Deprecated on Oct 5, 2026. 8 providers still list it at the prices below.

Qwen3.6 27BDeprecated

AlibabaReleased Apr 24, 2026

Vision Tool use Reasoning Prompt caching Structured output Web search

Compare Qwen3.6 27B Count tokens for Qwen3.6 27B

Context

262K

Max output

262K

Serving providers

Cheapest input

$0.15 /1M

On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis and Hugging Face leaderboards

Speed & latency

Output speed

58 t/s

tokens / second

Time to first token

3.62s

latency

Headline indices

Intelligence Index

21.4

of 100

Coding Index

53.7

of 100

Frozen Sep 9, 2026

Agentic Index

23.6

of 100

Frozen Sep 9, 2026

Individual benchmarks · click a row for effort variants

Benchmark

Best score

Effort

Cost / task

AA-BriefcaseUndated

15%

default

—

AIME 2026

94%

default

—

Automation Bench

0.1

default

—

CritPt

default

—

EvalComputeProxyFrozen Aug 18, 2026

1240.3

reasoning: false

—

GDPval v2Frozen Aug 18, 2026

1140.0

default

—

GPQA Diamond

84%

default

—

Harvey Lab

0.8

default

—

Humanity's Last Exam

23%

default

—

IFBench

68%

default

—

Long-Context Reasoning

77%

default

—

MMMU-Pro

75%

default

—

Omniscience

-20.0

default

—

Omniscience Accuracy

0.2

default

—

Omniscience Non Hallucination

0.5

default

—

SciCode

43%

default

—

SWE-bench Pro

54%

default

—

SWE-bench Verified

77%

default

—

Terminal Bench40

default

—

TerminalBench Hard

35%

default

—

TerminalBench v2.1

61%

default

—

Variant	Score	Token budget	Cost / task
default	61%	—	—
defaultArtificial Analysis did not report this score in its latest run on Oct 14, 2026	61%	—	—
reasoning: falseArtificial Analysis did not report this score in its latest run on Oct 14, 2026	51%	—	—
reasoning: false	51%	—	—

τ-bench Banking

17%

default

—

τ²-bench

94%

default

—

Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.

We cannot tell whether this benchmark is still being published. Treat these scores as undated.

Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand

Input pricing runs from $0.15 to $0.60 per 1M tokens across 8 providers, so the dearest route costs 300% more than the cheapest for the same model.

Serving provider

Input /1M

Output /1M

Endpoints

LibertaiCheapest

$0.15

$0.50

Standardlibertai/qwen3.6-27b

Component	Unit	Standard
Text input	/1M tok	$0.15
Text output	/1M tok	$0.50

DeepInfra

$0.32

$3.20

OpenRouter

$0.32

$3.20

Aihubmix

$0.422

$2.53

Groq

$0.60

$3.00

Novita

$0.60

$3.60

VercelVercel reseller quote

$0.60

$3.60

Wandb

$0.60

$3.60

Price history

listed seller prices, input and output per 1M tokens

Input Output

Cost calculator

estimate your monthly spend on this model

Input tokens / call

Output tokens / call

Calls / month

Serving provider

$70

estimated / month

Model IDs

copy the exact identifier for your platform

libertai/qwen3.6-27bdeepinfra/Qwen/Qwen3.6-27Bqwen/qwen3.6-27baihubmix/qwen3.6-27bwandb/Qwen/Qwen3.6-27Bnovita/qwen/qwen3.6-27bgroq/qwen/qwen3.6-27balibaba/qwen3.6-27b

Frequently asked questions

Qwen3.6 27B pricing, context and availability

Is Qwen3.6 27B still available?

Qwen3.6 27B was deprecated on 2026-10-05, but 8 serving providers still list it.

How much does Qwen3.6 27B cost?

Qwen3.6 27B costs $0.15 per 1M input tokens from Libertai, and $0.50 per 1M output tokens from Libertai. Across 8 serving providers, input prices range from $0.15 to $0.60 per 1M tokens.