LLM Pricing

← All Models

DeepSeek: DeepSeek V4 Flash 0731

🇨🇳 DeepSeek · DeepSeek V4

Input Price $0.040 per million tokens NT$1.3
Output Price $0.640 per million tokens NT$20.5
Context Window 1.31M tokens Output limit: 944K
OpenRouter Route Price Please verify with official pricing pages
Use this model via OpenRouter →

Overview

DeepSeek: DeepSeek V4 Flash 0731 is a large language model API from DeepSeek, part of its DeepSeek V4 model family. At $0.040 per million input tokens and $0.640 per million output tokens, it sits in the budget tier — among the cheaper options for high-throughput or cost-sensitive workloads. Output tokens cost about 16× as much as input, so prompt-heavy workloads run noticeably cheaper than generation-heavy ones. An exceptionally large 1.31M-token context window (≈1,966 pages of text) means entire repositories or document collections can be processed without chunking. On Artificial Analysis's Intelligence Index it scores 35 (C 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 $0.040 NT$1.3
Output per 1M tokens $0.640 NT$20.5
Cached Input per 1M tokens $0.016 NT$0.51

Provider
DeepSeek
Model Family
DeepSeek V4
Version String
deepseek/deepseek-v4-flash-0731
Status
Active
Modality
Text
Context Window
1,310,720 tokens
Output Limit
943,718 tokens

Index Metrics

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

Agentic Index 42 B Measured: 2026-09-08
Coding Index 69 S Measured: 2026-09-08
Intelligence Index 35 C Measured: 2026-09-08

Benchmark Scores

Data source: Artificial Analysis

AA-LCR 79.7% A Measured: 2026-09-08
GPQA Diamond 90.8% S Measured: 2026-09-08
HLE 38.6% S Measured: 2026-09-08
Non-Hallucination 8.3% Measured: 2026-09-08
Omniscience Accuracy 40.4% Measured: 2026-09-08
SciCode 50.3% A Measured: 2026-09-08

Performance Metrics

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

First Token Latency 0.9s Measured: 2026-09-08
Output Speed 128 t/s Measured: 2026-09-08
Response Time 20.5s Measured: 2026-09-08

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 $0.016 OpenRouter
Output $0.640 OpenRouter
Input $0.040 OpenRouter
Cached Input $0.016 OpenRouter
Output $0.320 OpenRouter
Input $0.040 OpenRouter
Cached Input $0.016 OpenRouter
Output $0.080 OpenRouter
Input $0.040 OpenRouter
Cached Input $0.016 OpenRouter
Output $0.080 OpenRouter
Input $0.040 OpenRouter
Cached Input $0.012 OpenRouter
Output $0.120 OpenRouter
Input $0.060 OpenRouter
Cached Input $0.012 OpenRouter
Output $0.120 OpenRouter
Input $0.060 OpenRouter
Cached Input $0.012 OpenRouter
Output $0.120 OpenRouter
Input $0.060 OpenRouter
Cached Input $0.012 OpenRouter
Output $0.120 OpenRouter
Input $0.060 OpenRouter
Cached Input $0.012 OpenRouter
Output $0.120 OpenRouter
Input $0.060 OpenRouter
Cached Input $0.0080 OpenRouter
Output $0.080 OpenRouter
Input $0.040 OpenRouter
Cached Input $0.0080 OpenRouter
Output $0.080 OpenRouter
Input $0.040 OpenRouter
Cached Input $0.016 OpenRouter
Output $0.180 OpenRouter
Input $0.065 OpenRouter
Cached Input $0.016 OpenRouter
Output $0.180 OpenRouter
Input $0.065 OpenRouter
Cached Input $0.016 OpenRouter
Output $0.180 OpenRouter
Input $0.065 OpenRouter
Cached Input $0.016 OpenRouter
Output $0.180 OpenRouter
Input $0.065 OpenRouter
Cached Input $0.028 OpenRouter
Output $0.280 OpenRouter
Input $0.140 OpenRouter
Cached Input $0.0100 OpenRouter
Output $0.100 OpenRouter

Key Insights

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

  • DeepSeek: DeepSeek V4 Flash 0731 Input price: $0.04/M tokens
  • DeepSeek: DeepSeek V4 Flash 0731 Output price: $0.64/M tokens
  • Context window: 1,310,720 tokens
  • Provider: DeepSeek
  • Model family: DeepSeek V4
  • Modalities: Text
  • Data source: OpenRouter, updated daily