deepseek-chat-v3-0324

completions

bydeepinfra

deepseek-chat-v3-0324

completions

Published by: deepseekProvider:

deepinfra

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well on a variety of tasks.

Released

Aug 21, 2025

Knowledge

Feb 22, 2025

Context

163840

Input

$0.28 / 1M tokens

Output

$0.88 / 1M tokens

Accepts: text

Returns: text

Released Aug 21, 2025Knowledge Cutoff: Feb 22, 2025

Context: 163840 Input: $0.28 / 1M tokensOutput: $0.88 / 1M tokensAccepts: textReturns: text

Access deepseek-chat-v3-0324 through LangDB AI Gateway

Recommended

Integrate with deepseek's deepseek-chat-v3-0324 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-chat-v3-0324

Category Performance Scores:

Academia: Score 59.15 (Top 20% - Rank #65)
Marketing: Score 31.97 (Top 44% - Rank #143)
Programming: Score 47.20 (Top 18% - Rank #59)
Science: Score 73.50 (Top 21% - Rank #69)
Writing: Score 24.87 (Top 47% - Rank #153)

Overall Performance: 47.338 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AA Coding Index	47.20	Top 18%	Programming
AAII	44.80	Top 18%	General
GPQA	73.50	Top 21%	STEM (Physics, Chemistry, Biology)
HLE	6.30	Top 21%	General Knowledge
LiveCodeBench	57.70	Top 21%	Programming
MMLU-Pro	83.30	Top 12%	General Knowledge
SciCode	36.70	Top 14%	Scientific

GPQA Score: 73.50 - Graduate-level reasoning benchmark

Model Comparison:

Provider: deepinfra

Model Type: completions

Context Size: 163840 tokens

Comparing against 324 models in the database

Performance Analytics for deepseek-chat-v3-0324

Usage Statistics (Last 7 Days):

Total Requests: 619 API calls
Average TPS: 221.41 tokens per second
Average Response Time: 26769.70ms
Average Time to First Token: 1013.10ms
Total Cost: $1.42
Average Request Cost: $0.0023

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
9/5/2025	32	715.90	13431.20ms	864.70ms	$0.11
9/6/2025	114	246.33	24795.10ms	935.50ms	$0.27
9/7/2025	148	214.09	32121.60ms	1002.50ms	$0.40
9/8/2025	70	311.07	23523.80ms	1018.50ms	$0.19
9/9/2025	90	179.06	20186.30ms	731.10ms	$0.13
9/10/2025	129	145.16	33758.30ms	1377.00ms	$0.25
9/11/2025	36	239.25	20603.90ms	825.00ms	$0.07

Performance Summary:

Model: deepseek-chat-v3-0324 by deepinfra

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

Average Daily Requests: 88

Peak Daily Requests: 148

Statistics

View Full Statistics

Request Volume

Daily API requests

619

Performance (TPS)

Tokens per second

221.41 tokens/s

Category Scores

programming#19

Benchmark Tests

View Other Benchmarks

AA Coding Index

47.2

Programming

AAII

44.8

General

GPQA

73.5

STEM (Physics, Chemistry, Biology)

HLE

6.3

General Knowledge

LiveCodeBench

57.7

Programming

MMLU-Pro

83.3

General Knowledge

SciCode

36.7

Scientific

Metric	AA Coding Index	AAII	GPQA	HLE	LiveCodeBench	MMLU-Pro	SciCode
Score	47.2	44.8	73.5	6.3	57.7	83.3	36.7

Compare with Similar Models

gemini-2.5-pro-preview

grok-4

Code Examples

Integration samples and API usage

Code Samples for deepseek-chat-v3-0324

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-chat-v3-0324",
    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-chat-v3-0324",
    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-chat-v3-0324",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: deepseek-chat-v3-0324

Provider: deepinfra

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

Create API Key

Related Models

Similar models from deepinfra

deepseek-chat-v3-0324

deepseek-chat-v3-0324

Access deepseek-chat-v3-0324 through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

deepseek-chat-v3.1

deepseek-prover-v2

DeepSeek-R1

deepseek-r1-0528

DeepSeek-R1-Distill-Llama-70B

DeepSeek-R1-Distill-Qwen-32B

deepseek-chat-v3-0324 by deepinfra - AI Model Details, Pricing, and Performance Metrics

deepseek-chat-v3-0324

deepseek-chat-v3-0324

Access deepseek-chat-v3-0324 through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

deepseek-chat-v3.1

deepseek-prover-v2

DeepSeek-R1

deepseek-r1-0528

DeepSeek-R1-Distill-Llama-70B

DeepSeek-R1-Distill-Qwen-32B