Last refreshed 2026-04-15. Next refresh: weekly.
Why use MPT 30B on Databricks Foundation Model Serving?
Databricks Foundation Model Serving offers MPT 30B with pay-as-you-go pricing at $1.00/1M input tokens. Databricks offers a comprehensive Data Intelligence Platform that unifies data, analytics, and AI capabilities.
Setup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: mpt-30bmpt-30bRequest example
mpt-30b.Gotchas
No curated gotchas have been sourced for this exact provider/model route yet.
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $1.00 |
| Output tokens | $1.00 |
Capabilities
No model capability flags are currently sourced.
About MPT 30B
MPT-30B, developed by MosaicML, is a powerful large language model (LLM) utilizing a decoder-only transformer architecture that excels in predicting the next word in a sequence. This model is particularly adept at handling various NLP tasks, such as text generation, question answering, summarization, and code generation, due to its training on a diverse dataset of 1 trillion tokens of English text and code. Notable architectural innovations like FlashAttention, ALiBi, and no biases contribute to its enhanced efficiency, allowing for operation on a single high-end GPU. Moreover, MPT-30B offers fine-tuned variants like mpt-30b-instruct and mpt-30b-chat, catering to specialized tasks like instruction following and dialogue generation, and is available for commercial use.
FAQ
What does MPT 30B cost on Databricks Foundation Model Serving?
On Databricks Foundation Model Serving, MPT 30B costs $1 per 1M input tokens and $1 per 1M output tokens.
Who created MPT 30B?
MPT 30B was created by Databricks Mosaic as part of the MPT model family.
Is MPT 30B open source?
MPT 30B's open source status is unknown in the seed data.