Qwen: Qwen3 4B

Text input Text output Unavailable
Author's Description

Qwen3-4B is a 4 billion parameter dense language model from the Qwen3 series, designed to support both general-purpose and reasoning-intensive tasks. It introduces a dual-mode architecture—thinking and non-thinking—allowing dynamic switching between high-precision logical reasoning and efficient dialogue generation. This makes it well-suited for multi-turn chat, instruction following, and complex agent workflows.

Key Specifications
Cost
$$$
Context
131K
Parameters
4B
Released
Apr 30, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

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

This model supports the following features:

Reasoning Tools Response Format
Performance Summary

Qwen3 4B, a 4 billion parameter model from qwen, demonstrates moderate speed performance, ranking in the 20th percentile across benchmarks. It offers competitive pricing, positioned at the 50th percentile. Notably, the model exhibits exceptional reliability with a 98% success rate, indicating minimal technical failures and consistent response generation. In terms of performance across categories, Qwen3 4B shows strong capabilities in Reasoning (96.0% accuracy, 87th percentile) and General Knowledge (99.0% accuracy, 66th percentile), suggesting proficiency in complex problem-solving and broad factual recall. Its Mathematics performance is also solid at 89.0% accuracy (58th percentile). However, the model struggles with Instruction Following (44.9% accuracy, 39th percentile) and Hallucinations (82.0% accuracy, 28th percentile), indicating areas for improvement in adhering to complex directives and acknowledging uncertainty. Email Classification also presents a weakness with 93.0% accuracy (22nd percentile). Its dual-mode architecture aims to balance high-precision reasoning with efficient dialogue, making it suitable for multi-turn chat and agent workflows despite some accuracy limitations in specific tasks.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.0715
Completion $0.273

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Alibaba
Alibaba | qwen/qwen3-4b-04-28 131K $0.0715 / 1M tokens $0.273 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by qwen