Qwen2.5 72B Instruct
Provider: Alibaba (Qwen) CN
Input price
$0.29
/ 1M tokens
Output price
$0.32
/ 1M tokens
Context
33K tokens
Max output 16K tokens
Overview
Alibaba's flagship 72B dense model targets general instruction following, coding, and structured data tasks within a 32K context window.
Strengths
- Native function-calling and JSON mode support
- Knowledge cutoff date of June 2024
- 16384 token maximum output capacity
Best use cases
- Parsing structured JSON outputs reliably
- Executing function-calling routines
- General instruction-following pipelines
Pricing position
Priced at $0.288/1M input and $0.32/1M output, matching DeepSeek V3.2's input rate while offering lower output costs.
Caveats
Context window is limited to 32K tokens, trailing behind newer Alibaba models with 256K to 1M limits.
Notes drafted by an LLM from the figures on this page (2026-11-15) and rewritten when the price changes.
Key facts
- Price basis
- Median third-party host price (no first-party API)
- Max output
- 16K tokens
- Knowledge cutoff
- 2024-06-30
- Listed on OpenRouter
- 2024-09-19
- Tracked since
- 2026-05-08
- Last updated
- 2026-11-15
Features
Function callingJSON output
Price history
- 2026-11-15 Price change $0.36 / $0.40 → $0.29 / $0.32
Monthly cost estimate
| Scale | Input (M) | Output (M) | Monthly |
|---|---|---|---|
| 0.1M (hobby) | 0.1 | 0.05 | $0.04 |
| 1M (small app) | 1 | 0.5 | $0.45 |
| 10M (mid scale) | 10 | 5 | $4.48 |
| 100M (large) | 100 | 50 | $44.80 |
※ Cache and batch discounts not factored in. Detailed calculator
Official resources
Other models from Alibaba (Qwen)
Similar-priced models
Source: OpenRouter API (qwen/qwen-2.5-72b-instruct)