R1 0528
by DeepSeek
May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...
Quick Facts
Provider
DeepSeek
Model ID
deepseek/deepseek-r1-0528
Modality
Text to Text
Tier
Premium
Last Updated
2026-07-12
Released
2025-05-28
Context Length
164K tokens
Tokenizer
DeepSeek
Input Price
$0.50/M
Output Price
$2.15/M
When To Use R1 0528
Best for
- Reasoning-heavy questions and step-by-step analysis
- Research, summarization, and document work
- Comparing DeepSeek responses against other leading AI models
Not ideal for
- High-volume casual chats where you want to conserve premium credits
- Native image generation workflows
- Prompts that require image or screenshot understanding
- Voice, speech, or audio transcription workflows
Input & Output
Accepts
Generates
Pricing
All prices are per 1 million tokens
Input
$0.50/M
Output
$2.15/M
Cache Read
$0.35/M
Capabilities
- Natural language understanding and generation
- Advanced reasoning and problem-solving
- Long context window for extended conversations
Example Prompts
Solve this problem step by step, then summarize the final answer in one paragraph.
Summarize these notes into key findings, risks, and recommended next steps.
Compare how R1 0528 and two other models answer this prompt.
Use R1 0528 to produce a concise answer, then list assumptions and tradeoffs.
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_pCompare and Use R1 0528
Related comparisons
GPT-5 vs Claude
Compare GPT-5 with Claude for writing, coding, and analysis.
GPT-5 vs Gemini
Compare GPT-5 with Gemini for reasoning and multimodal work.
GPT-5 vs Grok
Compare GPT-5 with Grok for reasoning and conversational style.
DeepSeek vs GPT-5
Compare DeepSeek with GPT-5 for coding and value-oriented tasks.
Claude vs DeepSeek
Compare DeepSeek with Claude for coding and writing.
Frequently Asked Questions
Try R1 0528 In Related Workflows
Model pages work best when they connect to real tasks. Use these bots and utilities to test R1 0528 against coding, research, and model-selection workflows.
Use R1 0528 on RyddleAI
Access R1 0528 with a RyddleAI subscription.
Compare R1 0528 With Alternatives
Use these nearby models to test whether R1 0528 is the right choice for your prompt, budget, and model family preference.
| Alternative | Provider | Tier | Why compare | Page |
|---|---|---|---|---|
| DeepSeek V4 Pro | Deepseek | Premium | Another DeepSeek model to compare within the same provider family | View model |
| DeepSeek V4 Flash | Deepseek | Free | Another DeepSeek model to compare within the same provider family | View model |
| Qwen3.7 Max | Qwen | Premium | Same tier alternative from another provider | View model |
| Grok Build 0.1 | X-ai | Premium | Same tier alternative from another provider | View model |