TokenRate

Qwen2.5 VL 72B Instruct Pricing

Flagship

Qwen · 131K tokens context

Qwen2.5 VL 72B Instruct from Qwen costs $0.250 per 1 million input tokens and $0.750 per 1 million output tokens as of June 2026 (live OpenRouter data). The model supports a 131,072-token context window (approximately 98,304 words) with a 32K-token maximum output. A typical 1,000-token request costs $0.0003 in input charges; a 10,000-token request costs $0.0025.

Qwen2.5 VL 72B Instruct pricing and capability summary
Input price$0.250 / 1M tokens
Output price$0.750 / 1M tokens
Output / input ratio3.0×
Context window131,072 tokens (~98,304 words)
Maximum output32,000 tokens
Cost per 1K tokens (input)$0.0003
TierFlagship
Last verified

Qwen2. 5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects.

Live pricing from OpenRouter

Input Price

$0.250

per 1 million tokens

Output Price

$0.750

per 1 million tokens

Context Window

131K tokens

max 32K output

Cost Examples

Request TypeTokensInput CostOutput Cost
1,000 word article1,333$0.000333$0.0003
10-page document (2,500 words)3,333$0.000833$0.00075
1,000 lines of code5,000$0.00125$0.00112
100K token document100,000$0.025$0.0225

Output cost estimated at 30% of input token count. Use the calculator for exact figures.

Strengths

  • Affordable at $0.25/1M input tokens
  • Frontier-class quality on complex tasks
  • Multimodal: understands images as well as text

Limitations

  • Quality and availability can vary by hosting provider
  • Quality and availability can vary by hosting provider

Best Use Cases

Complex research and analysis
Advanced coding and architecture
Multimodal document understanding
High-stakes production workloads

Calculate Qwen2.5 VL 72B Instruct Costs

Use the TokenRate calculator to convert any budget, token count, or text into exact Qwen2.5 VL 72B Instruct costs — and compare across all models.

Open Calculator →

Qwen2.5 VL 72B Instruct — FAQ

Related Models

Related Guides