Qwen2.5 72B Instruct
AlibabaOpen weights
Qwen2.5 72B Instruct by Alibaba costs $1.40 per 1M input tokens and $5.60 per 1M output tokens, with a 131K-token context window.
Pricing
Input (per 1M tokens)
$1.40
Output (per 1M tokens)
$5.60
Cached input (per 1M)
—
Specifications
- Provider
- Alibaba
- Context window
- 131K tokens
- Parameters
- —
- Released
- Sep 2024
- Open weights
- Yes
- Frontier model
- No
Benchmarks
- GPQA Diamond
- 49.1
Compare Qwen2.5 72B Instruct with…
Qwen2.5 72B Instruct vs Alibaba: Wan 3.0 Prime$0.00/1MQwen2.5 72B Instruct vs Alibaba: Wan 3.0$0.00/1MQwen2.5 72B Instruct vs Alibaba: Wan 2.7$0.00/1MQwen2.5 72B Instruct vs Alibaba: Wan 2.6$0.00/1MQwen2.5 72B Instruct vs Alibaba: HappyHorse 1.1$0.00/1MQwen2.5 72B Instruct vs Alibaba: HappyHorse 1.0$0.00/1M
FAQ
How much does Qwen2.5 72B Instruct cost?
Qwen2.5 72B Instruct is priced at $1.40 per 1M input tokens and $5.60 per 1M output tokens. Output tokens cost more than input.
What is Qwen2.5 72B Instruct's context window?
Qwen2.5 72B Instruct supports a context window of 131K tokens — the maximum prompt plus response length it can handle in a single request.
Is Qwen2.5 72B Instruct open weight?
Yes — Qwen2.5 72B Instruct has openly available weights.
Data as of 2026-10-14. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.