# Qwen 2.5 72B Instruct API prices

Qwen 2.5 72B Instruct (qwen) — 128k context, 8k max output.
2 metered per-token offers from 2 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Abacus | $0.11 | $0.38 | — | 128k |
| NovitaAI | $0.38 | $0.4 | — | 32k |

## Summary

- Cheapest input: $0.11 per 1M tokens (Abacus)
- Cheapest output: $0.38 per 1M tokens (Abacus)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2024-09-19
- Inputs: text

## FAQ

### What is the cheapest Qwen 2.5 72B Instruct API?

As of Oct 4, 2026, Abacus has the lowest Qwen 2.5 72B Instruct output price at $0.38 per 1M tokens, and Abacus has the lowest input price at $0.11 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer Qwen 2.5 72B Instruct?

2 providers list Qwen 2.5 72B Instruct on Sovyron; 2 of them sell it at a metered per-token price.

### Is Qwen 2.5 72B Instruct free?

No provider in the Sovyron catalog lists a free tier for Qwen 2.5 72B Instruct.

### What is the context window of Qwen 2.5 72B Instruct?

Qwen 2.5 72B Instruct supports a 128k-token context window and up to 8k output tokens.

HTML page: https://sovyron.com/models/qwen-2-5-72b-instruct/
Full dataset: https://sovyron.com/data/catalog.json