IGIbm Granite/ Granite
Granite 4.1 8B
ibm-granite/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...
Model information
Released
2026-04-30
Context window
131K
Max output
131K
Model parameters
8.8B
Weights
Open
Modalities
Input
Text
Output
Text
Identity
- Version
- granite-4.1-8b
- License
- Apache-2.0
Resources
Capabilities
Open weightStructuredTemperatureTool call
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouter | ibm-granite/granite-4.1-8b | openai_chat | 131K | 131K | Tool callStructuredTemperature | Hugging Face: ibm-granite/granite-4.1-8b | input $0.05/M · output $0.1/M cache read $0.05/M | Yes | ||
| Weights & Biases | ibm-granite/granite-4.1-8b | openai_chat | 131K | 131K | Tool callStructuredTemperature | - | input $0.05/M · output $0.1/M cache read $0.05/M | Yes | ||
| NanoGPT | ibm-granite/granite-4.1-8b | openai_chat | 131K | 131K | Tool callStructured | - | input $0.05/M · output $0.1/M cache read $0.05/M | Yes | ||
| Kilo Gateway | ibm-granite/granite-4.1-8b | openai_chat | 131K | 131K | Tool callStructuredTemperature | - | input $0.05/M · output $0.1/M cache read $0.05/M | Yes | ||
| IBM watsonx.ai | granite-4.1-8b | custom | 131K | 131K | - | - | - | Yes |