Skip to content

GLM-4.7 vs gpt-oss-20b

gpt-oss-20b is cheaper on output tokens, while GLM-4.7 offers a larger context window. Choose GLM-4.7 or gpt-oss-20b based on the trade-off between cost, context, and the benchmarks that matter for your use case.

SpecGLM-4.7gpt-oss-20b
ProviderOpenRouterOpenRouter
Input / 1M tokens$0.40$0.03
Output / 1M tokens$1.75$0.14
Context window203K131K
Parameters358B21B
Open weightsYesYes
ReleasedDec 2025Aug 2025

FAQ

Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.