modelgrep
D

DeepSeek: DeepSeek V3 0324

deepseek/deepseek-chat-v3-0324

112th smartest of 180ToolsJSON
Use via OpenRouter ↗
Intelligence
22.3
112th of 180
Design Elo
Speed
35
224th fastest
Latency
900ms
first token
Input price
$0.200
99th cheapest
Context
164K
16K max out

How it compares

Smarter than38%
of all ranked models
Faster than27%
of all ranked models
Cheaper than67%
of all ranked models

Overview

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...

Benchmarks

independent · via OpenRouter
Artificial Analysis37th percentile
Intelligence Index
22.3
Coding Index
22.0
Agentic Index
16.3
GPQA Diamond
66%
Humanity's Last Exam
5%
SciCode
36%
Tau²-Bench (agentic)
47%

Providers & pricing (6)

ProviderIn $/MOut $/MUptime
DeepInfrafp4$0.200$0.77099.8%
AtlasCloudfp8$0.216$0.88099.9%
ModelRunfp4$0.220$0.80099.7%
SiliconFlowfp8$0.250$1.0099.2%
Novitafp8$0.270$1.12100%
GMICloudfp8$0.290$1.14

Specifications

Context window164K
Max output16K
Knowledge cutoffJul 2024
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price$0.135/M
ModeratedNo

DeepSeek V3 0324 FAQ

How much does DeepSeek V3 0324 cost?

DeepSeek V3 0324 costs $0.200 per million input tokens and $0.770 per million output tokens via OpenRouter, making it 99th cheapest of 298 paid models.

How smart is DeepSeek V3 0324?

DeepSeek V3 0324 scores 22.3 on the Artificial Analysis Intelligence Index, ranking 112th of 180 benchmarked models, with a GPQA Diamond score of 66%.

How fast is DeepSeek V3 0324?

DeepSeek V3 0324 generates around 35 tokens per second with 900ms time-to-first-token (p50), the 224th fastest tracked model.

What is DeepSeek V3 0324's context window?

DeepSeek V3 0324 supports a 164K-token context window and can output up to 16K tokens. It accepts text input.

Compare head-to-head