---
title: "granite-4-h-small Cost Calculator - IBM watsonx"
description: "Calculate the cost of using granite-4-h-small from IBM watsonx. Input costs $0.06 and output $0.27 per 1M tokens."
url: "https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/watsonx/model/granite-4-h-small"
markdown: "https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/watsonx/model/granite-4-h-small.md"
---

# granite-4-h-small Cost Calculator - IBM watsonx

> Calculate the cost of using granite-4-h-small from IBM watsonx. Input costs $0.06 and output $0.27 per 1M tokens.

## Important Links

- [View MCP Gateway](https://www.getmaxim.ai/bifrost/resources/mcp-gateway.md)
- [Features](https://www.getmaxim.ai/bifrost/#features)
- [Enterprise](https://www.getmaxim.ai/bifrost/enterprise)
- [Pricing](https://www.getmaxim.ai/bifrost/pricing.md)
- [Docs](https://docs.getbifrost.ai)
- [GitHub](https://github.com/maximhq/bifrost)
- [Book a Demo](https://www.getmaxim.ai/bifrost/book-a-demo)

## About granite-4-h-small

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 $0.27 per 1M output tokens, ranking 198 out of 2912 chat models by cost and cheaper than 93% of models in this category. granite-4-h-small supports function calling. It accepts up to 20K input tokens.

## Pricing

Published IBM watsonx pricing for granite-4-h-small.

- **$0.06 / 1M tokens Input.**
- **$0.27 / 1M tokens Output.**

## Technical Specifications

- **Chat Mode.**
- **20,480 Max Input Tokens.**
- **20,480 Max Output Tokens.**
- **20,480 Max Tokens.**

## Model Capabilities

granite-4-h-small supports: Function Calling, Parallel Function Calling.

## How Pricing Compares

At $0.06 per 1M input tokens and $0.27 per 1M output tokens, granite-4-h-small ranks 198 out of 2912 chat models by input cost. It is more affordable compared to the median of $0.55 for chat models, and is cheaper than 93% 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 | Output $/1M | vs granite-4-h-small |
| --- | --- | --- | --- | --- |
| amazon.nova-lite-v1:0 | AWS Bedrock | $0.06 | $0.24 | -6% |
| apac.amazon.nova-lite-v1:0 | AWS Bedrock | $0.06 | $0.25 | -1% |
| gpt-5-nano-2025-08-07 | Azure | $0.06 | $0.44 | -14% |
| Phi-4-mini-instruct | Azure | $0.07 | $0.30 | +18% |
| Phi-4-mini-reasoning | Azure | $0.07 | $0.30 | +18% |

## More from IBM watsonx

- [granite-guardian-3-2-2b ($0.10/1M input)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/watsonx/model/granite-guardian-3-2-2b.md)
- [granite-vision-3-2-2b ($0.10/1M input)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/watsonx/model/granite-vision-3-2-2b.md)
- [llama-3-2-1b-instruct ($0.10/1M input)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/watsonx/model/llama-3-2-1b-instruct.md)
- [mistral-small-2503 ($0.10/1M input)](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/watsonx/model/mistral-small-2503.md)

## Related Resources

- [All IBM watsonx pricing](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/watsonx.md)

## FAQ

### Is granite-4-h-small cheaper than amazon.nova-lite-v1:0?

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 6% more affordable for input. However, granite-4-h-small may offer different capabilities or performance characteristics that justify the price difference.

### How does granite-4-h-small pricing compare to the average chat model?

granite-4-h-small input pricing is $0.06 per 1M tokens, which is 88% below the median of $0.55 for chat models. It ranks 198 out of 2912 chat models by input cost, making it cheaper than 93% of models in this category. For output, it costs $0.27 per 1M tokens compared to the median of $1.50.

### What makes granite-4-h-small different from other IBM watsonx models?

Among IBM watsonx's 28 chat models, granite-4-h-small ranks 1 by input cost.

### What are the best alternatives to granite-4-h-small?

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); Phi-4-mini-instruct from Azure ($0.07/1M 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 granite-4-h-small costs?

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 $0.27.

## Related Resources

- [All IBM watsonx pricing](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/watsonx.md)
- [LLM cost calculator](https://www.getmaxim.ai/bifrost/llm-cost-calculator.md)
- [Model library](https://www.getmaxim.ai/bifrost/model-library.md)
- [Docs: Bifrost docs](https://docs.getbifrost.ai)
- [GitHub: maximhq/bifrost](https://github.com/maximhq/bifrost)
- [Pricing: Bifrost pricing](https://www.getmaxim.ai/bifrost/pricing.md)
- [Enterprise: Bifrost enterprise](https://www.getmaxim.ai/bifrost/enterprise)
- [Book a Demo: Bifrost demo](https://www.getmaxim.ai/bifrost/book-a-demo)
- [Resources: Bifrost resources](https://www.getmaxim.ai/bifrost/resources.md)

---

*This is a markdown version of [https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/watsonx/model/granite-4-h-small](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/watsonx/model/granite-4-h-small) for AI/LLM consumption.*