Qwen2.5-VL 72B Instruct
AlibabaOpen weights
Qwen2.5-VL 72B Instruct by Alibaba costs $2.80 per 1M input tokens and $8.40 per 1M output tokens, with a 131K-token context window.
Pricing
Input (per 1M tokens)
$2.80
Output (per 1M tokens)
$8.40
Cached input (per 1M)
—
Specifications
- Provider
- Alibaba
- Context window
- 131K tokens
- Parameters
- —
- Released
- Sep 2024
- Open weights
- Yes
- Frontier model
- No
Benchmarks
- LMArena Vision Elo
- 1107.4
Compare Qwen2.5-VL 72B Instruct with…
Qwen2.5-VL 72B Instruct vs Kimi K2 Thinking Turbo$8.00/1MQwen2.5-VL 72B Instruct vs GPT-4.1$8.00/1MQwen2.5-VL 72B Instruct vs o3$8.00/1MQwen2.5-VL 72B Instruct vs Gemini 3.5 Flash$9.00/1MQwen2.5-VL 72B Instruct vs Qwen3.6 Max Preview$7.80/1MQwen2.5-VL 72B Instruct vs Qwen3-Coder 480B-A35B Instruct$7.50/1M
FAQ
How much does Qwen2.5-VL 72B Instruct cost?
Qwen2.5-VL 72B Instruct is priced at $2.80 per 1M input tokens and $8.40 per 1M output tokens. Output tokens cost more than input.
What is Qwen2.5-VL 72B Instruct's context window?
Qwen2.5-VL 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-VL 72B Instruct open weight?
Yes — Qwen2.5-VL 72B Instruct has openly available weights.
Data as of 2026-10-15. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.