# Granite 4 H Small API Pricing

As of October 10, 2026, Granite 4 H Small costs $0.0636 per 1M input tokens and $0.265 per 1M output tokens on IBM watsonx.ai. It has a 131,072-token context window and returns up to 131,072 tokens per response.

- Page: https://models.litellm.ai/models/granite-4-h-small
- LiteLLM model name: `watsonx/ibm/granite-4-h-small`
- Context window: 131,072 tokens
- Max output: 131,072 tokens
- Added to LiteLLM: October 2025
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| IBM watsonx.ai | `watsonx/ibm/granite-4-h-small` | $0.0636 | $0.265 | – | – | – | 128K |

## Cost examples

1,000 requests with 2,000 input and 500 output tokens each:

- IBM watsonx.ai: $0.2597

100 long-document requests with 100,000 input and 2,000 output tokens each:

- IBM watsonx.ai: $0.689

## Features

Supported: Function calling, Parallel tool calls.
Not supported: Image input.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="watsonx/ibm/granite-4-h-small",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Granite 4 H Small cost?

Granite 4 H Small costs $0.0636 per 1M input tokens and $0.265 per 1M output tokens on IBM watsonx.ai.

### What is the context window of Granite 4 H Small?

Granite 4 H Small has a 131,072-token context window and returns up to 131,072 tokens per response.

### Which providers offer Granite 4 H Small?

Granite 4 H Small is available from IBM watsonx.ai through LiteLLM, using the model name watsonx/ibm/granite-4-h-small.

### How do I call Granite 4 H Small with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="watsonx/ibm/granite-4-h-small", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### What features does Granite 4 H Small support?

Granite 4 H Small supports function calling and parallel tool calls. It does not support image input.

### When did LiteLLM add Granite 4 H Small?

Granite 4 H Small was added to LiteLLM's model price file in October 2025.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json