Granite 4.0 H Micro API Pricing
As of October 10, 2026, Granite 4.0 H Micro costs $0.017 per 1M input tokens and $0.112 per 1M output tokens on Cloudflare Workers AI. It has a 131,000-token context window and returns up to 131,000 tokens per response.
- Input
- $0.017 / 1M tokens
- Output
- $0.112 / 1M tokens
- Context window
- 131,000 tokens
- Max output
- 131,000 tokens
- Providers
- 1
- Added to LiteLLM
- June 2026
Granite 4.0 H Micro pricing by provider
1 listing across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Context |
|---|---|---|---|---|
| Cloudflare Workers AI | cloudflare/@cf/ibm-granite/granite-4.0-h-micro | $0.017 | $0.112 | 131K |
What Granite 4.0 H Micro costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Cloudflare Workers AI | $0.09 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Cloudflare Workers AI | $0.1924 |
Granite 4.0 H Micro features
- Function calling
Use Granite 4.0 H Micro with LiteLLM
Call Granite 4.0 H Micro through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="cloudflare/@cf/ibm-granite/granite-4.0-h-micro",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: granite-4.0-h-micro
litellm_params:
model: cloudflare/@cf/ibm-granite/granite-4.0-h-micro
# credentials: see the provider's LiteLLM docs pagecurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "granite-4.0-h-micro",
"messages": [{"role": "user", "content": "Hello!"}]
}'Granite 4.0 H Micro FAQ
How much does Granite 4.0 H Micro cost?
Granite 4.0 H Micro costs $0.017 per 1M input tokens and $0.112 per 1M output tokens on Cloudflare Workers AI.
What is the context window of Granite 4.0 H Micro?
Granite 4.0 H Micro has a 131,000-token context window and returns up to 131,000 tokens per response.
Which providers offer Granite 4.0 H Micro?
Granite 4.0 H Micro is available from Cloudflare Workers AI through LiteLLM, using the model name cloudflare/@cf/ibm-granite/granite-4.0-h-micro.
How do I call Granite 4.0 H Micro with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="cloudflare/@cf/ibm-granite/granite-4.0-h-micro", 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 4.0 H Micro support?
Granite 4.0 H Micro supports function calling.
When did LiteLLM add Granite 4.0 H Micro?
Granite 4.0 H Micro was added to LiteLLM's model price file in June 2026.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request.
LiteLLM docs: Cloudflare Workers AI.
Provider pages: Cloudflare Workers AI.
