AiCostCompare

Qwen3.5 Plus 2026-02-15

by Alibaba (Qwen) · qwen/qwen3.5-plus-02-15 · #138 cheapest of 325 paid models

Prices updated Jul 22, 2026, 1:33 AM UTC · refreshed hourly

The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...

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

Pricing

Input

$0.26

per 1M tokens

Output

$1.56

per 1M tokens

Blended (3:1)

$0.585

3 input : 1 output

Cache read

per 1M cached tokens

Cache write

per 1M tokens

Cache & batch economics

Effective prices for Qwen3.5 Plus 2026-02-15 (no cache-read rate published — hits billed as normal input).

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$0.585$0.0281
50%$0.585$0.0281−0%
90%$0.585$0.0281−0%

*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$0.000598$0.598
Document summary8,0001,000$0.00364$3.64
Codebase question (RAG)30,0002,000$0.0109$10.92
Long-context analysis150,0005,000$0.0468$46.80

Performance

Intelligence Index

AA composite quality

Coding Index

Math Index

Agentic Index

Output speed

median

Time to first token

median

Time to first answer

after reasoning tokens

Design Arena Elo

CategoryElo
Website1,215
UI components1,219
Data viz1,171
SVG1,154
3D1,178
Game dev1,164
Code categories1,200
ASCII art1,136

Specs

Context window

1M

tokens

Max output

66K

tokens

Input modalities

text, image, video

Tokenizer

Qwen3