Kimi K3.1 Pro HighSpeed vs GPT-6.1 Terra

Compare up to 4 models side by side.

Capability
—168
——
Priceper 1M tokens
Input$4.1756–$4.40↑ ×4.6$0.90–$1.80list $1.00-10%↓
Output$21.8416–$22.00↑ ×4.9$4.50–$6.75list $5.00-10%↓
Cache read$0.20878–$0.22↑ ×4.6$0.045–$0.09list $0.05-10%↓
Web searchper request—$0.0126list $0.014-10%
Limits and modalities
Context1M↓ 0%1.1M↑
Max output1M↑128K↓ 88%
ModalitiesInputTextImageVideoOutputTextInputTextImageOutputText
Availability
ProvidersMoonshot AI (Kimi), Tencent Cloud TokenHubAzure AI Foundry
30-day uptime——
Measured, last 30 days
Avg latency——
Effective price——
Cache hit rate——
About
Released2026-10-232026-10-26
Knowledge cutoff—2026-06-01

Capability scores are from Epoch AI’s Epoch Capabilities Index (CC BY 4.0, as of 2026-11-02), which combines dozens of benchmarks with GPT-5 set at 150. epoch.ai/eci