Qwen: Qwen3 30B A3B

Text input Text output
Author's Description

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...

Key Specifications
Cost
$$$
Context
40K
Parameters
30B
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 30B A3B, the latest Qwen model, demonstrates a strong overall performance profile, particularly excelling in reliability and specific cognitive tasks. While its speed performance is moderate, ranking in the 20th percentile across benchmarks, it offers competitive pricing, placing in the 51st percentile. A standout feature is its exceptional reliability, achieving a 100% success rate across all 8 benchmarks, indicating minimal technical failures and consistent response generation. The model exhibits significant strengths in knowledge-based and ethical reasoning tasks, achieving perfect 100% accuracy in both General Knowledge and Ethics benchmarks. It also performs very well in Coding (94.0% accuracy, 89th percentile) and Reasoning (96.0% accuracy, 85th percentile), showcasing its advanced capabilities in complex problem-solving. Its ability to handle multilingual support and advanced agent tasks, as highlighted in its description, is reflected in these strong reasoning scores. Hallucination rates are low at 96.0% accuracy, indicating a good understanding of uncertainty. While Mathematics performance is solid at 93.0% accuracy (73rd percentile), Instruction Following is a relative weakness at 60.8% accuracy (58th percentile), suggesting room for improvement in adhering to highly complex, multi-step instructions. The model's unique architecture, combining dense and MoE components, appears to contribute to its high accuracy in critical areas.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.08
Completion $0.28

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
DeepInfra
DeepInfra | qwen/qwen3-30b-a3b-04-28 40K $0.08 / 1M tokens $0.28 / 1M tokens
InferenceNet
InferenceNet | qwen/qwen3-30b-a3b-04-28 16K $0.08 / 1M tokens $0.28 / 1M tokens
Parasail
Parasail | qwen/qwen3-30b-a3b-04-28 40K $0.08 / 1M tokens $0.28 / 1M tokens
Nebius
Nebius | qwen/qwen3-30b-a3b-04-28 40K $0.08 / 1M tokens $0.28 / 1M tokens
Novita
Novita | qwen/qwen3-30b-a3b-04-28 40K $0.09 / 1M tokens $0.45 / 1M tokens
Fireworks
Fireworks | qwen/qwen3-30b-a3b-04-28 131K $0.08 / 1M tokens $0.28 / 1M tokens
Friendli
Friendli | qwen/qwen3-30b-a3b-04-28 131K $0.15 / 1M tokens $0.6 / 1M tokens
NextBit
NextBit | qwen/qwen3-30b-a3b-04-28 32K $0.08 / 1M tokens $0.28 / 1M tokens
Chutes
Chutes | qwen/qwen3-30b-a3b-04-28 40K $0.08 / 1M tokens $0.28 / 1M tokens
SiliconFlow
SiliconFlow | qwen/qwen3-30b-a3b-04-28 131K $0.08 / 1M tokens $0.28 / 1M tokens
NCompass
NCompass | qwen/qwen3-30b-a3b-04-28 131K $0.08 / 1M tokens $0.28 / 1M tokens
Crusoe
Crusoe | qwen/qwen3-30b-a3b-04-28 40K $0.08 / 1M tokens $0.28 / 1M tokens
NextBit
NextBit | qwen/qwen3-30b-a3b-04-28 32K $0.14 / 1M tokens $0.55 / 1M tokens
Chutes
Chutes | qwen/qwen3-30b-a3b-04-28 40K $0.08 / 1M tokens $0.28 / 1M tokens
AtlasCloud
AtlasCloud | qwen/qwen3-30b-a3b-04-28 32K $0.08 / 1M tokens $0.28 / 1M tokens
Alibaba
Alibaba | qwen/qwen3-30b-a3b-04-28 131K $0.13 / 1M tokens $0.52 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by qwen