DeepSeek V4.1 Flash 1017 vs GPT-5.1-Codex-Mini

Price, context window & benchmark comparison

DeepSeek

DeepSeek V4.1 Flash 1017

DeepSeek
$0.098 / $0.29
Input / Output · per 1M tokens
VS
OpenAI

GPT-5.1-Codex-Mini

OpenAI
$0.25 / $2.00
Input / Output · per 1M tokens
Compare different models
DeepSeek
OpenAI
Verdict: DeepSeek V4.1 Flash 1017 is 4.7× cheaper than GPT-5.1-Codex-Mini on a typical 3:1 input/output mix. DeepSeek V4.1 Flash 1017 has the larger context window (1M vs 400K).
DeepSeek V4.1 Flash 1017GPT-5.1-Codex-Mini
Input price / 1M$0.098$0.25
Output price / 1M$0.29$2.00
Blended price (3:1)$0.15$0.69
Cached input / 1M$0.0029$0.03
Context window1M400K
Max output393K128K
Intelligence index28.6—
Coding index——
Providers47—
Best provider uptime (30m)100.0%—
Vision inputYesYes
ReasoningYesYes
Tool callingYesYes
Released2026-10-172025-11-13
Retirement——

Cost calculator

FAQ

Which is cheaper, DeepSeek V4.1 Flash 1017 or GPT-5.1-Codex-Mini?

DeepSeek V4.1 Flash 1017 is 4.7× cheaper than GPT-5.1-Codex-Mini on a typical 3:1 input/output mix.

DeepSeek V4.1 Flash 1017 vs GPT-5.1-Codex-Mini: which has a bigger context window?

DeepSeek V4.1 Flash 1017: 1,048,576 tokens. GPT-5.1-Codex-Mini: 400,000 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: DeepSeek V4.1 Flash 1017 ≈ $343.00, GPT-5.1-Codex-Mini ≈ $1,500.

More comparisons