Sample data: Phase-1 sample snapshot. Official crawling and weekly benchmark jobs are not connected yet. All price, latency and score values validate the product structure only and must be replaced by traceable production data before launch.

Home / Pricing / Qwen 2.5 72B

Qwen 2.5 72B

Chinese-language performance is weighted higher in the Chinese task bucket.

Input
$0.35/1M
Output
$0.70/1M
TTFT
156ms
Context
128K

Source and version

This page uses phase-1 sample data. Before launch, every data point must show official or measured source, crawl/test time, benchmark version and methodology link.

Task performance

Coding

Repository edits, bug fixes, unit-test reasoning and API usage.

81Writing

Product copy, long-form prose, editing and tone control.

83Translation

Bidirectional English/Chinese translation with terminology consistency.

84Math

Word problems, algebraic reasoning and structured calculation.

81Tool Calling

JSON output, function selection and multi-step tool use.

81Chinese

Chinese writing, knowledge, instructions and domestic model coverage.

88

Use and disclosure

The use link is a placeholder. Rankings must never be affected by affiliate relationships, and production affiliate links require clear disclosure.

Use model

Price alert

Similar models

Turn model selection into a reviewable data workflow

Phase 1 has the interface, data fields and API skeleton; the next phase connects real crawlers, benchmark jobs and storage.

MethodologyPro