Qwen2.5 VL 72B
StandardLarge 72B vision-language model from Qwen 2.5 generation.
Strong at visual understanding, document parsing, and image QA. Good multimodal model for complex visual reasoning tasks.
▼
Qwen2.5 VL 72B by Qwen has a Capability Index of 62.8, making it below the field average in capability. It ranks #65 out of 92 models on the idapt capability leaderboard. Qwen2.5 VL 72B is somewhat expensive at $0.80/M tokens input and $1.00/M tokens output. Cached input reads are priced at $0.40/M tokens, making repeated context cheaper. The model supports vision/image input, a 128K context window.
Benchmarks
Category Rankings
Specifications
Performance
Providers
Misc
Compare with
GPT 5.6 Solvs Qwen2.5 VL 72BGPT 5.6 Lunavs Qwen2.5 VL 72B
Claude Fable 5vs Qwen2.5 VL 72BClaude Opus 4.8vs Qwen2.5 VL 72BClaude Sonnet 5vs Qwen2.5 VL 72BClaude Haiku 4.5vs Qwen2.5 VL 72B
Gemini 3.6 Flashvs Qwen2.5 VL 72BGemini 3.5 Flashvs Qwen2.5 VL 72BGemini 3.5 Flash-Litevs Qwen2.5 VL 72BGemma 4 31Bvs Qwen2.5 VL 72B
Grok 4.5vs Qwen2.5 VL 72BGrok Build 0.1vs Qwen2.5 VL 72BGrok 4.1 Fastvs Qwen2.5 VL 72B
Muse Spark 1.1vs Qwen2.5 VL 72B
DeepSeek V4 Provs Qwen2.5 VL 72BDeepSeek V4 Flashvs Qwen2.5 VL 72B
MiniMax M3vs Qwen2.5 VL 72B
GLM 5.2vs Qwen2.5 VL 72B
Qwen3.7 Maxvs Qwen2.5 VL 72BQwen3.7 Plusvs Qwen2.5 VL 72BQwen3 Coder Nextvs Qwen2.5 VL 72B
Nemotron 3 Ultravs Qwen2.5 VL 72B
Mistral Small 4vs Qwen2.5 VL 72BFrequently Asked Questions about Qwen2.5 VL 72B▼
When was Qwen2.5 VL 72B released?
▼
Qwen2.5 VL 72B was released on February 1, 2025.
Who created Qwen2.5 VL 72B?
▼
Qwen2.5 VL 72B was created by Qwen.
How capable is Qwen2.5 VL 72B?
▼
Qwen2.5 VL 72B has a Capability Index of 62.8/100, making it below the field average in capability. It ranks #65 out of 92 models.
How much does Qwen2.5 VL 72B cost?
▼
Qwen2.5 VL 72B costs $0.80/M input tokens and $1.00/M output tokens.
What is Qwen2.5 VL 72B API pricing?
▼
The Qwen2.5 VL 72B API is priced at $0.80 per million input tokens and $1.00 per million output tokens. You can access Qwen2.5 VL 72B through idapt.app alongside 200+ other AI models in one workspace.
Is Qwen2.5 VL 72B a reasoning model?
▼
No, Qwen2.5 VL 72B is not a reasoning model. It responds directly without an extended internal thinking step. For tasks requiring deep chain-of-thought reasoning, consider models like Claude, o-series from OpenAI, or Gemini Thinking.
Does Qwen2.5 VL 72B support image or vision input?
▼
Yes, Qwen2.5 VL 72B supports vision/image input. You can share images in your conversation and the model will analyze and respond based on their content.
Does Qwen2.5 VL 72B support audio?
▼
No, Qwen2.5 VL 72B does not support audio input.
What is the context window of Qwen2.5 VL 72B?
▼
Qwen2.5 VL 72B has a context window of 128K tokens, meaning it can process approximately 96,000 words of context at once.
Is Qwen2.5 VL 72B open source?
▼
Qwen2.5 VL 72B is a proprietary model developed by Qwen. The model weights and training data are not publicly available.
What is Qwen2.5 VL 72B good at?
▼
Based on benchmark data, Qwen2.5 VL 72B excels at: visual analysis and image understanding. It is Qwen's capable model suitable for a wide range of tasks.
Where can I use Qwen2.5 VL 72B?
▼
You can chat with Qwen2.5 VL 72B on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access Qwen2.5 VL 72B through Qwen's own API or platform.