Mistral 7B v0.3

Model Specifications

Context Window 32k tokens

Parameters 7.3B

Pricing (Input) $0.20 / M tokens

Pricing (Output) $0.60 / M tokens

What is Mistral 7B v0.3?

Mistral 7B v0.3 is the updated version of Mistral AI’s popular 7B open-weight model. Released in May 2024, it introduces support for function calling, a larger vocabulary size, and a 32k context window.

It remains a popular choice for local development, edge computing, and lightweight hosting configurations.

Key Capabilities

Function calling support: Can interface with external APIs.
Apache 2.0 License: Fully open for commercial modification and hosting.
Efficient memory footprint: Runs easily on small consumer GPUs.

Ideal Use Cases

On-device AI assistants: Deploying local models on laptops or edge devices.
API orchestration: Parsing inputs to route requests.
Simple content creation: Generating drafts and summaries.

Historical figures, architectures, and capabilities are for informational purposes only. Not technical, professional, legal, or financial advice. Sources: Benchmark evaluations derived from public developer statements.