AI Prosumer
EN

Models

11 models

Prices per 1M tokens

ibm/granite4

Granite 4 features improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.

5 model tags1M contextToken exchange

ibm/granite3.3

IBM Granite 2B and 8B models are 128K context length language models that have been fine-tuned for improved reasoning and instruction-following capabilities.

3 model tags131K contextToken exchange

ibm/granite3.2-vision

A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.

5 model tags16K contextToken exchange

ibm/granite3.2

Granite-3.2 is a family of long-context AI models from IBM Granite fine-tuned for thinking capabilities.

9 model tags131K contextToken exchange

ibm/granite-embedding

The IBM Granite Embedding 30M and 278M models models are text-only dense biencoder embedding models, with 30M available in English only and 278M serving multilingual use cases.

6 model tags512 contextToken exchange

ibm/granite3.1-moe

The IBM Granite 1B and 3B models are long-context mixture of experts (MoE) Granite models from IBM designed for low latency usage.

33 model tags131K contextToken exchange

ibm/granite3.1-dense

The IBM Granite 2B and 8B models are text-only dense LLMs trained on over 12 trillion tokens of data, demonstrated significant improvements over their predecessors in performance and speed in IBM’s initial testing.

33 model tags131K contextToken exchange

ibm/granite3-guardian

The IBM Granite Guardian 3.0 2B and 8B models are designed to detect risks in prompts and/or responses.

10 model tags8K contextToken exchange

ibm/granite3-moe

The IBM Granite 1B and 3B models are the first mixture of experts (MoE) Granite models from IBM designed for low latency usage.

33 model tags4K contextToken exchange

ibm/granite3-dense

The IBM Granite 2B and 8B models are designed to support tool-based use cases and support for retrieval augmented generation (RAG), streamlining code generation, translation and bug fixing.

33 model tags4K contextToken exchange

ibm/granite-code

A family of open foundation models by IBM for Code Intelligence

162 model tags128K contextToken exchange

Filters

Providers
Creators
Access
Serverless