# Qwen/Qwen2.5-72B-Instruct API prices

Qwen/Qwen2.5-72B-Instruct (qwen) — 33k context, 4k max output.
2 metered per-token offers from 2 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| SiliconFlow | $0.59 | $0.59 | — | 33k |
| SiliconFlow (China) | $0.59 | $0.59 | — | 33k |

## Summary

- Cheapest input: $0.59 per 1M tokens (SiliconFlow)
- Cheapest output: $0.59 per 1M tokens (SiliconFlow)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2024-09-18
- Inputs: text

HTML page: https://llmprice.gitlab.io/models/qwen-qwen2-5-72b-instruct/
Full dataset: https://llmprice.gitlab.io/data/catalog.json