From Mistral: An experimental specialized small model trained on meticulously curated data, designed for creative writing, narrative generation, roleplay and character-driven dialog, general-purpose instruction following and conversational agents.
The smaller Mistral models don’t get nearly enough love. For my use case (https://winterscience.com) of turning structured data points into consumable text, they way outperform other models in their cost tier. Only $0.1/M input $0.3/M output.
This is an interesting model. I have an embodied AI companion app on the App Store that uses Gemini 2.0 Flash. However, I've been searching for a model that is comparable to 2.0 Flash in cost with more creative and less repetitive outputs. The frontier labs have only gone up in cost and latency, and are ignoring use cases like this. This seems promising, I plan to try it in production.
cmoriam|2 months ago
The smaller Mistral models don’t get nearly enough love. For my use case (https://winterscience.com) of turning structured data points into consumable text, they way outperform other models in their cost tier. Only $0.1/M input $0.3/M output.
Eldodi|2 months ago
deeznuttynutz|2 months ago