AiCostCompare

Qwen3.6 Plus

by Alibaba (Qwen) · qwen/qwen3.6-plus · #153 cheapest of 325 paid models

Prices updated Jul 22, 2026, 1:31 AM UTC · refreshed hourly

Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...

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

Pricing

Input

$0.325

per 1M tokens

Output

$1.95

per 1M tokens

Blended (3:1)

$0.731

3 input : 1 output

Cache read

per 1M cached tokens

Cache write

$0.406

per 1M tokens

Cache & batch economics

Effective prices for Qwen3.6 Plus (no cache-read rate published — hits billed as normal input).

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$0.731$0.0351
50%$0.731$0.0351−0%
90%$0.731$0.0351−0%

*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$0.000747$0.7475
Document summary8,0001,000$0.00455$4.55
Codebase question (RAG)30,0002,000$0.0136$13.65
Long-context analysis150,0005,000$0.0585$58.50

Performance

Intelligence Index

39.6

AA composite quality

Coding Index

54.5

Math Index

Agentic Index

27.6

Output speed

52 tok/s

median

Time to first token

1.73s

median

Time to first answer

107.62s

after reasoning tokens

Artificial Analysis benchmarks

BenchmarkScore
GPQA Diamond88.2%
Humanity's Last Exam25.7%
SciCode40.7%
IFBench75.2%
AA-LCR (Long Context Reasoning)69.7%
Terminal-Bench Hard43.9%
Terminal-Bench 2.161.4%
τ²-Bench (Telecom)97.7%
τ³-Bench Banking16.5%

Design Arena Elo

CategoryElo
Website1,247
UI components1,271
Data viz1,255
SVG1,207
3D1,254
Game dev1,262
Code categories1,257
ASCII art1,165

Specs

Context window

1M

tokens

Max output

66K

tokens

Input modalities

text, image, video

Tokenizer

Qwen3