Models

14 models shown. Amounts are per the unit stated in each row.
Model	Provider	Context	Prices
IBM: Granite 4.2 8B	ibm	131,072	Input $0.06 per 1M tokens unverified Input (cached read) $0.015 per 1M tokens unverified Output $0.25 per 1M tokens unverified
Granite-4.0-H-Small	ibm	131,072	Input $0.0636 per 1M tokens low Output $0.265 per 1M tokens low
Granite 4.1 8B	ibm	131,072	Input $0.05 per 1M tokens low Input (cached read) $0.05 per 1M tokens low Output $0.10 per 1M tokens low
IBM: Granite 4.0 Micro	ibm	131,000	Input $0.017 per 1M tokens low Output $0.112 per 1M tokens low
watsonx/ibm/granite-3-8b-instruct	ibm	8,192	Input $0.20 per 1M tokens low Output $0.20 per 1M tokens low
watsonx/ibm/granite-13b-chat-v2	ibm	8,192	Input $0.60 per 1M tokens low Output $0.60 per 1M tokens low
watsonx/ibm/granite-13b-instruct-v2	ibm	8,192	Input $0.60 per 1M tokens low Output $0.60 per 1M tokens low
watsonx/ibm/granite-3-3-8b-instruct	ibm	8,192	Input $0.20 per 1M tokens low Output $0.20 per 1M tokens low
watsonx/ibm/granite-guardian-3-2-2b	ibm	8,192	Input $0.10 per 1M tokens low Output $0.10 per 1M tokens low
watsonx/ibm/granite-guardian-3-3-8b	ibm	8,192	Input $0.20 per 1M tokens low Output $0.20 per 1M tokens low
watsonx/ibm/granite-ttm-1024-96-r2	ibm	512	Input $0.38 per 1M tokens low Output $0.38 per 1M tokens low
watsonx/ibm/granite-ttm-1536-96-r2	ibm	512	Input $0.38 per 1M tokens low Output $0.38 per 1M tokens low
watsonx/ibm/granite-ttm-512-96-r2	ibm	512	Input $0.38 per 1M tokens low Output $0.38 per 1M tokens low
watsonx/ibm/granite-vision-3-2-2b	ibm	8,192	Input $0.10 per 1M tokens low Output $0.10 per 1M tokens low