LLM Reference
Fireworks AI

Hermes 2 Pro Mistral 7B on Fireworks AI

Hermes 2 · Nous Research

Provisioned

Pricing

TypePrice (per 1M)
Input tokens$0.20
Output tokens$0.20

Capabilities

VisionMultimodalReasoningFunction CallingTool UseJSON ModeCode Execution

About Hermes 2 Pro Mistral 7B

7B Hermes on Mistral architecture with 90-91% function calling accuracy and 84% JSON generation accuracy. Supports ChatML for structured multi-turn interactions.

Get Started

Model Specs

Released2023-12-12
Parameters7B
Context32K
ArchitectureDecoder Only
Knowledge cutoff2023-12