deepseek-chat

completions

bydeepseek

deepseek-chat

completions

Published by: deepseekProvider:

deepseek

DeepSeek-V3.2-Exp (Non-thinking Mode) is an advanced conversational AI model designed to provide intelligent

Released

Sep 29, 2025

Knowledge

Feb 22, 2025

License

MIT

Context

128K

Input

$0.28 / 1M tokens

Output

$0.42 / 1M tokens

Cached

$0.03 / 1M tokens

Capabilities: tools

Accepts: text

Returns: text

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

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

Access deepseek-chat through LangDB AI Gateway

Recommended

Integrate with deepseek's deepseek-chat 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

Category Performance Scores:

Maths: Score 59.00 (Top 44% - Rank #142)
Finance: Score 55.70 (Top 35% - Rank #113)
Science: Score 71.27 (Top 30% - Rank #97)
Writing: Score 55.24 (Top 35% - Rank #113)
Academia: Score 63.75 (Top 22% - Rank #71)
Marketing: Score 56.32 (Top 30% - Rank #97)
Programming: Score 42.80 (Top 25% - Rank #81)

Overall Performance: 57.72523809523809 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
HLE	10.50	Top 21%	General Knowledge
GPQA	75.10	Top 28%	STEM (Physics, Chemistry, Biology)
SciCode	38.70	Top 22%	Scientific
MMLU-Pro	83.70	Top 18%	General Knowledge
LiveCodeBench	59.30	Top 33%	Programming
AA Math Index	59.00	Top 44%	Mathematics
AA Coding Index	42.80	Top 25%	Programming
AAII	52.40	Top 17%	General

GPQA Score: 75.10 - Graduate-level reasoning benchmark

Model Comparison:

Provider: deepseek

Model Type: completions

Context Size: 128000 tokens

Comparing against 322 models in the database

Performance Analytics for deepseek-chat

Usage Statistics (Last 7 Days):

Total Requests: 372 API calls
Average TPS: 823.15 tokens per second
Average Response Time: 12803.00ms
Average Time to First Token: 1598.60ms
Total Cost: $0.28
Average Request Cost: $0.0007

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
11/11/2025	1	1376.79	19117.00ms	2088.30ms	$0.00
11/12/2025	6	100.55	9667.00ms	1098.60ms	$0.00
11/13/2025	77	649.13	19508.40ms	1606.70ms	$0.08
11/14/2025	1	325.03	45100.00ms	3159.40ms	$0.01
11/15/2025	48	2057.11	9780.30ms	2003.50ms	$0.05
11/16/2025	18	609.55	11854.70ms	1440.50ms	$0.01
11/17/2025	221	734.16	11110.90ms	1524.90ms	$0.14

Performance Summary:

Model: deepseek-chat by deepseek

Monitoring Period: 11/11/2025 to 11/18/2025

Average Daily Requests: 53

Peak Daily Requests: 221

Statistics

View Full Statistics

Request Volume

Daily API requests

372

Performance (TPS)

Tokens per second

823.15 tokens/s

Category Scores

Benchmark Tests

View Other Benchmarks

HLE

10.5

General Knowledge

GPQA

75.1

STEM (Physics, Chemistry, Biology)

SciCode

38.7

Scientific

MMLU-Pro

83.7

General Knowledge

LiveCodeBench

59.3

Programming

AA Math Index

59.0

Mathematics

AA Coding Index

42.8

Programming

AAII

52.4

General

Metric	HLE	GPQA	SciCode	MMLU-Pro	LiveCodeBench	AA Math Index	AA Coding Index	AAII
Score	10.5	75.1	38.7	83.7	59.3	59.0	42.8	52.4

Compare with Similar Models

claude-opus-4.5

gemini-3-flash-preview

Code Examples

Integration samples and API usage

Code Samples for deepseek-chat

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

Model: deepseek-chat

Provider: deepseek

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

Create API Key

Related Models

Similar models from deepseek

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

deepseek-chat

deepseek-chat

Access deepseek-chat through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

deepseek-reasoner