Qwen
Qwen2.5 VL 72B Instruct
Structured outputImage input
- Context
- 128K
- Released
- 1y ago
- Parameters
- 72B
- Input / 1M tokens
- $0.80
- Output / 1M tokens
- $1.00
- Cached input / 1M tokens
- $0.40
Sources:OpenRouter
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
No benchmark results have been matched to this model yet.
Specifications
- Developer
- Qwen
- Model family
- Qwen
- Type
- Language model
- Predecessor
- —
- Successor
- —
- Released
- January 26, 2025
- Model ID
qwen/qwen2.5-vl-72b-instruct- Openness
- Open weights
- License
- —
- Parameters
- 72B
- Input modalities
- text, image
- Output modalities
- text
- Modality
- text+image->text
- Tokenizer
- Qwen
- Max output tokens
- 115K
- Knowledge cutoff
- 2024-06-30
- Hugging Face
- Qwen/Qwen2.5-VL-72B-Instruct
- Source freshness
- Endpoints synced Oct 15, 2026, 8:17 AM UTC
Infrastructure
Provider availability
| Provider | Endpoint | Context | Input /M tokens | Output /M tokens | Cached input /M tokens | Cache write /M tokens | Uptime 1d | Data handling |
|---|---|---|---|---|---|---|---|---|
| parasail/fp8 | 128K | $0.80 | $1.00 | $0.40 | — | 99.93% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 |
Provider data:OpenRouter
Deployment graph
Can I run this?
Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.