DeepSeek V3.1

Provider: DeepSeek CN

Input price
$0.27
/ 1M tokens
Output price
$1.00
/ 1M tokens
Cache price
$0.13
/ 1M tokens (read)
Context
164K tokens
Max output 147K tokens

Overview

DeepSeek V3.1 is a flagship hybrid reasoning model by DeepSeek with 671B parameters and 37B active, handling general tasks and complex logic via prompt templates.

Strengths

  • Supports function-calling and json-mode capabilities
  • Features integrated thinking and non-thinking modes
  • Offers cached input pricing at $0.13 per million tokens
  • Provides 163,840 context window with 147,456 max output

Best use cases

  • Complex reasoning and logic tasks
  • Structured data extraction via json-mode
  • Agent workflows requiring function calling

Pricing position

Input sits at $0.27 and output at $1.00 per million tokens, matching DeepSeek V3 0324 output pricing.

Caveats

Context window is significantly smaller than the 1M token limit found in newer DeepSeek Flash models.

Notes drafted by an LLM from the figures on this page (2026-11-12) and rewritten when the price changes.

Key facts

Price basis
Median third-party host price (no first-party API)
Max output
147K tokens
Knowledge cutoff
2025-03-31
Listed on OpenRouter
2025-08-21
Tracked since
2026-05-08
Last updated
2026-11-10

Features

Function callingJSON outputReasoning

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 $7.70
100M (large) 100 50 $77.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from DeepSeek

Similar-priced models

Source: OpenRouter API (deepseek/deepseek-chat-v3.1)