deepseek-r1-0528

completions

On:deepinfraparasail

deepseek-r1-0528

completions

Published by: deepseekProviders:

deepinfra parasail

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 in an inference pass. Fully open-source model.

Provider	Input	Output
deepinfra	$0.5 / 1M tokens	$2.15 / 1M tokens
parasail	$0.79 / 1M tokens	$4 / 1M tokens

Released

May 28, 2025

Knowledge

Nov 29, 2024

Context

163840

Input

$0.5 / 1M tokens

Output

$2.15 / 1M tokens

Accepts: text

Returns: text

Providers	Context	Input Price	Output Price	Input Formats	Output Formats	License
deepinfra	163840 tokens	$0.5 / 1M tokens	$2.15 / 1M tokens	text	text	MIT
parasail	163840 tokens	$0.79 / 1M tokens	$4 / 1M tokens	text	text	MIT

Released May 28, 2025Knowledge Cutoff: Nov 29, 2024

Access deepseek-r1-0528 through LangDB AI Gateway

Recommended

Integrate with deepseek's deepseek-r1-0528 and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.

Unified API

Cost Optimization

Enterprise Security

Get Started Now

Free tier available • No credit card required

Instant Setup

99.9% Uptime

10,000+Monthly Requests

Available from 2 providers

Provider:

Benchmark Results for deepseek-r1-0528

Category Performance Scores:

Science: Score 82.75 (Top 2% - Rank #7)
Writing: Score 83.50 (Top 2% - Rank #7)

Overall Performance: 83.125 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
GPQA	81.00	Top 9%	STEM (Physics, Chemistry, Biology)
MMLU-Pro	85.00	Top 5%	General Knowledge

GPQA Score: 81.00 - Graduate-level reasoning benchmark

Model Comparison:

Provider: deepinfra

Model Type: completions

Context Size: 163840 tokens

Comparing against 335 models in the database

Performance Analytics for deepseek-r1-0528

Usage Statistics (Last 7 Days):

Total Requests: 1,003 API calls
Average TPS: 349.70 tokens per second
Average Response Time: 31781.30ms
Average Time to First Token: 1850.90ms
Total Cost: $8.84
Average Request Cost: $0.0088

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
10/3/2025	138	238.57	26900.40ms	1112.00ms	$0.78
10/4/2025	101	367.72	32029.40ms	4535.70ms	$0.90
10/5/2025	110	397.49	35335.40ms	2172.30ms	$1.17
10/6/2025	129	330.03	31629.10ms	1627.40ms	$1.04
10/7/2025	126	404.94	30089.50ms	1496.70ms	$1.18
10/8/2025	215	427.56	26915.70ms	1500.80ms	$1.94
10/9/2025	184	294.02	40131.40ms	1547.50ms	$1.83

Performance Summary:

Model: deepseek-r1-0528 by deepinfra

Monitoring Period: 10/2/2025 to 10/9/2025

Average Daily Requests: 143

Peak Daily Requests: 215

Statistics

View Full Statistics

Request Volume

Daily API requests

1,003

Performance (TPS)

Tokens per second

349.70 tokens/s

Category Scores

science#4 writing#4

Benchmark Tests

View Other Benchmarks

GPQA

81.0

STEM (Physics, Chemistry, Biology)

MMLU-Pro

85.0

General Knowledge

Metric	GPQA	MMLU-Pro
Score	81.0	85.0

Compare with Similar Models

gemini-2.5-pro-preview

Code Examples

Integration samples and API usage

Code Samples for deepseek-r1-0528

Python SDK Example:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    api_key="<your_api_key>"
)

response = client.chat.completions.create(
    model="deepseek-r1-0528",
    messages=[
        {"role": "user", "content": "Hello, how are you?"}
    ]
)

print(response.choices[0].message.content)

TypeScript SDK Example:

import OpenAI from 'openai';

const client = new OpenAI({
    baseURL: "https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    apiKey: "<your_api_key>"
});

const response = await client.chat.completions.create({
    model: "deepseek-r1-0528",
    messages: [
        { role: "user", content: "Hello, how are you?" }
    ]
});

console.log(response.choices[0].message.content);

cURL Example:

curl -X POST "https://api.us-east-1.langdb.ai/projects/<your_project_id>/v1/chat/completions" \
  -H "Authorization: Bearer <your_api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-r1-0528",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: deepseek-r1-0528

Provider: deepinfra

API Endpoint: $https://api.us-east-1.langdb.ai

Create API Key

Related Models

Similar models from deepinfra

deepseek-r1-0528

deepseek-r1-0528

Access deepseek-r1-0528 through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

deepseek-chat-v3-0324

deepseek-chat-v3.1

deepseek-prover-v2

DeepSeek-R1

DeepSeek-R1-Distill-Llama-70B

DeepSeek-V3

deepseek-r1-0528 by deepinfra - AI Model Details, Pricing, and Performance Metrics

deepseek-r1-0528

deepseek-r1-0528

Access deepseek-r1-0528 through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

deepseek-chat-v3-0324

deepseek-chat-v3.1

deepseek-prover-v2

DeepSeek-R1

DeepSeek-R1-Distill-Llama-70B

DeepSeek-V3