IBM watsonx API pricing
Cloud30 language models
As of Oct 14, 2026, IBM watsonx lists 30 language models through its API. Its cheapest language model is Llama 3.2 1B Instruct at $0.10 input / $0.10 output per million tokens.
Language models (30)
Prices per million tokens.
watsonx/openai/gpt-oss-120b
- Input
- $0.159
- Output
- $0.636
- Context
- 131K
watsonx/meta-llama/llama-3-2-1b-instruct
- Input
- $0.10
- Output
- $0.10
- Context
- 128K
watsonx/meta-llama/llama-3-2-3b-instruct
- Input
- $0.15
- Output
- $0.15
- Context
- 128K
watsonx/meta-llama/llama-3-2-11b-vision-instruct
- Input
- $0.35
- Output
- $0.35
- Context
- 128K
watsonx/meta-llama/llama-3-3-70b-instruct
- Input
- $0.7526
- Output
- $0.7526
- Context
- 131K
Llama 4 Maverick 17B 128e Instruct Fp8
watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8
- Input
- $0.371
- Output
- $1.48
- Context
- 131K
watsonx/mistralai/mistral-large
- Input
- $3.00
- Output
- $10.00
- Context
- 131K
watsonx/mistralai/mistral-small-2503
- Input
- $0.10
- Output
- $0.30
- Context
- 32K
Allam 1 13B Instruct
watsonx/sdaia/allam-1-13b-instruct
- Input
- $1.80
- Output
- $1.80
- Context
- 8K
Flan T5 Xl 3B
watsonx/google/flan-t5-xl-3b
- Input
- $0.60
- Output
- $0.60
- Context
- 8K
Granite 3 8B Instruct
watsonx/ibm/granite-3-8b-instruct
- Input
- $0.20
- Output
- $0.20
- Context
- 8K
Granite 3.3 8B Instruct
watsonx/ibm/granite-3-3-8b-instruct
- Input
- $0.20
- Output
- $0.20
- Context
- 8K
Granite 4 H Small
watsonx/ibm/granite-4-h-small
- Input
- $0.0636
- Output
- $0.265
- Context
- 131K
Granite 13B Chat V2
watsonx/ibm/granite-13b-chat-v2
- Input
- $0.60
- Output
- $0.60
- Context
- 8K
Granite 13B Instruct V2
watsonx/ibm/granite-13b-instruct-v2
- Input
- $0.60
- Output
- $0.60
- Context
- 8K
Granite Guardian 3.2 2B
watsonx/ibm/granite-guardian-3-2-2b
- Input
- $0.10
- Output
- $0.10
- Context
- 8K
Granite Guardian 3.3 8B
watsonx/ibm/granite-guardian-3-3-8b
- Input
- $0.20
- Output
- $0.20
- Context
- 8K
Granite Ttm 512.96 R2
watsonx/ibm/granite-ttm-512-96-r2
- Input
- $0.38
- Output
- $0.38
- Context
- 512
Granite Ttm 1024.96 R2
watsonx/ibm/granite-ttm-1024-96-r2
- Input
- $0.38
- Output
- $0.38
- Context
- 512
Granite Ttm 1536.96 R2
watsonx/ibm/granite-ttm-1536-96-r2
- Input
- $0.38
- Output
- $0.38
- Context
- 512
Granite Vision 3.2 2B
watsonx/ibm/granite-vision-3-2-2b
- Input
- $0.10
- Output
- $0.10
- Context
- 8K
Jais 13B Chat
watsonx/core42/jais-13b-chat
- Input
- $500.00
- Output
- $2,000.00
- Context
- 8K
Llama 3.2 90B Vision Instruct
watsonx/meta-llama/llama-3-2-90b-vision-instruct
- Input
- $2.00
- Output
- $2.00
- Context
- 128K
Llama 4 Maverick 17B
watsonx/meta-llama/llama-4-maverick-17b
- Input
- $0.371
- Output
- $1.48
- Context
- 131K
Llama Guard 3 11B Vision
watsonx/meta-llama/llama-guard-3-11b-vision
- Input
- $0.35
- Output
- $0.35
- Context
- 128K
Mistral Medium 2505
watsonx/mistralai/mistral-medium-2505
- Input
- $3.00
- Output
- $10.00
- Context
- 128K
Mistral Small 3.1 24B Instruct 2503
watsonx/mistralai/mistral-small-3-1-24b-instruct-2503
- Input
- $0.106
- Output
- $0.318
- Context
- 131K
Mt0 Xxl
watsonx/bigscience/mt0-xxl
- Input
- $1.91
- Output
- $1.91
- Context
- 4K
Mt0 Xxl 13B
watsonx/bigscience/mt0-xxl-13b
- Input
- $1.91
- Output
- $1.91
- Context
- 4K
Pixtral 12B 2409
watsonx/mistralai/pixtral-12b-2409
- Input
- $0.35
- Output
- $0.35
- Context
- 128K
Prices in USD from LiteLLM and models.dev, checked daily; confirm on IBM watsonx's pricing page before you rely on a number.