DeepSeek text

DeepSeek V4 Flash 0731 Pricing & Token Costs

Official API rate card for DeepSeek V4 Flash 0731 provided by DeepSeek. All token pricing is normalized per 1 Million tokens ($/1M).

Token Pricing Rates ($/1M Tokens)

Input Tokens 0.0400 per 1M tokens
Output Tokens 0.1200 per 1M tokens
Prompt Cache Read $0.0030 per 1M tokens
Prompt Cache Write $0.0400 per 1M tokens

Technical Specifications

Provider
DeepSeek
Context Window
1,311k tokens (1,310,720)
Max Output Tokens
16k tokens (16,384)
Reasoning Architecture
Standard Autoregressive
Supported Modalities
text

Estimated Inference Costs

Example cost calculation for standard application workloads assuming a 3:1 input-to-output token ratio.

100,000 requests (500 in / 150 out) 0.00
1,000,000 requests (1,000 in / 300 out) 0.08
← Compare DeepSeek V4 Flash 0731 on Master Pricing Table