Magica logo

DeepSeek V3 0324 Model Specs, Costs & Benchmarks (July 2026)

DeepSeek V3 0324, developed by DeepSeek, features a context window of 163.8K tokens. The model costs $0.27 per million tokens for input and $1.12 per million tokens for output. It was released on March 24, 2025, and has achieved impressive scores in various benchmarks.
Access DeepSeek V3 0324 & 210+ other AI models all in one platformTry Magica for free

Overview

DeepSeek V3 0324DeepSeek V3 0324
Model Provider
The organization behind this AI's development
DeepSeek logoDeepSeek
Input Context Window
Maximum input tokens this model can process at once
163.8K
tokens
Output Token Limit
Maximum output tokens this model can generate at once
65.5K
tokens
Release Date
When this model first became publicly available
March 24th, 2025
Knowledge Cutoff
Latest training-data date reported by the provider
July 31, 2024

Pricing

DeepSeek V3 0324DeepSeek V3 0324
Input Token Cost
Cost per million input tokens
$0.27
per million tokens
Output Token Cost
Cost per million output tokens
$1.12
per million tokens
Cache Read Cost
Cost to reuse cached input tokens
$0.14
per million tokens

Capabilities & Features

DeepSeek V3 0324DeepSeek V3 0324
Input Types
Supported input formats
text
Output Types
Supported output formats
text
Tokenizer
Text encoding system
DeepSeek
Key Features
Advanced capabilities
βœ“ Function Callingβœ“ Structured Output
Open Source
Model availability

Benchmarks

DeepSeek V3 0324DeepSeek V3 0324
Intelligence Index
Overall model quality across independent evaluations
15.4
(Artificial Analysis index; higher is better)
Coding Index
Programming performance across independent evaluations
21.2
(Artificial Analysis index; higher is better)
Agentic Index
Ability to complete multi-step agentic tasks
1.5
(Artificial Analysis index; higher is better)