Qwen: Qwen3.5 Plus 2026-04-20

Text input Image input Video input Text output
Author's Description

Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...

Key Specifications
Cost
$$$$$
Context
1M
Released
Apr 26, 2026
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

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

This model supports the following features:

Tools Reasoning Structured Outputs Response Format
Performance Summary

Qwen3.5 Plus (April 2026) from Alibaba demonstrates a unique performance profile, excelling in reliability while exhibiting slower response times and premium pricing. The model consistently delivers usable responses, boasting exceptional reliability with a 100% success rate across all benchmarks, indicating minimal technical failures. However, its speed ranking places it among models with longer response times (10th percentile), and its price ranking suggests it is positioned at premium pricing levels (11th percentile). In terms of specific benchmarks, Qwen3.5 Plus shows strong performance in Hallucinations (Baseline) with 98.0% accuracy, indicating a good ability to acknowledge uncertainty. Its Instruction Following (Baseline) capability is also robust at 76.0% accuracy, suggesting proficiency in handling complex directives. A standout achievement is its perfect 100.0% accuracy in Email Classification (Baseline), where it is noted as the most accurate model at its price point and among models of comparable speed. This highlights a key strength in classification tasks. The primary weakness lies in its speed and cost, as evidenced by the high duration and cost metrics across all benchmarks.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.4
Completion $2.4

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Alibaba
Alibaba | qwen/qwen3.5-plus-20260420 1M $0.4 / 1M tokens $2.4 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by qwen