Skip to content
OhMyGPT

Search

Search pages and models…

GPT-6.1 Terra vs Qwen4 Max

Compare up to 4 models side by side.

Capability
168—
——
Priceper 1M tokens
Input$0.90–$1.80list $1.00-10%↓$1.413↑ ×1.6
Output$4.50–$6.75list $5.00-10%↑ ×1.1$4.24↓
Cache read$0.045–$0.09list $0.05-10%↓$0.071↑ ×1.6
Explicit cache read—$0.071
Web searchper request$0.009–$0.0126list $0.01-10%—
Limits and modalities
Context1.1M↑1M↓ 5%
Max output128K↓ 51%262K↑
ModalitiesInputTextImagePDFOutputTextInputTextImageVideoOutputText
Availability
ProvidersAzure AI Foundry, OpenAIAlibaba Cloud (Model Studio Intl)
30-day uptime——
Measured, last 30 days
Avg latency——
Effective price——
Cache hit rate——
About
Released2026-10-262026-11-16
Knowledge cutoff2026-06-01—

Capability scores are from Epoch AI’s Epoch Capabilities Index (CC BY 4.0, as of 2026-11-16), which combines dozens of benchmarks with GPT-5 set at 150. epoch.ai/eci