MPT 7B is Mosaicml's language model. A 7B-parameter open-source LLM from MosaicML built on the MPT architecture with support for long context and commercial use.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Cheapest Instances to Run It
Cloud GPU instances that can host MPT 7B, ranked by cheapest on-demand price. The model needs about 17 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| g2-standard-4 |  GCP | nvidia-l4 | 24 GB | $0.705/hr | us-east4 | |
| g6.xlarge |  AWS | L4 | 22 GB | $0.805/hr | us-east-1 | |
| g2-standard-8 | GCP | nvidia-l4 | 24 GB | $0.851/hr | us-east4 | |
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| MPT 7B | — | — | — | — | Current |
| MPT 30B Instruct | — | 8K | $1.00 | $1.00 | Available |
| MPT 7B Instruct | — | 8K | $0.500 | — | Available |
| MPT 7B Instruct | — | — | — | — | Available |
| MPT 7B StoryWriter | — | — | — | — | Available |