TokenRate

Qwen 2.5 72B Pricing

Balanced

Qwen · 131K tokens context

Qwen 2.5 72B from Qwen costs $0.360 per 1 million input tokens and $0.400 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 8K-token maximum output. A typical 1,000-token request costs $0.0004 in input charges; a 10,000-token request costs $0.0036.

Qwen 2.5 72B pricing and capability summary
Input price$0.360 / 1M tokens
Output price$0.400 / 1M tokens
Output / input ratio1.1×
Context window131,072 tokens (~98,304 words)
Maximum output8,192 tokens
Cost per 1K tokens (input)$0.0004
TierBalanced
Last verified

Qwen 2.5 72B is Alibaba's flagship open-weight model — surprisingly strong on coding and math benchmarks, competitive with GPT-4o class models at a fraction of the cost. A top choice for self-hosted general workloads.

Live pricing from OpenRouter

Input Price

$0.360

per 1 million tokens

Output Price

$0.400

per 1 million tokens

Context Window

131K tokens

max 8K output

Cost Examples

Request TypeTokensInput CostOutput Cost
1,000 word article1,333$0.00048$0.00016
10-page document (2,500 words)3,333$0.0012$0.0004
1,000 lines of code5,000$0.0018$0.0006
100K token document100,000$0.036$0.012

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

Strengths

  • Excellent coding and math benchmark scores
  • Open weights — self-hostable
  • Cheap at $0.35/1M input
  • Strong multilingual support (Chinese, Japanese, etc.)

Limitations

  • Less mature Western ecosystem
  • Below frontier on non-STEM tasks

Best Use Cases

Coding assistants on a budget
APAC multilingual apps
Self-hosted high-quality chat

Calculate Qwen 2.5 72B Costs

Use the TokenRate calculator to convert any budget, token count, or text into exact Qwen 2.5 72B costs — and compare across all models.

Open Calculator →

Qwen 2.5 72B — FAQ

Related Models

Related Guides