Mantle

Calculate the cost of using nvidia.nemotron-super-3-120b from Bedrock Mantle for your AI applications

Pricing data last updated:

nvidia.nemotron-super-3-120b Cost Calculator

Mode: Chat

Max: 256,000 tokens

Max: 32,000 tokens

Cost Breakdown

Input Cost$0.00018000
Output Cost$0.00078000
Total Cost$0.00096000

Pricing Details

Input: $0.0000001800 per token
Output: $0.0000007800 per token
[ WE'RE OPEN SOURCE ]

Scale with the Fastest LLM Gateway

Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.

Model Specifications

Capabilities

Function Calling

Limits

Max Input Tokens256,000
Max Output Tokens32,000
Max Tokens32,000

About nvidia.nemotron-super-3-120b

nvidia.nemotron-super-3-120b is a chat model from Bedrock Mantle, one of 81 chat models they offer. It is priced at $0.18 per 1M input tokens and $0.78 per 1M output tokens, ranking 869 out of 3639 chat models by cost and cheaper than 76% of models in this category. nvidia.nemotron-super-3-120b supports function calling. Its 256K-token context window is in the top 44% among chat models.

Pricing Information

Input Cost$0.18 per 1M tokens
Output Cost$0.78 per 1M tokens

Note: Use the interactive calculator above to estimate costs for your specific usage patterns.

Technical Specifications

Maximum Input Tokens256,000
Maximum Output Tokens32,000
Maximum Total Tokens32,000

Pro Tip

Use the maximum token limits shown above to understand the model's capacity. This model can handle up to 256,000 input tokens. The maximum output length is 32,000 tokens.

Model Capabilities

Function Calling - Execute custom functions and tools

How nvidia.nemotron-super-3-120b Pricing Compares

At $0.18 per 1M input tokens and $0.78 per 1M output tokens, nvidia.nemotron-super-3-120b ranks 869 out of 3639 chat models by input cost. It is more affordable compared to the median of $0.58 for chat models, and is cheaper than 76% of models in this category.

nvidia.nemotron-super-3-120b is one of 81 Bedrock Mantle chat models, with support for function calling. its 256K-token context window places it in the top 44% of chat models.

ModelProviderInput / 1M tokensOutput / 1M tokensvs nvidia.nemotron-super-3-120b
Mistral-7B-Instruct-v0.1Anyscale$0.15$0.15-17%
Mixtral-8x7B-Instruct-v0.1Anyscale$0.15$0.15-17%
gpt-oss-120bAzure$0.15$0.60-17%

Alternatives to nvidia.nemotron-super-3-120b

Similar chat models from other providers

Anyscale
Mistral-7B-Instruct-v0.1
$0.15/1M input
-17% vs nvidia.nemotron-super-3-120b
Anyscale
Mixtral-8x7B-Instruct-v0.1
$0.15/1M input
-17% vs nvidia.nemotron-super-3-120b
Azure
gpt-oss-120b
$0.15/1M input
-17% vs nvidia.nemotron-super-3-120b
Azure
gpt-5.4-nano
$0.20/1M input
+11% vs nvidia.nemotron-super-3-120b
Azure
gpt-5.4-nano-2026-03-17
$0.20/1M input
+11% vs nvidia.nemotron-super-3-120b

Frequently Asked Questions

Is nvidia.nemotron-super-3-120b cheaper than Mistral-7B-Instruct-v0.1?

No. nvidia.nemotron-super-3-120b costs $0.18 per 1M input tokens while Mistral-7B-Instruct-v0.1 costs $0.15 per 1M input tokens, making Mistral-7B-Instruct-v0.1 17% more affordable for input. However, nvidia.nemotron-super-3-120b may offer different capabilities or performance characteristics that justify the price difference.

How does nvidia.nemotron-super-3-120b pricing compare to the average chat model?

nvidia.nemotron-super-3-120b input pricing is $0.18 per 1M tokens, which is 69% below the median of $0.58 for chat models. It ranks 869 out of 3639 chat models by input cost, making it cheaper than 76% of models in this category. For output, it costs $0.78 per 1M tokens compared to the median of $1.66.

What makes nvidia.nemotron-super-3-120b different from other Bedrock Mantle models?

Among Bedrock Mantle's 81 chat models, nvidia.nemotron-super-3-120b ranks 39 by input cost.

What are the best alternatives to nvidia.nemotron-super-3-120b?

The most comparable chat models to nvidia.nemotron-super-3-120b are: Mistral-7B-Instruct-v0.1 from Anyscale ($0.15/1M input tokens); Mixtral-8x7B-Instruct-v0.1 from Anyscale ($0.15/1M input tokens); gpt-oss-120b from Azure ($0.15/1M input tokens); gpt-5.4-nano from Azure ($0.20/1M 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.

How do I calculate nvidia.nemotron-super-3-120b costs?

nvidia.nemotron-super-3-120b 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 $0.18 and generating 1M output tokens costs $0.78.