DeepSeek V4 Flash 0731

Provider: DeepSeek CN

Input price
$0.10
/ 1M tokens
Output price
$0.42
/ 1M tokens
Cache price
$0.06
/ 1M tokens (read)
Batch API
$0.048 / $0.14
input / output per 1M tokens
Context
1.05M tokens
Max output 944K tokens

Overview

DeepSeek V4 Flash 0731 is a budget sparse mixture-of-experts model featuring 13B active parameters out of 284B total. It targets coding, reasoning, and agent workflows.

Strengths

  • 1,048,576 token context window with 943,718 max output
  • Input cost of $0.10 per million tokens
  • Supports function-calling, json-mode, and thinking
  • Batch discounts at $0.048 input and $0.144 output

Best use cases

  • Processing large multi-file codebases and repositories
  • Running high-volume automated agentic reasoning loops
  • Extracting structured JSON from massive documents

Pricing position

Output pricing at $0.42 per million tokens sits higher than GPT-4.1 Nano at $0.40, but below GPT-5.4 Nano at $0.625.

Caveats

No free tier is available across third-party hosts.

Notes drafted by an LLM from the figures on this page (2026-11-15) and rewritten when the price changes.

Key facts

Price basis
Median third-party host price (no first-party API)
Max output
944K tokens
Listed on OpenRouter
2026-07-31
Tracked since
2026-07-31
Last updated
2026-11-15

Features

Function callingJSON outputReasoning

Price history

  • 2026-11-15 Price change $0.15 / $0.30 → $0.10 / $0.42
  • 2026-07-31 Added

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.03
1M (small app) 1 0.5 $0.31
10M (mid scale) 10 5 $3.10
100M (large) 100 50 $31.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from DeepSeek

Similar-priced models

Source: OpenRouter API (deepseek/deepseek-v4-flash-0731)