Skip to content

text-embedding-3-large vs GPT-5.2

text-embedding-3-large is cheaper on output tokens, while GPT-5.2 offers a larger context window. Choose text-embedding-3-large or GPT-5.2 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spectext-embedding-3-largeGPT-5.2
ProviderAzure Cognitive ServicesAzure Cognitive Services
Input / 1M tokens$0.13$1.75
Output / 1M tokens$0.00$14.00
Context window8K400K
Parameters
Open weightsNoNo
ReleasedJan 2024Dec 2025

FAQ

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