DeepSeek V3

Provider: DeepSeek CN

Input price
$0.26
/ 1M tokens
Output price
$1.03
/ 1M tokens
Context
164K tokens
Max output 16K tokens

Overview

DeepSeek V3 is a flagship instruction and coding model from DeepSeek with a 163,840-token context window.

Strengths

  • 163,840 token context window
  • Native function-calling support
  • JSON mode output generation
  • Pretrained on 15 trillion tokens

Best use cases

  • Complex coding tasks
  • Structured data extraction pipelines
  • Large scale text processing

Pricing position

Input is $0.2574 and output is $1.0287 per million tokens, closely matching DeepSeek V3 0324 and Gemini 3 Flash Preview.

Caveats

Outputs are capped at 16,384 tokens and third-party host pricing applies with no free tier available.

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
16K tokens
Knowledge cutoff
2024-07-31
Listed on OpenRouter
2024-12-26
Tracked since
2026-05-08
Last updated
2026-11-13

Features

Function callingJSON output

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.08
1M (small app) 1 0.5 $0.77
10M (mid scale) 10 5 $7.72
100M (large) 100 50 $77.17

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from DeepSeek

Similar-priced models

Source: OpenRouter API (deepseek/deepseek-chat)