# Llama 3.1 70B Instruct API prices

Llama 3.1 70B Instruct (llama) — 131k context, 16k max output.
7 metered per-token offers from 7 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Kilo Gateway | $0.4 | $0.4 | — | 131k |
| OpenRouter | $0.4 | $0.4 | — | 131k |
| Amazon Bedrock | $0.72 | $0.72 | — | 128k |
| Amazon Bedrock (us) | $0.72 | $0.72 | — | 128k |
| DevPass (LLM Gateway) | $0.72 | $0.72 | — | 128k |
| LLM Gateway | $0.72 | $0.72 | — | 128k |
| Vercel AI Gateway | $0.72 | $0.72 | — | 128k |

## Summary

- Cheapest input: $0.4 per 1M tokens (Kilo Gateway)
- Cheapest output: $0.4 per 1M tokens (Kilo Gateway)
- First-party: not listed separately
- Free offers: Nvidia
- Subscription plans (not per-token): none
- Released: 2024-07-23
- Inputs: text

HTML page: https://llmprice.gitlab.io/models/llama-3-1-70b-instruct/
Full dataset: https://llmprice.gitlab.io/data/catalog.json