Skip to content

Phi-3-small-instruct (128k) vs Kimi K2.6

Phi-3-small-instruct (128k) is cheaper on output tokens, while Kimi K2.6 offers a larger context window. Choose Phi-3-small-instruct (128k) or Kimi K2.6 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

SpecPhi-3-small-instruct (128k)Kimi K2.6
ProviderAzureAzure
Input / 1M tokens$0.15$0.95
Output / 1M tokens$0.60$4.00
Context window128K262K
Parameters1T
Open weightsYesYes
ReleasedApr 2024Apr 2026

FAQ

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