DeepSeek V4.1 Flash 1017 vs GPT-6.1 Sol

Compare up to 4 models side by side.

Capability
159↓ 5%168↑
—1446
Priceper 1M tokens
Input$0.015–$0.292list $0.30-95%↓$1.80–$3.60list $2.00-10%↑ ×120.0
Output$0.06–$1.168list $1.20-95%↓$9.00–$13.50list $10.00-10%↑ ×150.0
Cache read$0.0003–$0.00584list $0.006-95%↓$0.09–$0.18list $0.10-10%↑ ×300.0
Web searchper request$0.000732↓$0.009–$0.0126list $0.01-10%↑ ×12.3
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, OpenAI
30-day uptime——
Measured, last 30 days
Avg latency——
Effective price——
Cache hit rate——
About
Released2026-10-172026-09-29
Knowledge cutoff—2026-04-30

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

Human preference ratings are from the LMArena Text Arena (CC BY 4.0, as of 2026-10-28): Elo ratings from blind votes, on a different scale from capability scores. lmarena.ai/leaderboard/text