MPT-Chat (30B) overview
MPT-Chat (30B) by Mosaic ML
Explore MPT-Chat (30B) API : an efficient, scalable, and ethically designed open-source language model.
MPT-Chat (30B) specs
- Developer
- Mosaic ML
- Input
- Text
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
Basic Information
- Developer/Creator: MosaicML, part of Databricks
- Model Type: Text-based Language Model
Overview
MPT-Chat (30B) is an advanced, open-source language model designed for a broad spectrum of natural language processing tasks, emphasizing efficiency, scalability, and ethical AI practices.
Key Features
- Decoder-only transformer architecture.
- Large model size with 30 billion parameters.
- Supports a context window of up to 8,192 tokens.
- Utilizes innovative techniques like FlashAttention and ALiBi.
Language Support
Currently, detailed language support specifics are not provided; however, it typically includes major global languages given its extensive training data.
Architecture
MPT-Chat (30B) employs a decoder-only transformer architecture, similar to GPT models, enhanced with modern techniques like FlashAttention for efficient attention computation and ALiBi for positional biases, which facilitate better scaling and performance.
Training Data
The model was trained on a curated dataset of 1 trillion tokens, encompassing a wide range of internet text to ensure relevance and diversity.
Use cases
- chatbots and virtual assistants capable of multi-turn, context-aware conversations
- content generation including creative writing, summarization, and explanation
- instruction following for complex task automation
- coding assistance including code completion and review
- long-form document processing such as legal, technical, and academic text
- research and development of advanced LLM applications with ethical considerations
- deployment on enterprise applications requiring high performance and scalability
Capabilities
- Function calling
- Streaming
- Structured outputs
MPT-Chat (30B) API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $0.84 | 1M tokens |
| Output | $0.84 | 1M tokens |
MPT-Chat (30B) is deprecated on AI/ML API. The rates apply to existing integrations; the models below are current alternatives.
Prices from the AI/ML API price list, checked on Nov 4, 2026.
MPT-Chat (30B) vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
 MPT-Chat (30B) | $0.84 | $0.84 |
 Mercury 2.5 | $0.2116 | $0.7935 |
| Mercury 2 | $0.2645 | $0.7935 |
 Hy3 | $0.2116 | $0.8464 |
| Skyfall 36B V2 | $0.5819 | $0.8464 |
Models similar to MPT-Chat (30B)
Related articles
MPT-Chat (30B) FAQ
Does MPT-Chat (30B) support streaming?
Yes, MPT-Chat (30B) can stream responses as they are generated.
Does MPT-Chat (30B) support tool calling and structured outputs?
Yes, MPT-Chat (30B) supports both function calling and structured outputs.
Who created MPT-Chat (30B)?
MPT-Chat (30B) was built by Mosaic ML.