Skip to content

Sarvam 105B vs GLM 4.5

Sarvam 105B is cheaper on output tokens, while Sarvam 105B offers a larger context window. Choose Sarvam 105B or GLM 4.5 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

SpecSarvam 105BGLM 4.5
ProviderNanoGPTNanoGPT
Input / 1M tokens$0.05$0.30
Output / 1M tokens$0.18$1.30
Context window131K128K
Parameters355B
Open weightsNoNo
ReleasedMay 2026Apr 2025

FAQ

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