deepseek-ai/DeepSeek-R1-0528

DeepSeek-R1-0528 is the May 2025 update to the original DeepSeek-R1. Built on the DeepSeek-V3 backbone with 671B total parameters and 37B active per inference pass (MoE), it achieves performance on par with OpenAI o1. Key improvements include 87.5% on AIME 2025 (up from 70%), reduced hallucinations, enhanced front-end capabilities, and newly added JSON output and function calling support.

DeepSeek Chat 128K Tokens
Get API Key
Try in Playground
Free Trial Credit No Credit Card Required
$1.00

api_example.sh

curl -X POST "https://platform.qubrid.com/v1/chat/completions" \
  -H "Authorization: Bearer QUBRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepseek-ai/DeepSeek-R1-0528",
  "messages": [
    {
      "role": "user",
      "content": "Explain quantum computing in simple terms"
    }
  ],
  "temperature": 0.6,
  "max_tokens": 16384,
  "stream": true,
  "top_p": 0.95
}'

Technical Specifications

Model Architecture & Performance

Variant Reasoning
Model Size 671B params (37B active)
Context Length 128K Tokens
Quantization FP8
Tokens/Second 50
Architecture DeepSeek-V3 backbone — Sparse MoE with 671B total / 37B active, MLA attention, MTP speculative decoding
Precision FP8
License MIT License
Release Date May 2025
Developers DeepSeek-AI

Pricing

Pay-per-use, no commitments

Input Tokens $0.0009/1K Tokens
Output Tokens $0.0032/1K Tokens

API Reference

Complete parameter documentation

Parameter Type Default Description
stream boolean true Enable streaming responses for real-time output.
temperature number 0.6 Recommended range 0.5–0.7 (0.6 default) to prevent endless repetitions.
max_tokens number 16384 Maximum number of tokens to generate.
top_p number 0.95 Nucleus sampling.

Explore the full request and response schema in our external API documentation

Performance

Strengths & considerations

Strengths Considerations
671B total / 37B active MoE — frontier reasoning
87.5% on AIME 2025 (up +17.5% from previous version)
Now supports JSON output and function calling
Reduced hallucinations vs prior R1
Fully open-source with MIT license
Chain-of-thought reasoning with visible traces
128K max context (shorter than some competitors)
Requires very large infrastructure for self-hosting
Temperature must stay in 0.5–0.7 range
Reasoning traces increase total output length

Use cases

Recommended applications for this model

Advanced mathematical reasoning
Code generation & debugging
Complex multi-step problem solving
Research and analysis
JSON-structured output generation
Function calling and tool use

Enterprise
Platform Integration

Docker

Docker Support

Official Docker images for containerized deployments

Kubernetes

Kubernetes Ready

Production-grade KBS manifests and Helm charts

SDK

SDK Libraries

Official SDKs for Python, Javascript, Go, and Java

Don't let your AI control you. Control your AI the Qubrid way!

Have questions? Want to Partner with us? Looking for larger deployments or custom fine-tuning? Let's collaborate on the right setup for your workloads.

"Qubrid enabled us to deploy production AI agents with reliable tool-calling and step tracing. We now ship agents faster with full visibility into every decision and API call."

AI Agents Team

Agent Systems & Orchestration