Qwen2.5 72B
Qwen's flagship open dense model — strong instruction following, math, and coding in a 72B package.
Pricing
InputOpen weights / ~$0.35 / 1M hosted
OutputOpen weights / ~$0.40 / 1M hosted
Cost bandFree/open
Free tierOpen weights (Apache 2.0).
Limits
Context window131k
Max outputRuntime-dependent
Knowledge cutoffQ2 2024
DeploymentSelf-hosted, Hugging Face, Together, Hyperbolic
OpenAI-compatible APIYes
ModalitiesText
Where it fits
Best forSelf-hosted general-purpose workloads where a well-tuned open model beats smaller alternatives.
Business fitOne of the strongest general open models at the 70B tier alongside Llama 3.3 70B.
Capabilities
Open weights (Apache 2.0)Function callingMathCoding
Benchmark scores
Composite78 / 100
Coding80 / 100 (LiveCodeBench)
Reasoning78 / 100 (MMLU-Pro)
Long context74 / 100 (RULER 128K)
Instruction following80 / 100 (IFEval)
Editorial aggregate of published benchmark results as of Nov 1, 2024. These are not independent measurements run by this site.
Change history
No recorded changes for this model yet. Pricing and context are checked daily; changes appear here with dates and sources.
Data
Last checkedJan 10, 2026
Verify with provider documentation before committing spend. Report an error and it gets fixed with a logged correction.