DeepSeek V4 Pro 0423

Provider: DeepSeek CN

Input price
$1.42
/ 1M tokens
Output price
$2.83
/ 1M tokens
Cache price
$0.12
/ 1M tokens (read)
Context
1.05M tokens
Max output 393K tokens

Overview

DeepSeek V4 Pro 0423 is a flagship Mixture-of-Experts model featuring 1.6T total parameters, built for advanced reasoning and coding workloads.

Strengths

  • 1,048,576 token context window capacity
  • 384,000 maximum token output limit
  • Supports native function-calling and json-mode
  • Cached input drops to $0.118 per million

Best use cases

  • Large-scale codebase analysis and refactoring
  • Complex multi-step reasoning workflows
  • Long-context document extraction

Pricing position

Input sits at $1.416/M and output at $2.832/M, making output cheaper than GLM 5.3 ($4.4/M) and Mistral Medium 3.5 ($7.5/M).

Caveats

Higher cost than DeepSeek V4 Flash variants if 1M context and reasoning features are not 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
Median third-party host price (no first-party API)
Max output
393K tokens
Listed on OpenRouter
2026-04-24
Tracked since
2026-08-16
Last updated
2026-11-13

Features

Function callingJSON outputReasoning

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.28
1M (small app) 1 0.5 $2.83
10M (mid scale) 10 5 $28.32
100M (large) 100 50 $283.20

※ 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)