Claude Sonnet 5.5 vs DeepSeek V4.1 Flash

Compare Claude Sonnet 5.5 from Anthropic and DeepSeek V4.1 Flash 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 anthropic
Claude Sonnet 5.5
Favicon for deepseek
DeepSeek V4.1 Flash

Overview

Claude Sonnet 5.5
Author
Anthropic
DeepSeek V4.1 Flash
Author
DeepSeek
Claude Sonnet 5.5
Context length
1Mtokens
DeepSeek V4.1 Flash
Context length
1.05Mtokens
Claude Sonnet 5.5
Reasoning
DeepSeek V4.1 Flash
Reasoning
Claude Sonnet 5.5
Input modalities
DeepSeek V4.1 Flash
Input modalities
Claude Sonnet 5.5
Output modalities
DeepSeek V4.1 Flash
Output modalities

Analysis

Claude Sonnet 5.5 vs DeepSeek V4.1 Flash 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.

Claude Sonnet 5.5
Input price
$2/M tokens
DeepSeek V4.1 Flash
Input price
$0.0498/M tokens
Claude Sonnet 5.5
Output price
$10/M tokens
DeepSeek V4.1 Flash
Output price
$0.1992/M tokens
Claude Sonnet 5.5
Context window
1,000,000 tokens
DeepSeek V4.1 Flash
Context window
1,048,576 tokens
Claude Sonnet 5.5
Intelligence Index Artificial Analysis, best published result
54.5
DeepSeek V4.1 Flash
Intelligence Index Artificial Analysis, best published result
Not available
Claude Sonnet 5.5
Finance & Accounting Index Artificial Analysis, best published result
55.8
DeepSeek V4.1 Flash
Finance & Accounting Index Artificial Analysis, best published result
Not available
Claude Sonnet 5.5
Strategy & Ops Index Artificial Analysis, best published result
58.1
DeepSeek V4.1 Flash
Strategy & Ops Index Artificial Analysis, best published result
Not available
Claude Sonnet 5.5
Legal Index Artificial Analysis, best published result
52.2
DeepSeek V4.1 Flash
Legal Index Artificial Analysis, best published result
Not available
Claude Sonnet 5.5
Healthcare & Medical Index Artificial Analysis, best published result
54.2
DeepSeek V4.1 Flash
Healthcare & Medical Index Artificial Analysis, best published result
Not available
Claude Sonnet 5.5
Engineering Index Artificial Analysis, best published result
58.5
DeepSeek V4.1 Flash
Engineering Index Artificial Analysis, best published result
Not available
Claude Sonnet 5.5
Economics Index Artificial Analysis, best published result
54.1
DeepSeek V4.1 Flash
Economics Index Artificial Analysis, best published result
Not available
Claude Sonnet 5.5
Cyber Index Artificial Analysis, best published result
Not available
DeepSeek V4.1 Flash
Cyber Index Artificial Analysis, best published result
40.80.0% of tasks refused
Claude Sonnet 5.5
Openness Index Artificial Analysis, best published result
Not available
DeepSeek V4.1 Flash
Openness Index Artificial Analysis, best published result
44.4
Claude Sonnet 5.5
FrontierCode-AA 2.0 Artificial Analysis, best published result
41.7%
DeepSeek V4.1 Flash
FrontierCode-AA 2.0 Artificial Analysis, best published result
Not available
Claude Sonnet 5.5
Latency (p50)
2.13 s
DeepSeek V4.1 Flash
Latency (p50)
1.42 s
Claude Sonnet 5.5
Throughput (p50)
118.0 tok/s
DeepSeek V4.1 Flash
Throughput (p50)
97.0 tok/s
Claude Sonnet 5.5
Provided by
Anthropic
DeepSeek V4.1 Flash
Provided by
DeepSeek

Benchmark data updated

Frequently asked questions

Is Claude Sonnet 5.5 cheaper than DeepSeek V4.1 Flash?

DeepSeek V4.1 Flash is cheaper than Claude Sonnet 5.5 on OpenRouter: DeepSeek V4.1 Flash costs $0.0498/M tokens input and $0.1992/M tokens output, while Claude Sonnet 5.5 costs $2/M tokens input and $10/M tokens output.

Which has the longer context window, Claude Sonnet 5.5 or DeepSeek V4.1 Flash?

DeepSeek V4.1 Flash has the longer context window at 1,048,576 tokens, compared with 1,000,000 tokens for Claude Sonnet 5.5.

Which is faster, Claude Sonnet 5.5 or DeepSeek V4.1 Flash?

Claude Sonnet 5.5 is faster on OpenRouter, generating a median 118.0 tokens per second compared with 97.0 tokens per second for DeepSeek V4.1 Flash.