Alibaba

Qwen3.5 35B-A3B — Benchmark Scores, Pricing & Performance Analysis

OPEN SOURCE
Input Cost
$0.31/1M
Output Cost
$1.3/1M
Context Window
262K
Max Output
66K
Accepts
text, image, video, audio

Qwen3.5 35B-A3B by Alibaba demonstrates competitive pricing. View detailed benchmark data including scores across coding, math, reasoning, speed, and cost metrics.

Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.

Coding Benchmarks

AA Coding Index
3763rd of 96

Artificial Analysis composite coding score

Artificial Analysis (via OpenRouter)

Reasoning Benchmarks

GPQA Diamond
81.7%53rd of 140

Graduate-level science Q&A by domain experts

Papers
τ²-Bench Airline
73.2%36th of 93

Multi-turn service agent making tool calls under strict policy constraints

OpenRouter (measured)

Cost Benchmarks

Input Cost
$0.31219th of 413

Cost per 1M input tokens

OpenRouter API
Output Cost
$1.3215th of 413

Cost per 1M output tokens

OpenRouter API
Cached Input Cost
$0.1685th of 136

Cost per 1M cached input tokens — the price that actually applies to a long agent conversation

OpenRouter API

Context Benchmarks

Context Length
262K108th of 451

Maximum context window size

OpenRouter API

Available from 16 providers

The same model costs different amounts depending on who serves it. You can bring your own key for 3 of these — connect it here.

ProviderInput / 1MOutput / 1MCached inContextYour key
EmpirioLabs AI$0.057$0.459$0.057256K
Merge Gateway$0.057$0.459$0.020357131K
OrcaRouter$0.057$0.459262K
302.AI$0.06$0.46262K
Requesty$0.14$1$0.05262K
Kilo Gateway$0.1625$1.3256K
NanoGPT$0.225$1.8$0.1125260K
SiliconFlow$0.24$1.8262K
Alibaba$0.25$2262KSupported
Hugging Face$0.25$2262KSupported
Jalapeno Cloud$0.25$2262K
Mixlayer$0.25$1.3262K
NovitaAI$0.25$2262K
Weights & Biases$0.25$1.25$0.25262K
Ofox$0.29$1.83$0.29262K
OpenRouter$0.3125$1.25$0.15625262KSupported

Qwen3.5 35B-A3B — Benchmark Scores Overview

Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).

Qwen3.5 35B-A3B — Frequently Asked Questions

How much does Qwen3.5 35B-A3B cost?

Qwen3.5 35B-A3B costs $0.31 per 1M input tokens and $1.3 per 1M output tokens. This makes it one of the more affordable models.

What is the context window of Qwen3.5 35B-A3B?

Qwen3.5 35B-A3B has a context window of 262K tokens. This determines how much text, conversation history, and code the model can process in a single request.

Who created Qwen3.5 35B-A3B?

Qwen3.5 35B-A3B was created by Alibaba. It is classified as a open source model in our catalogue.

Is Qwen3.5 35B-A3B open source?

Yes, Qwen3.5 35B-A3B is an open-source model. The model weights are publicly available for download and self-hosting.