Last refreshed 2026-05-19. Next refresh: weekly.
Why use MT0 XXL on IBM watsonx?
IBM watsonx offers MT0 XXL with pay-as-you-go pricing at $1.80/1M input tokens. IBM offers a comprehensive AI platform that includes IBM watsonx, a next-generation enterprise AI and data platform.
Setup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: mt0-xxlmt0-xxlRequest example
mt0-xxl.Gotchas
No curated gotchas have been sourced for this exact provider/model route yet.
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $1.80 |
| Output tokens | $1.80 |
Capabilities
No model capability flags are currently sourced.
About MT0 XXL
The MT0 XXL model, part of the BLOOMZ and mT0 family developed by the BigScience workshop, is a large language AI model designed for multilingual applications with zero-shot capabilities. It features 13.9 billion parameters and is built on a transformer architecture with an encoder-decoder structure. Trained with a multitask finetuning approach using the xP3 dataset, MT0 XXL excels in tasks such as translation, question answering, text generation, and summarization. Although powerful, the model's performance hinges on prompt specificity and the diversity of its training data. Running the model can be resource-intensive, which might limit its accessibility for smaller entities 1.
FAQ
What does MT0 XXL cost on IBM watsonx?
On IBM watsonx, MT0 XXL costs $1.8 per 1M input tokens and $1.8 per 1M output tokens.
What is the context window for MT0 XXL on IBM watsonx?
MT0 XXL supports a 1k token context window on IBM watsonx.
Who created MT0 XXL?
MT0 XXL was created by BigScience as part of the MT0 model family.
Is MT0 XXL open source?
MT0 XXL is open source under Apache 2.0 according to the seed data.