Granite 4.1 8B

Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks including tool calling, retrieval-augmented generation (RAG), code generation with fill-in-the-middle support, text summarization, classification, and extraction. The model handles 12 languages (English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese) and implements OpenAI-compatible tool calling. Released under the Apache 2.0 license.

ChatIBM131k tokens$0.0545 / $0.109 · 1M

ibm-granite/granite-4.1-8b

Context
131k tokens
Completion cap
131,072
Tools
Yes
JSON
Yes
Released
2026-04-30

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-4.1-8b",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Granite 4.1 8B?
Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks including tool calling, retrieval-augmented generation (RAG), code generation with fill-in-the-middle support, text summarization, classification, and extraction. The model handles 12 languages (English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese) and implements OpenAI-compatible tool calling. Released under the Apache 2.0 license. Granite 4.1 8B runs on the Geek Hub API (OpenAI-compatible). Model id: ibm-granite/granite-4.1-8b.
Is Granite 4.1 8B free?
No. Input is $0.0545 per 1M tokens and output is $0.109 per 1M tokens on Geek Hub (markup included).
What is the context length of Granite 4.1 8B?
Granite 4.1 8B has a 131k tokens context window. It supports up to 131,072 completion tokens.
Does Granite 4.1 8B support tool calling and structured outputs?
Granite 4.1 8B accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was Granite 4.1 8B released?
Granite 4.1 8B was released on 2026-04-30.

More models from IBM