AiCostCompare

Qwen3.5-35B-A3B

by Alibaba (Qwen) · qwen/qwen3.5-35b-a3b · #147 cheapest of 422 paid models

Prices updated Sep 19, 2026, 6:21 PM UTC · refreshed hourly

The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...

Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol

Pricing

Input

$0.163

per 1M tokens

Output

$1.30

per 1M tokens

Blended (3:1)

$0.447

3 input : 1 output

Cache read

per 1M cached tokens

Cache write

per 1M tokens

Cache & batch economics

Effective prices for Qwen3.5-35B-A3B (no cache-read rate published — hits billed as normal input).

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$0.447$0.0179
50%$0.447$0.0179−0%
90%$0.447$0.0179−0%

*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.

What a request costs

WorkloadInput tokensOutput tokensCost / requestCost / 1K requests
Short chat message500300$0.000471$0.4713
Document summary8,0001,000$0.0026$2.60
Codebase question (RAG)30,0002,000$0.007475$7.48
Long-context analysis150,0005,000$0.0309$30.88

Performance

Intelligence Index

19.3

AA composite quality

Coding Index

37

Math Index

Agentic Index

Output speed

0 tok/s

median

Time to first token

0s

median

Time to first answer

0s

after reasoning tokens

Artificial Analysis benchmarks

BenchmarkScore
GPQA Diamond84.5%
Humanity's Last Exam21.0%
IFBench72.5%
AA-LCR (Long Context Reasoning)72.0%
Terminal-Bench Hard26.5%
τ²-Bench (Telecom)89.2%

Specs

Context window

262K

tokens

Max output

66K

tokens

Input modalities

text, image, video

Tokenizer

Qwen3