Provider pricing
IBM AI API pricing
IBM's Granite family is a set of open, enterprise-grade foundation models served through watsonx.ai. Granite 3.3 8B Instruct delivers strong RAG, summarization, and function-calling performance at $0.50/M input and output, with a 128K context window — purpose-built for regulated industries that need on-prem or sovereign-cloud deployment.
Founded2024 (Granite launch — IBM founded 1911)
HeadquartersArmonk, NY
Tracked models5
Best for
Regulated enterprises, financial services, and government teams needing sovereign-cloud LLMs with IP indemnity.
Strengths
- Open-source weights with enterprise IP indemnification
- Apache 2.0 license — fine-tune and self-host freely
- Strong RAG, summarization, and function calling for enterprise workflows
- Available on watsonx.ai with EU, US, and Japan data residency
Tracked IBM models
| Model | Input $/M | Output $/M | Context | Tier | Best for |
|---|---|---|---|---|---|
| Granite 3.3 2B Instruct | $0.100 | $0.100 | 128,000 | Budget | Ultra-cheap on-device/edge inference, classification, summarization on watsonx.ai |
| Granite 3.3 8B Instruct | $0.500 | $0.500 | 128,000 | Open Source | Enterprise RAG, summarization, function calling on watsonx.ai |
| Granite Code 8B Instruct | $0.200 | $0.200 | 128,000 | Budget | Code-specialized 8B for enterprise IDE integrations on watsonx.ai |
| Granite Vision 3.2 2B | $0.100 | $0.100 | 16,000 | Budget | Compact vision-language model for document and chart understanding |
| Granite 4 8B Instruct | $0.200 | $0.200 | 256,000 | Open Source | Hybrid Mamba-Transformer enterprise instruct on watsonx.ai |