DeepSeek V4.1 Flash 1017 vs GPT-6.1 Terra

Compare up to 4 models side by side.

Capability
159↓ 6%168↑
——
Priceper 1M tokens
Input$0.015–$0.292list $0.30-95%↓$0.90–$1.80list $1.00-10%↑ ×60.0
Output$0.06–$1.168list $1.20-95%↓$4.50–$6.75list $5.00-10%↑ ×75.0
Cache read$0.0003–$0.00584list $0.006-95%↓$0.045–$0.09list $0.05-10%↑ ×150.0
Web searchper request$0.000732↓$0.0126list $0.014-10%↑ ×17.2
Limits and modalities
Context1M↓ 5%1.1M↑
Max output384K↑128K↓ 67%
ModalitiesInputTextImageOutputTextInputTextImageOutputText
Availability
ProvidersByteDance (Volcano Engine), Tencent Cloud TokenHub, DeepSeek, Cloudflare Workers AIAzure AI Foundry
30-day uptime——
Measured, last 30 days
Avg latency——
Effective price——
Cache hit rate——
About
Released2026-10-172026-10-26
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