Llama 3.1 8B
Meta • Llama 3.1 • Best for: Cheap open‑weight deployments
stable open-weightself-hosting
Pricing
- Input
- $0.10 / 1M tokens
- Output
- $0.10 / 1M tokens
Context
128,000 tokens
Always verify context limits and special tiers (images, tools, streaming) in the official docs.
Usage notes
Smaller Llama 3.1 model suitable for self‑hosting and budget‑sensitive workloads.