Markdown version for AI agents

A token-efficient Markdown version of this page is available at: https://www.getmaxim.ai/bifrost/model-library/provider/watsonx.md

AI agents and LLMs should fetch the Markdown version instead of parsing this HTML — it contains the same content with far fewer tokens.

Watsonx Models

Browse all 31 AI models from Watsonx

Total Models

31

Modes

2

Avg Input (1M Tokens)

$17.35

Avg Output (1M Tokens)

$1.26

All Watsonx Models

Click on any model to view details

All Modes

Showing 31 of 31 models

Model Name↑	Provider	Mode	Pricing (tokens, images, audio, or pages)	Max Input Tokens	Max Output Tokens	Capabilities
allam-1-13b-instruct watsonx/sdaia/allam-1-13b-instruct	Watsonx	Chat	Input $1.80 / 1M tokensOutput $1.80 / 1M tokens	8,192	8,192
flan-t5-xl-3b watsonx/google/flan-t5-xl-3b	Watsonx	Chat	Input $0.600000 / 1M tokensOutput $0.600000 / 1M tokens	8,192	8,192
gpt-oss-120b watsonx/openai/gpt-oss-120b	Watsonx	Chat	Input $0.159000 / 1M tokensOutput $0.636000 / 1M tokens	131k	131k
granite-13b-chat-v2 watsonx/ibm/granite-13b-chat-v2	Watsonx	Chat	Input $0.600000 / 1M tokensOutput $0.600000 / 1M tokens	8,192	8,192
granite-13b-instruct-v2 watsonx/ibm/granite-13b-instruct-v2	Watsonx	Chat	Input $0.600000 / 1M tokensOutput $0.600000 / 1M tokens	8,192	8,192
granite-3-3-8b-instruct watsonx/ibm/granite-3-3-8b-instruct	Watsonx	Chat	Input $0.200000 / 1M tokensOutput $0.200000 / 1M tokens	8,192	8,192	Functions
granite-3-8b-instruct watsonx/ibm/granite-3-8b-instruct	Watsonx	Chat	Input $0.200000 / 1M tokensOutput $0.200000 / 1M tokens	8,192	1,024	Functions
granite-4-h-small watsonx/ibm/granite-4-h-small	Watsonx	Chat	Input $0.063600 / 1M tokensOutput $0.265000 / 1M tokens	131k	131k	Functions
granite-guardian-3-2-2b watsonx/ibm/granite-guardian-3-2-2b	Watsonx	Chat	Input $0.100000 / 1M tokensOutput $0.100000 / 1M tokens	8,192	8,192
granite-guardian-3-3-8b watsonx/ibm/granite-guardian-3-3-8b	Watsonx	Chat	Input $0.200000 / 1M tokensOutput $0.200000 / 1M tokens	8,192	8,192
granite-ttm-1024-96-r2 watsonx/ibm/granite-ttm-1024-96-r2	Watsonx	Chat	Input $0.380000 / 1M tokensOutput $0.380000 / 1M tokens	512	512
granite-ttm-1536-96-r2 watsonx/ibm/granite-ttm-1536-96-r2	Watsonx	Chat	Input $0.380000 / 1M tokensOutput $0.380000 / 1M tokens	512	512
granite-ttm-512-96-r2 watsonx/ibm/granite-ttm-512-96-r2	Watsonx	Chat	Input $0.380000 / 1M tokensOutput $0.380000 / 1M tokens	512	512
granite-vision-3-2-2b watsonx/ibm/granite-vision-3-2-2b	Watsonx	Chat	Input $0.100000 / 1M tokensOutput $0.100000 / 1M tokens	8,192	8,192	Vision
jais-13b-chat watsonx/core42/jais-13b-chat	Watsonx	Chat	Input $500.00 / 1M tokensOutput $0.002000 / 1M tokens	8,192	8,192
llama-3-2-11b-vision-instruct watsonx/meta-llama/llama-3-2-11b-vision-instruct	Watsonx	Chat	Input $0.350000 / 1M tokensOutput $0.350000 / 1M tokens	128k	128k	FunctionsVision
llama-3-2-1b-instruct watsonx/meta-llama/llama-3-2-1b-instruct	Watsonx	Chat	Input $0.100000 / 1M tokensOutput $0.100000 / 1M tokens	128k	128k	Functions
llama-3-2-3b-instruct watsonx/meta-llama/llama-3-2-3b-instruct	Watsonx	Chat	Input $0.150000 / 1M tokensOutput $0.150000 / 1M tokens	128k	128k	Functions
llama-3-2-90b-vision-instruct watsonx/meta-llama/llama-3-2-90b-vision-instruct	Watsonx	Chat	Input $2.00 / 1M tokensOutput $2.00 / 1M tokens	128k	128k	FunctionsVision
llama-3-3-70b-instruct watsonx/meta-llama/llama-3-3-70b-instruct	Watsonx	Chat	Input $0.752600 / 1M tokensOutput $0.752600 / 1M tokens	131k	131k	Functions
llama-4-maverick-17b watsonx/meta-llama/llama-4-maverick-17b	Watsonx	Chat	Input $0.371000 / 1M tokensOutput $1.48 / 1M tokens	131k	8,192	Functions
llama-4-maverick-17b-128e-instruct-fp8 watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8	Watsonx	Chat	Input $0.371000 / 1M tokensOutput $1.48 / 1M tokens	131k	8,192	Functions
llama-guard-3-11b-vision watsonx/meta-llama/llama-guard-3-11b-vision	Watsonx	Chat	Input $0.350000 / 1M tokensOutput $0.350000 / 1M tokens	128k	128k	Vision
mistral-large watsonx/mistralai/mistral-large	Watsonx	Chat	Input $3.00 / 1M tokensOutput $10.00 / 1M tokens	131k	16,384	Functions
mistral-medium-2505 watsonx/mistralai/mistral-medium-2505	Watsonx	Chat	Input $3.00 / 1M tokensOutput $10.00 / 1M tokens	128k	128k	Functions
mistral-small-2503 watsonx/mistralai/mistral-small-2503	Watsonx	Chat	Input $0.100000 / 1M tokensOutput $0.300000 / 1M tokens	32,000	32,000	Functions
mistral-small-3-1-24b-instruct-2503 watsonx/mistralai/mistral-small-3-1-24b-instruct-2503	Watsonx	Chat	Input $0.106000 / 1M tokensOutput $0.318000 / 1M tokens	131k	16,384	Functions
mt0-xxl watsonx/bigscience/mt0-xxl	Watsonx	Chat	Input $1.91 / 1M tokensOutput $1.91 / 1M tokens	4,096	4,096
mt0-xxl-13b watsonx/bigscience/mt0-xxl-13b	Watsonx	Chat	Input $1.91 / 1M tokensOutput $1.91 / 1M tokens	4,096	4,096
pixtral-12b-2409 watsonx/mistralai/pixtral-12b-2409	Watsonx	Chat	Input $0.350000 / 1M tokensOutput $0.350000 / 1M tokens	128k	128k	Vision
whisper-large-v3-turbo watsonx/whisper-large-v3-turbo	Watsonx	Audio Transcription	Input $0.00010000 / secondOutput $0.00010000 / second	,	,

Related Resources

Calculate Watsonx costs →