DeepSeek V4 Pro 0813

Provider: DeepSeek CN Official API price

Input price
$0.66
/ 1M tokens
Output price
$1.98
/ 1M tokens
Cache price
$0.022
/ 1M tokens (read)
Context
1.05M tokens
Max output 393K tokens

Overview

DeepSeek V4 Pro 0813 is a mixture-of-experts flagship model featuring a 1M token context window and native thinking capabilities.

Strengths

  • 1,048,576 token input context window
  • 393,216 token maximum output limit
  • Supports function-calling and JSON mode
  • Cached input drops to $0.022 per million

Best use cases

  • Processing large codebases and documents
  • Complex reasoning tasks via thinking capability
  • Structured data generation using JSON mode

Pricing position

Priced at $0.66 input and $1.98 output per million tokens, sitting above the Flash variants and comparable to Qwen2.5 Coder 32B.

Caveats

No free tier is available; use cheaper Flash variants if 1M context and thinking are not strictly required.

Notes drafted by an LLM from the figures on this page (2026-11-10) and rewritten when the price changes.

Key facts

Price basis
Official API price
Max output
393K tokens
Listed on OpenRouter
2026-08-12
Tracked since
2026-08-12
Last updated
2026-11-10

Features

Function callingJSON outputReasoning

Price history

  • 2026-11-10 Price change $1.32 / $3.96 → $0.66 / $1.98
  • 2026-08-12 Added

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.17
1M (small app) 1 0.5 $1.65
10M (mid scale) 10 5 $16.50
100M (large) 100 50 $165.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from DeepSeek

Similar-priced models

Source: OpenRouter API (deepseek/deepseek-v4-pro-0813)