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 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.

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

This model supports the following parameters:

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

This model supports the following features:

Tools Reasoning Response Format
Performance Summary

Qwen3-14B demonstrates moderate speed performance, ranking in the 26th percentile across benchmarks, and offers competitive pricing, placing it in the 59th percentile. Notably, the model exhibits exceptional reliability with a 100% success rate, indicating minimal technical failures. In terms of performance across categories, Qwen3-14B excels in Reasoning (98.0% accuracy, 96th percentile) and Coding (91.0% accuracy, 76th percentile), aligning with its description for complex reasoning and programming tasks. General Knowledge and Ethics also show strong results at 98.8% and 99.0% accuracy respectively. However, a significant weakness is observed in its ability to acknowledge uncertainty, with a low 28.0% accuracy in the Hallucinations benchmark, suggesting it often fails to appropriately respond with "I don't know" to fictional concepts. Instruction Following is average at 50.5% accuracy, while Email Classification is solid at 97.0%. The model's strengths lie in its robust reasoning, coding capabilities, and high reliability, making it suitable for applications requiring precise logical inference and stable operation. Its primary area for improvement is in managing uncertainty and reducing instances of hallucination.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.06
Completion $0.24

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
DeepInfra
DeepInfra | qwen/qwen3-14b-04-28 40K $0.06 / 1M tokens $0.24 / 1M tokens
Parasail
Parasail | qwen/qwen3-14b-04-28 40K $0.04 / 1M tokens $0.14 / 1M tokens
Nebius
Nebius | qwen/qwen3-14b-04-28 40K $0.08 / 1M tokens $0.24 / 1M tokens
Parasail
Parasail | qwen/qwen3-14b-04-28 40K $0.06 / 1M tokens $0.25 / 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 $0.04 / 1M tokens $0.14 / 1M tokens
Chutes
Chutes | qwen/qwen3-14b-04-28 40K $0.04 / 1M tokens $0.14 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by qwen