LLMOpen weights

Granite 4.1 8B

IBM

Updated May 21, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error

Specifications

Type: LLM
Access: Open weights
Released: April 30, 2026
Context window: 131,072 tokens
Output speed: 133 tok/s
Latency (TTFT): 0.47s
Input: Text
Output: Text
API pricing: $0.05 in · $0.10 out / 1M tokens

Capabilities

Function callingStructured output

Benchmarks

Reasoning

43.3

General

Humanity’s Last Exam

3.8

Compare Granite 4.1 8B with

vs Sonar Reasoning Pro vs R1 1776 vs Qwen3.7 Max vs Gemini 3.5 Flash

See all Granite 4.1 8B alternatives →