Qwen: Qwen3 30B A3B Instruct 2507

Text input Text output
Author's Description

Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...

Key Specifications
Cost
$$$
Context
131K
Parameters
30B
Released
Jul 29, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Seed Top P Response Format Temperature Presence Penalty Max Tokens
Features

This model supports the following features:

Response Format
Performance Summary

Qwen3 30B A3B Instruct 2507, a 30.5B-parameter mixture-of-experts model with 3.3B active parameters, demonstrates strong overall performance, particularly in speed and reliability. It performs among the fastest models, typically ranking in the top tier (65th percentile), and offers competitive pricing (59th percentile). Notably, the model exhibits exceptional reliability with a 100% success rate across all benchmarks, indicating minimal technical failures. The model excels in specific areas, achieving perfect accuracy in Keyword Topic Relevance Classification and Ethics (Baseline), where it is also identified as the most accurate model at its price point and speed. It shows strong performance in Mathematics (94.0% accuracy, 83rd percentile) and Coding (93.0% accuracy, 82nd percentile), aligning with its design for high-quality instruction following and agentic tool use. Its ability to appropriately acknowledge uncertainty is high, with 98.0% accuracy in Hallucinations (Baseline). While General Knowledge (97.0% accuracy) and Reasoning (78.0% accuracy) are solid, Email Classification (94.0% accuracy, 25th percentile) and Instruction Following (59.8% accuracy, 56th percentile) represent areas for potential improvement compared to its other strengths. Overall, Qwen3 30B A3B Instruct 2507 is a robust model with competitive speed, price, and outstanding reliability, making it a strong contender for tasks requiring high-quality instruction following and specialized reasoning.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.13
Completion $0.52

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Alibaba
Alibaba | qwen/qwen3-30b-a3b-instruct-2507 131K $0.13 / 1M tokens $0.52 / 1M tokens
Nebius
Nebius | qwen/qwen3-30b-a3b-instruct-2507 262K $0.1 / 1M tokens $0.3 / 1M tokens
Chutes
Chutes | qwen/qwen3-30b-a3b-instruct-2507 262K $0.09 / 1M tokens $0.3 / 1M tokens
SiliconFlow
SiliconFlow | qwen/qwen3-30b-a3b-instruct-2507 262K $0.09 / 1M tokens $0.3 / 1M tokens
AtlasCloud
AtlasCloud | qwen/qwen3-30b-a3b-instruct-2507 131K $0.09 / 1M tokens $0.3 / 1M tokens
Chutes
Chutes | qwen/qwen3-30b-a3b-instruct-2507 262K $0.09 / 1M tokens $0.3 / 1M tokens
AtlasCloud
AtlasCloud | qwen/qwen3-30b-a3b-instruct-2507 131K $0.1 / 1M tokens $0.3 / 1M tokens
WandB
WandB | qwen/qwen3-30b-a3b-instruct-2507 262K $0.1 / 1M tokens $0.3 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by qwen