Compare AI models

Specifications
Parameters
671B—
Context window
128k1M
API pricing
Input price
—$0.30
Output price
—$2.50
Cached input price
—$0.03
Cheapest input
$0.256DeepInfra$0.15Google AI Studio
Cheapest output
$0.712DeepInfra$1.25Google AI Studio
$103StreamLake$185Google list price
Benchmarks
LiveCodeBench
40.5%63.5%
GPQA Diamond
59.1%78.3%
Overview
CompanyDeepSeekGoogle
Release dateDec 26 2024Apr 17 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Gemini 2.5 Flash leads DeepSeek V3 on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). Only Gemini 2.5 Flash has a verified first-party price for an available API: $0.30 per million input tokens and $2.50 per million output tokens. No currently available pay-as-you-go API rate is tracked for DeepSeek V3. DeepSeek V3 shipped 112 days before Gemini 2.5 Flash, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek V3) vs 1M (Gemini 2.5 Flash). DeepSeek V3 is open weight, while Gemini 2.5 Flash is closed.

On LiveCodeBench, Gemini 2.5 Flash leads at 63.5% vs DeepSeek V3 at 40.5%. On GPQA Diamond, Gemini 2.5 Flash leads at 78.3% vs DeepSeek V3 at 59.1%.