Skip to content
No models found
OpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Apps
  • Models
  • Providers
  • Pricing
  • Enterprise
  • Labs

Company

  • About
  • Announcements
  • CareersHiring
  • Privacy
  • Terms of Service
  • Support
  • State of AI
  • Works With OR
  • Data

Developer

  • Documentation
  • API Reference
  • SDK
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for ibm-granite

IBM: Granite 4.1 8B

ibm-granite/granite-4.1-8b

Compare

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.

Modalities

Input Price

$0.05per 1M

Output Price

$0.10per 1M

Context

131K

Weekly Tokens

858M

Released

Apr 30, 2026

Overview
Providers
Performance
Pricing
Benchmarks
Apps
Activity
Uptime
API

Sample code and API for Granite 4.1 8B

OpenRouter normalizes requests and responses across providers for you.

1

Get your API key

Create an API key from your OpenRouter dashboard and set it as an environment variable:

2

Make your first request

Use ibm-granite/granite-4.1-8b with the OpenRouter API:

OpenRouter provides an OpenAI-compatible completion API to 400+ models & providers that you can call directly, or using the OpenAI SDK. Additionally, some third-party SDKs are available.

In the examples below, the OpenRouter-specific headers are optional. Setting them allows your app to appear on the OpenRouter leaderboards.

Using third-party SDKs

For information about using third-party SDKs and frameworks with OpenRouter, please see our frameworks documentation.

3

Enable streaming

Add "stream": true to your request body to receive responses as server-sent events:

Endpoint

POSThttps://openrouter.ai/api/v1/chat/completions
AuthorizationBearer $OPENROUTER_API_KEY
Content-Typeapplication/json
HTTP-Refereroptional — your site URL, for rankings
X-Titleoptional — your site name, for rankings
Modelibm-granite/granite-4.1-8b

Parameters

NameTypeDefaultDescription
response_formatmap—Forces the model to produce specific output format.
max_tokensinteger—This sets the upper limit for the number of tokens the model can generate in response.
temperaturefloat1This setting influences the variety in the model's responses.
top_pfloat1This setting limits the model's choices to a percentage of likely tokens: only the top tokens whose probabilities add up to P.
top_kinteger0This limits the model's choice of tokens at each step, making it choose from a smaller set.
repetition_penaltyfloat1Helps to reduce the repetition of tokens from the input.
frequency_penaltyfloat0This setting aims to control the repetition of tokens based on how often they appear in the input.
presence_penaltyfloat0Adjusts how often the model repeats specific tokens already used in the input.
stoparray—Stop generation immediately if the model encounter any token specified in the stop array.
seedinteger—If specified, the inferencing will sample deterministically, such that repeated requests with the same seed and parameters should return the same result.
toolsarray—Tool calling parameter, following OpenAI's tool calling request shape.
tool_choicestring or object—Controls which (if any) tool is called by the model.