Qwen2.5 VL 72B Instruct
Alibaba · Multimodal · Released Feb 2025
A 72-billion-parameter dense language model from Alibaba, instruction-tuned for general-purpose conversation and tasks.
- Strengths
- Handles long-form reasoning and complex multi-step tasks with its 128k-token context window, giving it significantly more room than its Qwen2.5 siblings.
- Best for
- Workloads requiring sustained context over longer documents, conversations, or multi-part queries where the extended window is a concrete advantage.
- Limitations
- Superseded by the Qwen3 line (released 2025), which offers higher parameter counts, mixture-of-experts efficiency, and in some cases longer context windows; not specialized for code or vision tasks.
Input / 1M
$0.8
Output / 1M
$1.00
Cached input / 1M
$0.4
Context window
128K
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in — out —
- 90d
- in decreased 0.0% out decreased 0.0%
- 1y
- in increased 220.0% out increased 33.3%
- Since launch
- in increased 220.0% out increased 33.3%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 3 Sep 2026 | $0.8 | $1.00 | $0.4 | Imported from OpenRouter | openrouter.ai |
| 27 Aug 2026 | $0.25 | $0.75 | — | Imported from OpenRouter | openrouter.ai |
| 26 Aug 2026 | $0.25 | $0.75 | — | Imported from OpenRouter | openrouter.ai |
| 16 Aug 2026 | $0.8 | $1.00 | $0.4 | Imported from OpenRouter | openrouter.ai |
| 4 Aug 2026 | $0.25 | $0.75 | — | Imported from OpenRouter | openrouter.ai |
| 15 Jul 2026 | $0.8 | $1.00 | $0.4 | Imported from OpenRouter | openrouter.ai |
| 12 Jul 2026 | $0.25 | $0.75 | — | Imported from OpenRouter | openrouter.ai |
| 12 Jun 2026 | $0.8 | $1.00 | $0.4 | Imported from OpenRouter | openrouter.ai |
| 11 Jun 2026 | $0.25 | $0.75 | — | Imported from OpenRouter | openrouter.ai |