llama-3.1-8b-instruct-awq
meta
Quantized (int4) generative text model with 8 billion parameters from Meta.
- Context window
- 8,192 tokens
- Input cost
- $0.12 / 1M
- Output cost
- $0.27 / 1M
- Latency (p50)
- —
Compare Models
Run side-by-side checks for pricing, context window, and latency.