Calculate the cost of using granite-4-h-small from IBM watsonx for your AI applications
Pricing data last updated:
Mode: Chat
Max: 20,480 tokens
Max: 20,480 tokens
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
granite-4-h-small is a chat model from IBM watsonx, one of 28 chat models they offer. It is priced at $0.06 per 1M input tokens and $0.25 per 1M output tokens, ranking 135 out of 2292 chat models by cost and cheaper than 94% of models in this category. granite-4-h-small supports function calling. It accepts up to 20K input tokens.
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 20,480 input tokens. The maximum output length is 20,480 tokens.
At $0.06 per 1M input tokens and $0.25 per 1M output tokens, granite-4-h-small ranks 135 out of 2292 chat models by input cost. It is more affordable compared to the median of $0.55 for chat models, and is cheaper than 94% of models in this category.
granite-4-h-small is one of 28 IBM watsonx chat models, with support for function calling.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs granite-4-h-small |
|---|---|---|---|---|
| amazon.nova-lite-v1:0 | AWS Bedrock | $0.06 | $0.24 | 0% |
| apac.amazon.nova-lite-v1:0 | AWS Bedrock | $0.06 | $0.25 | +5% |
| gpt-5-nano-2025-08-07 | Azure | $0.06 | $0.44 | -8% |
Similar chat models from other providers
No. granite-4-h-small costs $0.06 per 1M input tokens while amazon.nova-lite-v1:0 costs $0.06 per 1M input tokens, making amazon.nova-lite-v1:0 0% more affordable for input. However, granite-4-h-small may offer different capabilities or performance characteristics that justify the price difference.
granite-4-h-small input pricing is $0.06 per 1M tokens, which is 89% below the median of $0.55 for chat models. It ranks 135 out of 2292 chat models by input cost, making it cheaper than 94% of models in this category. For output, it costs $0.25 per 1M tokens compared to the median of $1.50.
Among IBM watsonx's 28 chat models, granite-4-h-small ranks 1 by input cost.
The most comparable chat models to granite-4-h-small are: amazon.nova-lite-v1:0 from AWS Bedrock ($0.06/1M input tokens); apac.amazon.nova-lite-v1:0 from AWS Bedrock ($0.06/1M input tokens); gpt-5-nano-2025-08-07 from Azure ($0.06/1M input tokens); gpt-5-nano from Azure ($0.05/1M 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.
granite-4-h-small 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 $0.06 and generating 1M output tokens costs $0.25.
