qwen3-14b

completions

On:deepinfraparasail

qwen3-14b

completions

Published by: qwenProviders:

deepinfra parasail

Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for tasks like math, programming, and logical inference, and a "non-thinking" mode for general-purpose conversation. The model is fine-tuned for instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling.

Provider	Input	Output
deepinfra	$0.06 / 1M tokens	$0.24 / 1M tokens
parasail	$0.06 / 1M tokens	$0.25 / 1M tokens

Released

Apr 28, 2025

Knowledge

Oct 30, 2024

Context

40960

Input

$0.06 / 1M tokens

Output

$0.24 / 1M tokens

Capabilities: tools

Accepts: text

Returns: text

Providers	Context	Input Price	Output Price	Input Formats	Output Formats
deepinfra	40960 tokens	$0.06 / 1M tokens	$0.24 / 1M tokens	text	text
parasail	40960 tokens	$0.06 / 1M tokens	$0.25 / 1M tokens	text	text

Released Apr 28, 2025Knowledge Cutoff: Oct 30, 2024

Access qwen3-14b through LangDB AI Gateway

Recommended

Integrate with qwen's qwen3-14b 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 2 providers

Provider:

Benchmark Results for qwen3-14b

Category Performance Scores:

Academia: Score 38.10 (Top 66% - Rank #222)
Finance: Score 43.60 (Top 45% - Rank #151)
Marketing: Score 29.32 (Top 92% - Rank #309)
Maths: Score 58.00 (Top 35% - Rank #118)
Programming: Score 19.80 (Top 79% - Rank #265)
Science: Score 50.22 (Top 72% - Rank #242)
Writing: Score 30.32 (Top 91% - Rank #305)

Overall Performance: 38.478809523809524 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AIME	28.00	Top 51%	Mathematics
AA Coding Index	19.80	Top 79%	Programming
AAII	29.20	Top 54%	General
AA Math Index	58.00	Top 35%	Mathematics
GPQA	47.00	Top 69%	STEM (Physics, Chemistry, Biology)
HLE	4.20	Top 74%	General Knowledge
LiveCodeBench	28.00	Top 64%	Programming
MATH-500	87.10	Top 48%	Mathematics
MMLU-Pro	67.50	Top 70%	General Knowledge
SciCode	26.50	Top 59%	Scientific

GPQA Score: 47.00 - Graduate-level reasoning benchmark

Model Comparison:

Provider: deepinfra

Model Type: completions

Context Size: 40960 tokens

Comparing against 335 models in the database

Category Scores

Benchmark Tests

View Other Benchmarks

AIME

28.0

Mathematics

AA Coding Index

19.8

Programming

AAII

29.2

General

AA Math Index

58.0

Mathematics

GPQA

47.0

STEM (Physics, Chemistry, Biology)

HLE

4.2

General Knowledge

LiveCodeBench

28.0

Programming

MATH-500

87.1

Mathematics

MMLU-Pro

67.5

General Knowledge

SciCode

26.5

Scientific

Metric	AIME	AA Coding Index	AAII	AA Math Index	GPQA	HLE	LiveCodeBench	MATH-500	MMLU-Pro	SciCode
Score	28.0	19.8	29.2	58.0	47.0	4.2	28.0	87.1	67.5	26.5

Compare with Similar Models

gemini-2.5-pro-preview

Code Examples

Integration samples and API usage

Code Samples for qwen3-14b

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="qwen3-14b",
    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: "qwen3-14b",
    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": "qwen3-14b",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: qwen3-14b

Provider: deepinfra

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

Create API Key

Related Models

Similar models from deepinfra

qwen3-14b

qwen3-14b

Access qwen3-14b through LangDB AI Gateway

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-r1-0528

DeepSeek-R1-Distill-Llama-70B

qwen3-14b by deepinfra - AI Model Details, Pricing, and Performance Metrics

qwen3-14b

qwen3-14b

Access qwen3-14b through LangDB AI Gateway

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-r1-0528

DeepSeek-R1-Distill-Llama-70B