R1 0528

Provider: DeepSeek CN

Input price
$0.50
/ 1M tokens
Output price
$2.18
/ 1M tokens
Cache price
$0.35
/ 1M tokens (read)
Context
164K tokens
Max output 33K tokens

Overview

DeepSeek R1 0528 is a flagship or specialized reasoning model from DeepSeek, targeting complex workloads that require advanced processing and extended conversational context. It offers a substantial context window and robust capabilities like function-calling and JSON-mode.

Strengths

  • Processes extensive information with a large 163840-token context window.
  • Generates exceptionally long responses, supporting outputs up to 32768 tokens.
  • Supports structured interactions through its function-calling and JSON-mode capabilities.
  • Capable of advanced reasoning, indicated by its explicit 'thinking' capability.
  • Offers a cache read pricing option at $0.35/1M tokens for repeated context.

Best use cases

  • Analyzing and summarizing very long documents or detailed technical reports.
  • Building sophisticated AI agents that require function-calling and structured outputs.
  • Developing applications that need to process and generate extensive text.
  • Tasks requiring advanced reasoning and multi-step thought processes.
  • Generating structured data or code snippets with JSON-mode integration.

Pricing position

DeepSeek R1 0528 is positioned as DeepSeek's premium offering, with an input price of $0.5/1M tokens and an output price of $2.15/1M tokens, making it significantly more expensive than its V3 and V4 Flash siblings. Compared to similarly-priced peers on input, its output price is higher than Mistral Large 3 ($1.5/1M) and Llama 3 70B Instruct ($0.74/1M), but more cost-effective than Gemini 3 Flash Preview ($3/1M) for output.

Caveats

While powerful, DeepSeek R1 0528 does not offer a free tier, and its premium pricing may not be suitable for all applications. For tasks not requiring its advanced reasoning, extensive context, or large output capabilities, DeepSeek's V3 or V4 Flash models offer significantly lower input and output costs, providing more economical alternatives.

Notes drafted by an LLM from the figures on this page (2026-05-21) and rewritten when the price changes.

Key facts

Price basis
Median third-party host price (no first-party API)
Max output
33K tokens
Knowledge cutoff
2025-03-31
Listed on OpenRouter
2025-05-28
Tracked since
2026-05-08
Last updated
2026-11-15

Features

Function callingJSON outputReasoning

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.16
1M (small app) 1 0.5 $1.59
10M (mid scale) 10 5 $15.90
100M (large) 100 50 $159.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from DeepSeek

Similar-priced models

Source: OpenRouter API (deepseek/deepseek-r1-0528)