deepseek-v3

completions

On:fireworksaitogetheraideepinfra

deepseek-v3

completions

Published by: deepseekProviders:

fireworksai togetherai deepinfra

A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token from Deepseek.

Provider	Input	Output
fireworksai	$0.9 / 1M tokens	$0.9 / 1M tokens
togetherai	$1.25 / 1M tokens	$1.25 / 1M tokens
deepinfra	$0.49 / 1M tokens	$0.89 / 1M tokens

Released

Dec 25, 2024

Knowledge

Jun 28, 2024

Context

128K

Input

$0.9 / 1M tokens

Output

$0.9 / 1M tokens

Accepts: text

Returns: text

Providers	Context	Input Price	Output Price	Input Formats	Output Formats	License
fireworksai	128K tokens	$0.9 / 1M tokens	$0.9 / 1M tokens	text	text	MIT + Model License (Commercial use allowed)
togetherai	131072 tokens	$1.25 / 1M tokens	$1.25 / 1M tokens	text	text	MIT + Model License (Commercial use allowed)
deepinfra	16K tokens	$0.49 / 1M tokens	$0.89 / 1M tokens	text	text	MIT + Model License (Commercial use allowed)

Released Dec 25, 2024Knowledge Cutoff: Jun 28, 2024

Access deepseek-v3 through LangDB AI Gateway

Recommended

Integrate with deepseek's deepseek-v3 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

Available from 3 providers

Provider:

Benchmark Results for deepseek-v3

Category Performance Scores:

Academia: Score 44.95 (Top 44% - Rank #152)
Finance: Score 29.25 (Top 54% - Rank #187)
Marketing: Score 44.15 (Top 42% - Rank #145)
Maths: Score 26.00 (Top 53% - Rank #183)
Programming: Score 35.60 (Top 33% - Rank #114)
Science: Score 58.48 (Top 48% - Rank #166)
Writing: Score 43.81 (Top 47% - Rank #163)

Overall Performance: 40.31936507936508 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AIME	25.30	Top 45%	Mathematics
AA Coding Index	35.60	Top 33%	Programming
AAII	32.50	Top 36%	General
AA Math Index	26.00	Top 53%	Mathematics
DROP	91.60	Top 0%	General Knowledge
GPQA	57.40	Top 47%	STEM (Physics, Chemistry, Biology)
HLE	3.60	Top 87%	General Knowledge
LiveCodeBench	35.90	Top 36%	Programming
MATH-500	88.70	Top 36%	Mathematics
MMLU	88.50	Top 15%	General Knowledge
MMLU-Pro	75.55	Top 37%	General Knowledge
SciCode	35.40	Top 23%	Scientific

MMLU Score: 88.50 - Massive Multitask Language Understanding benchmark

GPQA Score: 57.40 - Graduate-level reasoning benchmark

Model Comparison:

Provider: fireworksai

Model Type: completions

Context Size: 128000 tokens

Comparing against 345 models in the database

Performance Analytics for deepseek-v3

Usage Statistics (Last 2 Days):

Total Requests: 4 API calls
Average TPS: 108.12 tokens per second
Average Response Time: 5873.30ms
Average Time to First Token: 566.40ms
Total Cost: $0.00
Average Request Cost: $0.0007

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
9/15/2025	3	113.60	5176.00ms	481.30ms	$0.00
9/16/2025	1	97.43	7965.10ms	821.70ms	$0.00

Performance Summary:

Model: deepseek-v3 by fireworksai

Monitoring Period: 9/13/2025 to 9/20/2025

Average Daily Requests: 2

Peak Daily Requests: 3

Statistics

View Full Statistics

Request Volume

Daily API requests

Performance (TPS)

Tokens per second

108.12 tokens/s

Category Scores

Benchmark Tests

View Other Benchmarks

AIME

25.3

Mathematics

AA Coding Index

35.6

Programming

AAII

32.5

General

AA Math Index

26.0

Mathematics

DROP

91.6

General Knowledge

GPQA

57.4

STEM (Physics, Chemistry, Biology)

HLE

3.6

General Knowledge

LiveCodeBench

35.9

Programming

MATH-500

88.7

Mathematics

MMLU

88.5

General Knowledge

MMLU-Pro

75.6

General Knowledge

SciCode

35.4

Scientific

Metric	AIME	AA Coding Index	AAII	AA Math Index	DROP	GPQA	HLE	LiveCodeBench	MATH-500	MMLU	MMLU-Pro	SciCode
Score	25.3	35.6	32.5	26.0	91.6	57.4	3.6	35.9	88.7	88.5	75.6	35.4

Compare with Similar Models

gemini-2.5-pro-preview

grok-4

Code Examples

Integration samples and API usage

Code Samples for deepseek-v3

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

Model: deepseek-v3

Provider: fireworksai

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

Create API Key

Related Models

Similar models from fireworksai

deepseek-v3

deepseek-v3

Access deepseek-v3 through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

deepseek-chat-v3-0324

deepseek-chat-v3.1

deepseek-prover-v2

deepseek-r1

DeepSeek-R1

deepseek-r1-0528

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

deepseek-v3

deepseek-v3

Access deepseek-v3 through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

deepseek-chat-v3-0324

deepseek-chat-v3.1

deepseek-prover-v2

deepseek-r1

DeepSeek-R1

deepseek-r1-0528