Qwen: Qwen3 14B

Text input Text output
Author's Description

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...

Key Specifications
Cost
$$$
Context
40K
Parameters
14B
Released
Apr 28, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Seed Min P Response Format Reasoning Temperature Presence Penalty Include Reasoning Tools Frequency Penalty Top P Stop Tool Choice Max Tokens
Features

This model supports the following features:

Response Format Tools Reasoning
Performance Summary

Qwen3 14B demonstrates moderate speed performance, ranking in the 29th percentile across various benchmarks, indicating it is not among the fastest models available. However, it offers cost-effective solutions, placing in the 62nd percentile for pricing. A standout feature is its exceptional reliability, achieving a 100% success rate across all benchmarks, meaning it consistently provides usable responses without technical failures. In terms of specific performance, Qwen3 14B exhibits strong capabilities in several areas. It achieves high accuracy in Coding (91.0%), General Knowledge (98.8%), Reasoning (98.0%), and Ethics (99.0%), with its Reasoning performance being particularly impressive at the 93rd percentile. This aligns with its design for complex reasoning. Its Instruction Following is moderate at 50.5% accuracy. A notable weakness is its performance on the Hallucinations benchmark, where it scored only 28.0% accuracy, suggesting a tendency to generate information rather than acknowledge uncertainty. Despite this, its overall accuracy in core knowledge and reasoning tasks is robust, making it a reliable choice for applications requiring precise output and consistent operation.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.12
Completion $0.24

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
DeepInfra
DeepInfra | qwen/qwen3-14b-04-28 40K $0.12 / 1M tokens $0.24 / 1M tokens
Parasail
Parasail | qwen/qwen3-14b-04-28 40K $0.06 / 1M tokens $0.24 / 1M tokens
Nebius
Nebius | qwen/qwen3-14b-04-28 40K $0.06 / 1M tokens $0.24 / 1M tokens
Parasail
Parasail | qwen/qwen3-14b-04-28 40K $0.06 / 1M tokens $0.24 / 1M tokens
NextBit
NextBit | qwen/qwen3-14b-04-28 40K $0.06 / 1M tokens $0.24 / 1M tokens
Chutes
Chutes | qwen/qwen3-14b-04-28 40K $0.06 / 1M tokens $0.24 / 1M tokens
Chutes
Chutes | qwen/qwen3-14b-04-28 40K $0.06 / 1M tokens $0.24 / 1M tokens
Alibaba
Alibaba | qwen/qwen3-14b-04-28 131K $0.228 / 1M tokens $0.91 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by qwen