Qwen3.6 27B API Pricing

Alibaba · released 2026-04-22

Also searched as: Qwen 3.6 27B pricing

Qwen3.6 27B price

$0.60
input / 1M tokens
0.060¢ / 1K
$3.60
output / 1M tokens
0.360¢ / 1K
$1.35
blended / 1M tokens
0.135¢ / 1K

Single public source; verify on the official site

Official list price from Alibaba, as recorded by models.dev

What it actually costs

WorkloadTokensCost
Short chat reply500 in / 300 out0.138¢
RAG query4,000 in / 500 out0.42¢
Long document summary50,000 in / 1,000 out$0.0336
Code review of a 2k-line file30,000 in / 2,000 out$0.0252
1,000 chat replies/day for 30 days30,000 × (500 in / 300 out)$41.40

Cost = (input tokens ÷ 1,000,000 × $0.60) + (output tokens ÷ 1,000,000 × $3.60).

Benchmarks

BenchmarkValueSourceAs of
Epoch Capabilities Index (ECI) 146.7 epoch 2026-04-22
Epoch Mock AIME accuracy 91.1% epoch 2026-04-22
Epoch FrontierMath (T1–3) accuracy 35.1% epoch 2026-04-22
Arena text rating No public data yet
Arena coding rating (human preference votes, not task accuracy) No public data yet
Arena math rating No public data yet
Arena WebDev rating No public data yet

LiveBench

Shown on this model page only — LiveBench data never appears in any leaderboard, comparison table or structured data on this site.

LiveBench metricValueAs of
LiveBench Global Average64.02026-06-25
LiveBench Reasoning70.32026-06-25
LiveBench Coding71.82026-06-25
LiveBench Agentic Coding39.32026-06-25
LiveBench Mathematics79.92026-06-25
LiveBench Data Analysis70.42026-06-25
LiveBench Language63.32026-06-25
LiveBench Instruction Following53.22026-06-25

LiveBench leaderboard (livebench.ai, github.com/LiveBench/new-livebench), CC BY-SA 4.0 — livebench.ai · github.com/LiveBench/new-livebench · CC BY-SA 4.0

Similar ECI, lower price

ModelECIBlended $/1M
GPT-5.4 nano146.4$0.4625
DeepSeek V4 Flash146.9$0.525
MiniMax-M3147.6$0.525
Gemini 3.1 Flash Lite144.9$0.5625
GPT-5 Mini146.1$0.6875

More from Alibaba

ModelReleasedBlended $/1M
Qwen-Image-2.1-Turbo2026-10-09—
Qwen-Image-2.1-Pro2026-10-02—
Qwen 3.8 Max Prime2026-09-23—
Qwen3.8 Omni Flash2026-09-17$0.23
Qwen-Image-2.12026-09-14—
Qwen3.8 Max 09022026-09-02$3.00
Qwen3.8 Flash Next2026-08-27—
Qwen3.8 Flash2026-08-26$0.23

Count tokens & estimate cost for Qwen3.6 27B See Qwen3.6 27B on the leaderboard

Prices: Alibaba's official list price as recorded by models.dev; benchmarks: see sources below; last synced 2026-11-06.

FAQ

Who develops Qwen3.6 27B?

Qwen3.6 27B is developed by Alibaba, released 2026-04-22.

How much does Qwen3.6 27B cost per million tokens?

Qwen3.6 27B costs $0.60 per 1M input tokens and $3.60 per 1M output tokens ($1.35 blended), per Alibaba's official list price as recorded by models.dev.

What is the Qwen3.6 27B API price?

The Qwen3.6 27B API price is $0.60 per 1M input tokens and $3.60 per 1M output tokens ($1.35 per 1M blended).

How much does Qwen3.6 27B cost for a typical request?

A short chat reply (500 in / 300 out tokens) costs about 0.138¢ on Qwen3.6 27B, at $0.60/1M input and $3.60/1M output.

Is Qwen3.6 27B free?

Qwen3.6 27B's official API list price is $0.60 per 1M input tokens and $3.60 per 1M output tokens. This site tracks list prices only, not free tiers or trial credits — check Alibaba's site for those.

How does Qwen3.6 27B rank on benchmarks?

Qwen3.6 27B scores 146.7 on the Epoch Capabilities Index (ECI), ranking #69 of 107 models we track with a published ECI score.

Is there a cheaper model with a similar ECI to Qwen3.6 27B?

Yes — GPT-5.4 nano scores a similar ECI (146.4) at $0.4625/1M blended, versus $1.35/1M for Qwen3.6 27B.

Where does this data come from?

Pricing for Qwen3.6 27B comes from models.dev and LiteLLM (open MIT-licensed catalogs); benchmark scores come from Epoch AI and LMArena (open CC BY 4.0 licenses); LiveBench scores (below) are CC BY-SA 4.0 — see /data-sources/. Last synced 2026-11-06.