← Back to Calculator

Gemini 3.5 Flash vs DeepSeek V4 Flash

Detailed comparison of API pricing, technical specifications, and benchmark scores. Updated 2026-06-29.

Cost at a Glance

Gemini 3.5 Flash is 3.4× more expensive than DeepSeek V4 Flash — switching could save 70.4% on your monthly API bill.

At 5M input + 2M output tokens per month:

Gemini 3.5 Flash$4.25/movsDeepSeek V4 Flash$1.26/mo

Choosing DeepSeek V4 Flash could save you $2.99/mo

Price Comparison (per 1M tokens)

Input (per 1M tokens)
$0.25vs$0.14
Output (per 1M tokens)
$1.50vs$0.28
Cache Write (per 1M tokens)
vs$0.14
Cache Read (per 1M tokens)
$0.03vs$0.00
Batch Input (per 1M tokens)
vs
Batch Output (per 1M tokens)
vs

Prices are per 1 million tokens. Actual costs depend on your monthly token volume. Use the calculator →

Specifications

Context Window
1Mvs1M
Max Output Tokens
64Kvs64K
Knowledge Cutoff
2026-04vs2026-05
Modalities
Text, ImagevsText
Prompt Caching
YesvsNo
Batch API
NovsNo
Thinking / Reasoning
NovsNo

Benchmark Scores

SWE-bench Verified
65.0vs79.0
MMLU-Pro
80.0vs80.5
HumanEval
90.0vs91.2

Benchmark scores from official provider reports. Higher is better. Missing scores indicate the provider has not published that benchmark yet.

Use Cases

Gemini 3.5 Flash

fastcheapmultimodal

DeepSeek V4 Flash

cheapestfastcoding

About the Providers

Gemini 3.5 Flash is developed by Google. DeepSeek V4 Flash is developed by DeepSeek. This is a cross-provider comparison between Google and DeepSeek models. For the most up-to-date pricing, always check the official API documentation from each provider.

Compare More AI Models