# Llama 3.1 8B API prices

Llama 3.1 8B (llama) — 131k context, 131k max output.
3 metered per-token offers from 3 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Groq | $0.05 | $0.08 | — | 131k |
| Merge Gateway | $0.22 | $0.22 | — | 128k |
| Weights & Biases | $0.22 | $0.22 | $0.22 | 131k |

## Summary

- Cheapest input: $0.05 per 1M tokens (Groq)
- Cheapest output: $0.08 per 1M tokens (Groq)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2024-07-23
- Inputs: text

HTML page: https://llmprice.gitlab.io/models/llama-3-1-8b/
Full dataset: https://llmprice.gitlab.io/data/catalog.json