LLM ReferenceLLM Reference
OpenRouter

Using Granite 4.1 8B on OpenRouter

Implementation guide · Granite 4.1 · IBM Research

ServerlessOpen Source

Quick Start

  1. 1
    Create an account at OpenRouter and generate an API key.
  2. 2
    Use the OpenRouter SDK or REST API to call ibm-granite/granite-4.1-8b — see the documentation for request format.
  3. 3
    You'll be billed $0.05/1M input, $0.10/1M output tokens. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

See OpenRouter documentation for integration details.

About OpenRouter

OpenRouter provides a unified interface for Large Language Models with better pricing, improved uptime, and no subscription requirements. Route across providers for cost optimization and reliability.

Multi-provider LLM aggregator offering unified API access to 300+ models from all major labs and emerging providers, with automatic failover for reliability.

View all models on OpenRouter →

Pricing on OpenRouter

TypePrice (per 1M)
Input tokens$0.05
Output tokens$0.10

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

About Granite 4.1 8B

IBM Granite 4.1 8B is a dense decoder-only transformer instruct model with 40 layers, 4096 embedding size, GQA (32 attention heads, 8 KV heads). Supports multilingual dialog (12 languages), code with FIM, tool-calling/function-calling, RAG, and summarization. Trained on NVIDIA GB200 NVL72 cluster. Apache 2.0. Benchmarks: MMLU 73.84, HumanEval 85.37, GSM8K 92.49, BFCL v3 68.27.

Full model details →

Model Specs

Released2026-04-29
Parameters8B
Context131K
ArchitectureDense decoder-only transformer: 40 layers, 4096 embed, 32 attn heads, 8 KV heads, SwiGLU, RoPE, RMSNorm

Provider

OpenRouter
OpenRouter

OpenRouter, Inc.

New York, NY, USA