Mistral Large 4 vs DeepSeek V4.1 Flash 1017

Compare Mistral Large 4 from Mistral and DeepSeek V4.1 Flash 1017 from DeepSeek on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.

Favicon for mistralai
Mistral Large 4
Favicon for deepseek
DeepSeek V4.1 Flash 1017

Overview

Mistral Large 4
Author
Mistral
DeepSeek V4.1 Flash 1017
Author
DeepSeek
Mistral Large 4
Context length
1.05Mtokens
DeepSeek V4.1 Flash 1017
Context length
1.05Mtokens
Mistral Large 4
Reasoning
DeepSeek V4.1 Flash 1017
Reasoning
Mistral Large 4
Input modalities
DeepSeek V4.1 Flash 1017
Input modalities
Mistral Large 4
Output modalities
DeepSeek V4.1 Flash 1017
Output modalities

Analysis

Mistral Large 4 vs DeepSeek V4.1 Flash 1017 at a glance

Index and benchmark scores are from Artificial Analysis. Each score is the model's best published result across the configurations Artificial Analysis evaluated.

Mistral Large 4
Input price
$0.70/M tokens
DeepSeek V4.1 Flash 1017
Input price
$0.035/M tokens
Mistral Large 4
Output price
$2.10/M tokens
DeepSeek V4.1 Flash 1017
Output price
$0.15/M tokens
Mistral Large 4
Context window
1,048,576 tokens
DeepSeek V4.1 Flash 1017
Context window
1,048,576 tokens
Mistral Large 4
Intelligence Index Artificial Analysis, best published result
26.1
DeepSeek V4.1 Flash 1017
Intelligence Index Artificial Analysis, best published result
32.6
Mistral Large 4
Finance & Accounting Index Artificial Analysis, best published result
39.1
DeepSeek V4.1 Flash 1017
Finance & Accounting Index Artificial Analysis, best published result
42.2
Mistral Large 4
Strategy & Ops Index Artificial Analysis, best published result
43.4
DeepSeek V4.1 Flash 1017
Strategy & Ops Index Artificial Analysis, best published result
49.2
Mistral Large 4
Legal Index Artificial Analysis, best published result
34.6
DeepSeek V4.1 Flash 1017
Legal Index Artificial Analysis, best published result
37.7
Mistral Large 4
Healthcare & Medical Index Artificial Analysis, best published result
36.7
DeepSeek V4.1 Flash 1017
Healthcare & Medical Index Artificial Analysis, best published result
41.3
Mistral Large 4
Engineering Index Artificial Analysis, best published result
33.4
DeepSeek V4.1 Flash 1017
Engineering Index Artificial Analysis, best published result
37.6
Mistral Large 4
Economics Index Artificial Analysis, best published result
35.6
DeepSeek V4.1 Flash 1017
Economics Index Artificial Analysis, best published result
38.5
Mistral Large 4
Cyber Index Artificial Analysis, best published result
50.90.0% of tasks refused
DeepSeek V4.1 Flash 1017
Cyber Index Artificial Analysis, best published result
56.80.0% of tasks refused
Mistral Large 4
Openness Index Artificial Analysis, best published result
38.9
DeepSeek V4.1 Flash 1017
Openness Index Artificial Analysis, best published result
44.4
Mistral Large 4
FrontierCode-AA 2.0 Artificial Analysis, best published result
15.0%
DeepSeek V4.1 Flash 1017
FrontierCode-AA 2.0 Artificial Analysis, best published result
28.5%
Mistral Large 4
Latency (p50)
1.85 s
DeepSeek V4.1 Flash 1017
Latency (p50)
2.15 s
Mistral Large 4
Throughput (p50)
48.0 tok/s
DeepSeek V4.1 Flash 1017
Throughput (p50)
65.0 tok/s
Mistral Large 4
Provided by
Mistral
DeepSeek V4.1 Flash 1017
Provided by
DeepSeek

Benchmark data updated

Frequently asked questions

Is Mistral Large 4 cheaper than DeepSeek V4.1 Flash 1017?

DeepSeek V4.1 Flash 1017 is cheaper than Mistral Large 4 on OpenRouter: DeepSeek V4.1 Flash 1017 costs $0.035/M tokens input and $0.15/M tokens output, while Mistral Large 4 costs $0.70/M tokens input and $2.10/M tokens output.

Which has the longer context window, Mistral Large 4 or DeepSeek V4.1 Flash 1017?

Mistral Large 4 and DeepSeek V4.1 Flash 1017 have the same context window of 1,048,576 tokens.

Which is faster, Mistral Large 4 or DeepSeek V4.1 Flash 1017?

DeepSeek V4.1 Flash 1017 is faster on OpenRouter, generating a median 65.0 tokens per second compared with 48.0 tokens per second for Mistral Large 4.

Which scores higher on coding, Mistral Large 4 or DeepSeek V4.1 Flash 1017?

DeepSeek V4.1 Flash 1017 scores higher on FrontierCode-AA 2.0, the evaluation OpenRouter ranks models for coding by: 28.5% compared with 15.0% for Mistral Large 4, as measured by Artificial Analysis.