# Llama 3.3 70B API prices

Llama 3.3 70B (llama) — 131k context, 131k max output.
6 metered per-token offers from 6 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| STACKIT | $0.53 | $0.76 | — | 128k |
| Groq | $0.59 | $0.79 | — | 131k |
| Weights & Biases | $0.71 | $0.71 | $0.71 | 128k |
| Together AI | $1.04 | $1.04 | — | 131k |
| Venice AI | $0.7 | $2.8 | — | 128k |
| NanoGPT | $1.75 | $2.75 | $1.75 | 128k |

## Summary

- Cheapest input: $0.53 per 1M tokens (STACKIT)
- Cheapest output: $0.71 per 1M tokens (Weights & Biases)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2024-12-06
- Inputs: text

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