LLM Pricing

← All Models

DeepSeek: DeepSeek V4 Pro 0813

🇨🇳 DeepSeek · DeepSeek V4

Input Price $1.12 per million tokens NT$35.9
Output Price $3.37 per million tokens NT$108
Context Window 1.05M tokens Output limit: 944K
OpenRouter Route Price Please verify with official pricing pages
Use this model via OpenRouter →

Overview

DeepSeek: DeepSeek V4 Pro 0813 is a large language model API from DeepSeek, part of its DeepSeek V4 model family. Priced at $1.12 per million input tokens and $3.37 per million output tokens, it occupies the mid-range, balancing capability against running cost. Output tokens cost about 3× as much as input, so prompt-heavy workloads run noticeably cheaper than generation-heavy ones. An exceptionally large 1.05M-token context window (≈1,573 pages of text) means entire repositories or document collections can be processed without chunking. On Artificial Analysis's Intelligence Index it scores 53 (A grade), a useful proxy for its general reasoning strength relative to the other models tracked here. All prices on this page reflect OpenRouter's routed rates and are re-synced automatically every day; confirm against the provider's official pricing before committing to production.

Dimension Unit Price (USD) Price (TWD) Effective From
Input per 1M tokens $1.12 NT$35.9
Output per 1M tokens $3.37 NT$108
Cached Input per 1M tokens $0.037 NT$1.2

Provider
DeepSeek
Model Family
DeepSeek V4
Version String
deepseek/deepseek-v4-pro-0813
Status
Active
Modality
Text
Context Window
1,048,576 tokens
Output Limit
943,717 tokens

Index Metrics

Cross-domain capability indexes evaluated by Artificial Analysis — Artificial Analysis

Agentic Index 50 A Measured: 2026-08-26
Coding Index 69 S Measured: 2026-08-26
Intelligence Index 53 A Measured: 2026-08-26

Benchmark Scores

Data source: Artificial Analysis

AA-LCR 75.3% A Measured: 2026-08-26
GPQA Diamond 92.8% S Measured: 2026-08-26
Non-Hallucination 5.2% Measured: 2026-08-26
Omniscience Accuracy 49.1% Measured: 2026-08-26
SciCode 49.2% A Measured: 2026-08-26

Performance Metrics

Real-world benchmarks, updated every 72 hours by Artificial Analysis — Artificial Analysis

First Token Latency 1.6s Measured: 2026-08-26
Output Speed 67 t/s Measured: 2026-08-26
Response Time 38.9s Measured: 2026-08-26

90-Day Price Trend

Input / Output price (USD per 1M tokens)

Past 90 days of records; every price change is shown here

Date Dimension Price (USD) Source
Cached Input $0.037 OpenRouter
Output $3.37 OpenRouter
Input $1.12 OpenRouter
Cached Input $0.037 OpenRouter
Output $3.37 OpenRouter
Input $1.12 OpenRouter
Cached Input $0.037 OpenRouter
Output $3.37 OpenRouter
Input $1.12 OpenRouter
Cached Input $0.037 OpenRouter
Output $3.37 OpenRouter
Input $1.12 OpenRouter
Cached Input $0.040 OpenRouter
Output $3.56 OpenRouter
Input $1.19 OpenRouter
Cached Input $0.040 OpenRouter
Output $3.56 OpenRouter
Input $1.19 OpenRouter
Cached Input $0.040 OpenRouter
Output $3.56 OpenRouter
Input $1.19 OpenRouter
Cached Input $0.022 OpenRouter
Output $1.98 OpenRouter
Input $0.660 OpenRouter
Cached Input $0.022 OpenRouter
Output $1.98 OpenRouter
Input $0.660 OpenRouter
Cached Input $0.022 OpenRouter
Output $1.98 OpenRouter
Input $0.660 OpenRouter
Cached Input $0.022 OpenRouter
Output $1.98 OpenRouter
Input $0.660 OpenRouter
Cached Input $0.0036 OpenRouter
Output $0.870 OpenRouter
Input $0.435 OpenRouter
Cached Input $0.0036 OpenRouter
Output $0.870 OpenRouter
Input $0.435 OpenRouter
Cached Input $0.0036 OpenRouter
Output $0.870 OpenRouter
Input $0.435 OpenRouter
Cached Input $0.0036 OpenRouter
Output $0.870 OpenRouter
Input $0.435 OpenRouter

Key Insights

Key data points from this page for quick reference and citation.

  • DeepSeek: DeepSeek V4 Pro 0813 Input price: $1.122/M tokens
  • DeepSeek: DeepSeek V4 Pro 0813 Output price: $3.366/M tokens
  • Context window: 1,048,576 tokens
  • Provider: DeepSeek
  • Model family: DeepSeek V4
  • Modalities: Text
  • Data source: OpenRouter, updated daily