deepseek-r1-05-28

completions

byfireworksai

deepseek-r1-05-28

completions

Published by: deepseekProvider:

fireworksai

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.

Released

Jan 20, 2025

Knowledge

Jul 24, 2024

License

MIT

Context

163840

Input

$3 / 1M tokens

Output

$8 / 1M tokens

Capabilities: tools

Accepts: text

Returns: text

Released Jan 20, 2025Knowledge Cutoff: Jul 24, 2024License: MIT

Context: 163840 Input: $3 / 1M tokensOutput: $8 / 1M tokensCapabilities: toolsAccepts: textReturns: text

Access deepseek-r1-05-28 through LangDB AI Gateway

Recommended

Integrate with deepseek's deepseek-r1-05-28 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

Benchmark Results for deepseek-r1-05-28

Category Performance Scores:

Academia: Score 66.65 (Top 7% - Rank #23)
Finance: Score 72.90 (Top 4% - Rank #13)
Marketing: Score 60.10 (Top 1% - Rank #4)
Maths: Score 93.80 (Top 3% - Rank #10)
Programming: Score 58.70 (Top 3% - Rank #10)
Science: Score 81.30 (Top 6% - Rank #20)
Writing: Score 47.54 (Top 3% - Rank #10)

Overall Performance: 68.71357142857143 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AIME	89.30	Top 3%	Mathematics
AA Coding Index	58.70	Top 3%	Programming
AAII	52.00	Top 8%	General
AA Math Index	93.80	Top 3%	Mathematics
DROP	92.20	Top 0%	General Knowledge
GPQA	81.30	Top 6%	STEM (Physics, Chemistry, Biology)
HLE	14.90	Top 6%	General Knowledge
LiveCodeBench	77.00	Top 3%	Programming
MATH-500	98.30	Top 3%	Mathematics
MMLU	90.80	Top 2%	General Knowledge
MMLU-Pro	84.45	Top 6%	General Knowledge
SciCode	40.30	Top 5%	Scientific

MMLU Score: 90.80 - Massive Multitask Language Understanding benchmark

GPQA Score: 81.30 - Graduate-level reasoning benchmark

Model Comparison:

Provider: fireworksai

Model Type: completions

Context Size: 163840 tokens

Comparing against 324 models in the database

Performance Analytics for deepseek-r1-05-28

Usage Statistics (Last 2 Days):

Total Requests: 5 API calls
Average TPS: 443.04 tokens per second
Average Response Time: 13347.70ms
Average Time to First Token: 787.30ms
Total Cost: $0.13
Average Request Cost: $0.0259

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
9/7/2025	4	404.99	15515.20ms	810.90ms	$0.11
9/9/2025	1	947.94	4677.50ms	692.90ms	$0.02

Performance Summary:

Model: deepseek-r1-05-28 by fireworksai

Monitoring Period: 9/4/2025 to 9/11/2025

Average Daily Requests: 3

Peak Daily Requests: 4

Statistics

View Full Statistics

Request Volume

Daily API requests

Performance (TPS)

Tokens per second

443.04 tokens/s

Category Scores

academia#10 finance#6 marketing#2 maths#5 programming#6 science#10 writing#5

Benchmark Tests

View Other Benchmarks

AIME

89.3

Mathematics

AA Coding Index

58.7

Programming

AAII

52.0

General

AA Math Index

93.8

Mathematics

DROP

92.2

General Knowledge

GPQA

81.3

STEM (Physics, Chemistry, Biology)

HLE

14.9

General Knowledge

LiveCodeBench

77.0

Programming

MATH-500

98.3

Mathematics

MMLU

90.8

General Knowledge

MMLU-Pro

84.5

General Knowledge

SciCode

40.3

Scientific

Metric	AIME	AA Coding Index	AAII	AA Math Index	DROP	GPQA	HLE	LiveCodeBench	MATH-500	MMLU	MMLU-Pro	SciCode
Score	89.3	58.7	52.0	93.8	92.2	81.3	14.9	77.0	98.3	90.8	84.5	40.3

Compare with Similar Models

gemini-2.5-pro-preview

grok-4

Code Examples

Integration samples and API usage

Code Samples for deepseek-r1-05-28

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-r1-05-28",
    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-r1-05-28",
    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-r1-05-28",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: deepseek-r1-05-28

Provider: fireworksai

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

Create API Key

Related Models

Similar models from fireworksai

deepseek-r1-05-28

deepseek-r1-05-28

Access deepseek-r1-05-28 through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

deepseek-r1

deepseek-v3

deepseek-v3-03-24

gpt-oss-120b

gpt-oss-20b

kimi-k2-instruct

deepseek-r1-05-28 by fireworksai - AI Model Details, Pricing, and Performance Metrics

deepseek-r1-05-28

deepseek-r1-05-28

Access deepseek-r1-05-28 through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

deepseek-r1

deepseek-v3

deepseek-v3-03-24

gpt-oss-120b

gpt-oss-20b

kimi-k2-instruct