deepseek-v3-03-24

completions

byfireworksai

deepseek-v3-03-24

completions

Published by: deepseekProvider:

fireworksai

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

Dec 25, 2024

Knowledge

Jun 28, 2024

License

MIT + Model License (Commercial use allowed)

Context

163840

Input

$0.9 / 1M tokens

Output

$0.9 / 1M tokens

Capabilities: tools

Accepts: text

Returns: text

Released Dec 25, 2024Knowledge Cutoff: Jun 28, 2024License: MIT + Model License (Commercial use allowed)

Context: 163840 Input: $0.9 / 1M tokensOutput: $0.9 / 1M tokensCapabilities: toolsAccepts: textReturns: text

Access deepseek-v3-03-24 through LangDB AI Gateway

Recommended

Integrate with deepseek's deepseek-v3-03-24 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-v3-03-24

Category Performance Scores:

Maths: Score 26.00 (Top 62% - Rank #198)
Finance: Score 29.25 (Top 62% - Rank #198)
Science: Score 58.34 (Top 55% - Rank #176)
Writing: Score 43.72 (Top 57% - Rank #182)
Academia: Score 44.95 (Top 51% - Rank #163)
Marketing: Score 44.06 (Top 51% - Rank #163)
Programming: Score 25.90 (Top 59% - Rank #189)

Overall Performance: 38.88920634920635 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
HLE	3.60	Top 88%	General Knowledge
AIME	25.30	Top 49%	Mathematics
DROP	91.60	Top 0%	General Knowledge
GPQA	57.40	Top 55%	STEM (Physics, Chemistry, Biology)
SciCode	35.40	Top 30%	Scientific
MATH-500	88.70	Top 42%	Mathematics
MMLU-Pro	75.20	Top 48%	General Knowledge
LiveCodeBench	35.90	Top 49%	Programming
AA Math Index	26.00	Top 62%	Mathematics
AA Coding Index	25.90	Top 59%	Programming
AAII	32.50	Top 47%	General

GPQA Score: 57.40 - Graduate-level reasoning benchmark

Model Comparison:

Provider: fireworksai

Model Type: completions

Context Size: 163840 tokens

Comparing against 319 models in the database

Performance Analytics for deepseek-v3-03-24

Usage Statistics (Last 8 Days):

Total Requests: 333 API calls
Average TPS: 1534.40 tokens per second
Average Response Time: 6828.60ms
Average Time to First Token: 1034.30ms
Total Cost: $3.77
Average Request Cost: $0.0113

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
11/11/2025	5	781.75	11691.40ms	1186.80ms	$0.05
11/12/2025	23	1455.81	10337.90ms	1513.00ms	$0.37
11/13/2025	47	1310.86	6810.80ms	975.10ms	$0.45
11/14/2025	34	1790.84	6866.00ms	905.50ms	$0.45
11/15/2025	101	1113.47	6783.40ms	908.50ms	$0.82
11/16/2025	114	2012.02	6000.50ms	1052.00ms	$1.49
11/17/2025	8	2475.00	5556.10ms	1658.40ms	$0.12
11/18/2025	1	987.48	10530.90ms	2119.30ms	$0.01

Performance Summary:

Model: deepseek-v3-03-24 by fireworksai

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

Average Daily Requests: 42

Peak Daily Requests: 114

Statistics

View Full Statistics

Request Volume

Daily API requests

333

Performance (TPS)

Tokens per second

1534.40 tokens/s

Category Scores

Benchmark Tests

View Other Benchmarks

HLE

3.6

General Knowledge

AIME

25.3

Mathematics

DROP

91.6

General Knowledge

GPQA

57.4

STEM (Physics, Chemistry, Biology)

SciCode

35.4

Scientific

MATH-500

88.7

Mathematics

MMLU-Pro

75.2

General Knowledge

LiveCodeBench

35.9

Programming

AA Math Index

26.0

Mathematics

AA Coding Index

25.9

Programming

AAII

32.5

General

Metric	HLE	AIME	DROP	GPQA	SciCode	MATH-500	MMLU-Pro	LiveCodeBench	AA Math Index	AA Coding Index	AAII
Score	3.6	25.3	91.6	57.4	35.4	88.7	75.2	35.9	26.0	25.9	32.5

Compare with Similar Models

Code Examples

Integration samples and API usage

Code Samples for deepseek-v3-03-24

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-v3-03-24",
    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-v3-03-24",
    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-v3-03-24",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: deepseek-v3-03-24

Provider: fireworksai

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

Create API Key

Related Models

Similar models from fireworksai

deepseek-v3-03-24

deepseek-v3-03-24

Access deepseek-v3-03-24 through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

deepseek-r1-05-28

kimi-k2-instruct

llama-v3p1-405b-instruct

mixtral-8x22b-instruct

qwen2-5-vl-32b-instruct

qwen3-coder-480b-a35b-instruct

deepseek-v3-03-24 by fireworksai - AI Model Details, Pricing, and Performance Metrics

deepseek-v3-03-24

deepseek-v3-03-24

Access deepseek-v3-03-24 through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

deepseek-r1-05-28

kimi-k2-instruct

llama-v3p1-405b-instruct

mixtral-8x22b-instruct

qwen2-5-vl-32b-instruct

qwen3-coder-480b-a35b-instruct