deepseek-reasoner

completions

bydeepseek

deepseek-reasoner

completions

Published by: deepseekProvider:

deepseek

DeepSeek-V3.2-Exp (Thinking Mode) is an advanced AI model designed to enhance logical reasoning and problem-solving capabilities, leveraging deep learning techniques to provide accurate and contextually relevant insights across various domains.

Released

Sep 29, 2025

Knowledge

Feb 22, 2025

Context

128K

Input

$0.28 / 1M tokens

Output

$0.42 / 1M tokens

Cached

$0.03 / 1M tokens

Accepts: text

Returns: text

Released Sep 29, 2025Knowledge Cutoff: Feb 22, 2025

Context: 128K Input: $0.28 / 1M tokensOutput: $0.42 / 1M tokensCached: $0.03 / 1M tokensAccepts: textReturns: text

Access deepseek-reasoner through LangDB AI Gateway

Recommended

Integrate with deepseek's deepseek-reasoner 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-reasoner

Category Performance Scores:

Academia: Score 65.95 (Top 11% - Rank #37)
Finance: Score 71.85 (Top 10% - Rank #34)
Marketing: Score 59.01 (Top 16% - Rank #54)
Maths: Score 89.70 (Top 7% - Rank #24)
Programming: Score 47.20 (Top 7% - Rank #24)
Science: Score 73.49 (Top 13% - Rank #44)
Writing: Score 57.96 (Top 22% - Rank #74)

Overall Performance: 66.45126984126983 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AA Coding Index	47.20	Top 7%	Programming
AAII	54.00	Top 9%	General
AA Math Index	89.70	Top 7%	Mathematics
GPQA	77.90	Top 17%	STEM (Physics, Chemistry, Biology)
HLE	13.00	Top 9%	General Knowledge
LiveCodeBench	78.40	Top 5%	Programming
MMLU-Pro	85.10	Top 4%	General Knowledge
SciCode	39.10	Top 9%	Scientific

GPQA Score: 77.90 - Graduate-level reasoning benchmark

Model Comparison:

Provider: deepseek

Model Type: completions

Context Size: 128000 tokens

Comparing against 335 models in the database

Performance Analytics for deepseek-reasoner

Usage Statistics (Last 8 Days):

Total Requests: 1,655 API calls
Average TPS: 426.34 tokens per second
Average Response Time: 27271.10ms
Average Time to First Token: 1950.30ms
Total Cost: $1.89
Average Request Cost: $0.0011

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
10/2/2025	5	136.95	19868.70ms	1375.40ms	$0.00
10/3/2025	175	546.08	29244.50ms	2134.20ms	$0.28
10/4/2025	169	447.81	27116.10ms	1931.10ms	$0.19
10/5/2025	388	383.82	23250.40ms	1725.00ms	$0.34
10/6/2025	262	434.98	26532.40ms	1990.70ms	$0.30
10/7/2025	242	453.65	27084.90ms	2142.90ms	$0.31
10/8/2025	164	428.52	30503.90ms	1879.30ms	$0.22
10/9/2025	250	356.03	31216.30ms	2013.60ms	$0.24

Performance Summary:

Model: deepseek-reasoner by deepseek

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

Average Daily Requests: 207

Peak Daily Requests: 388

Statistics

View Full Statistics

Request Volume

Daily API requests

1,655

Performance (TPS)

Tokens per second

426.34 tokens/s

Category Scores

maths#9 programming#8

Benchmark Tests

View Other Benchmarks

AA Coding Index

47.2

Programming

AAII

54.0

General

AA Math Index

89.7

Mathematics

GPQA

77.9

STEM (Physics, Chemistry, Biology)

HLE

13.0

General Knowledge

LiveCodeBench

78.4

Programming

MMLU-Pro

85.1

General Knowledge

SciCode

39.1

Scientific

Metric	AA Coding Index	AAII	AA Math Index	GPQA	HLE	LiveCodeBench	MMLU-Pro	SciCode
Score	47.2	54.0	89.7	77.9	13.0	78.4	85.1	39.1

Compare with Similar Models

gemini-2.5-pro-preview

Code Examples

Integration samples and API usage

Code Samples for deepseek-reasoner

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

Model: deepseek-reasoner

Provider: deepseek

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