DeepSeek · Updated 4 November 2026

DeepSeek V4.1 Flash 1017

Intelligence
33 · 17th of 54
Coding
Not scored yet
Price per 1M tokens
$0.53 blended · $0.30 input · $1.20 output
Output speed
157 tok/s
Time to first token
0.9 s
Context window
1M tokens
Open weights
Yes
Released
17 October 2026

2nd in best open model

Settings

#SettingIntelligenceCodingPrice / 1M tokensSpeed
1Max33—$0.53157 tok/s
2High29—$0.53166 tok/s
3Non-reasoning19—$0.53158 tok/s

The same model at different reasoning settings. Higher settings think longer and usually score higher.

How it compares

#ModelIntelligenceCodingPrice / 1M tokensSpeedContext
1DeepSeek V4.1 Flash 1017 DeepSeek · open weights33—$0.53157 tok/s1M
2Gemini 4 Carbon Google60—$8.0092 tok/s—
3Grok 4.7 SpaceXAI36—$3.0064 tok/s500K
4Qwen3.8 Max Alibaba34—$3.0037 tok/s1M
5GPT-5.6 Terra OpenAI32—$4.50—1.1M
6Claude Haiku 5.5 Anthropic37—$0.20236 tok/s1M

Cheaper alternative within 3 points: Claude Haiku 5.5 at $0.20 per million tokens.

Data: Artificial Analysis (intelligence and coding indexes, prices, speed) and OpenRouter (open weights, context windows). Updated 4 November 2026; refreshed every 6 hours.

More rankings