Granite 4.0 Micro
Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long context tool calling.
ibm-granite/granite-4.0-h-micro
- Context
- 131k tokens
- Completion cap
- 131,000
- Tools
- No
- JSON
- Yes
- Released
- 2025-10-20
Call it from Geek Hub
Same OpenAI SDK. Change the base URL and the model id.
curl https://api.geekhub.mx/v1/chat/completions \
-H "Authorization: Bearer $GEEKHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "ibm-granite/granite-4.0-h-micro",
"messages": [{"role": "user", "content": "Hola"}]
}'Frequently asked questions
- What is Granite 4.0 Micro?
- Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long context tool calling. Granite 4.0 Micro runs on the Geek Hub API (OpenAI-compatible). Model id: ibm-granite/granite-4.0-h-micro.
- Is Granite 4.0 Micro free?
- No. Input is $0.0185 per 1M tokens and output is $0.1221 per 1M tokens on Geek Hub (markup included).
- What is the context length of Granite 4.0 Micro?
- Granite 4.0 Micro has a 131k tokens context window. It supports up to 131,000 completion tokens.
- Does Granite 4.0 Micro support tool calling and structured outputs?
- Granite 4.0 Micro does not advertise tool calling on this endpoint. It also supports structured outputs via a JSON schema in response_format.
- When was Granite 4.0 Micro released?
- Granite 4.0 Micro was released on 2025-10-20.