DeepSeek V3.1 Model Specs, Costs & Benchmarks (July 2026)
DeepSeek V3.1, developed by DeepSeek, features a context window of 163.8K tokens. The model costs $0.25 per million tokens for input and $0.95 per million tokens for output. It was released on August 21, 2025, and has achieved impressive scores in various benchmarks.
Access DeepSeek V3.1 & 210+ other AI models all in one platformTry Magica for free
Overview
Model Provider The organization behind this AI's development | |
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 | 32.8K tokens |
Release Date When this model first became publicly available | August 21, 2025 11 months ago August 21st, 2025 |
Knowledge Cutoff Latest training-data date reported by the provider | March 31, 2025 |
Pricing
Input Token Cost Cost per million input tokens | $0.25 per million tokens |
Output Token Cost Cost per million output tokens | $0.95 per million tokens |
Cache Read Cost Cost to reuse cached input tokens | $0.13 per million tokens |
Capabilities & Features
Input Types Supported input formats | text |
Output Types Supported output formats | text |
Tokenizer Text encoding system | DeepSeek |
Key Features Advanced capabilities | β Function Callingβ Structured Outputβ Reasoning Mode |
Reasoning Controls Defaults and configurable reasoning effort | Optional |
Open Source Model availability |
Benchmarks
Best Design Arena Score Highest human-preference Elo score across design arenas | 1,149 Elo (#72 in Website (48.0% win rate)) |
Compare This Model
See how DeepSeek V3.1 compares with other top models
Compare DeepSeek V3.1 with top models in each category:
πProgramming
Best models for coding and development
π¨Creative & Roleplay
Models optimized for creative writing
π’Marketing
Content creation and marketing tasks
π»Technology
Technical analysis and explanations
π¬Science
Scientific research and analysis
πTranslation
Multilingual translation tasks