Mistral Tiny
Detailed specifications for implementing Mistral Tiny in your RAG applications.
Model Overview
Released:January 10, 2024
This model is built on the Mistral-7B-v0.2 architecture and features enhanced fine-tuning, drawing inspiration from community-driven advancements to deliver improved performance over its predecessor, Mistral 7B. It is particularly well-suited for high-volume batch processing tasks where cost efficiency is a priority, and advanced reasoning capabilities are not a primary requirement.
Architecture
- Modality
- text->text
- Tokenizer
- Mistral
Pricing
| Operation | Rate |
|---|---|
| Prompt | 0.00000025 |
| Completion | 0.00000025 |
| Image | 0 |
| Request | 0 |
Provider Details
- Context Length
- 32,000 tokens
- Max Completion
- 0 tokens
- Moderation
- Not Enabled
Ready to implement Mistral Tiny?
Start building powerful RAG applications with our flexible pricing plans and developer-friendly API.