Qwen3.5-122B-A10B

AlibabaReleasedFeb 23, 2026

Vision Tool use Reasoning Structured output

Compare Qwen3.5-122B-A10B Count tokens for Qwen3.5-122B-A10B

Context

262K

Max output

262K

Serving providers

Cheapest input

$0.25 /1M

Prices are on-demand list rates. 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

131 t/s

tokens / second

Time to first token

2.30s

latency

Headline indices

Intelligence Index

32.8

of 100

Coding Index

45.7

of 100

Agentic Index

21.3

of 100

Individual benchmarks · click a row for effort variants

Benchmark

Best score

Effort

Cost / task

CritPt

reasoning: false

—

EvalComputeProxy

243.6

default

—

GDPval

987.7

default

—

GPQA Diamond

86%

default

—

Humanity's Last Exam

25%

default

—

IFBench

76%

default

—

Long-Context Reasoning

70%

default

—

MMMU-Pro

75%

default

—

Omniscience

-41.5

default

—

Omniscience Accuracy

0.2

default

—

Omniscience Non Hallucination

0.1

default

—

SciCode

42%

default

—

SWE-bench Verified

72%

default

—

TerminalBench Hard

31%

default

—

TerminalBench v2.1

48%

default

—

τ-bench Banking

15%

default

—

τ²-bench

94%

default

—

Pricing by serving provider

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

Input pricing runs from $0.25 to $0.40 per 1M tokens across 4 providers, so the dearest route costs 60% more than the cheapest for the same model.

Serving provider

Input /1M

Output /1M

Endpoints

LibertaiCheapest

$0.25

$1.75

Component	Unit	Standard	Batch	Cached
Text input	/1M tok	$0.2500	—	—
Text output	/1M tok	$1.75	—	—

OpenRouter

$0.29

$2.40

DeepInfra

$0.29

$2.40

Novita

$0.40

$3.20

Price history

input + output $/1M since we started tracking

Input Output

Input down 38% since first tracked

Cost calculator

estimate your monthly spend on this model

Input tokens / call

Output tokens / call

Calls / month

Serving provider

$190

estimated / month

Model IDs

copy the exact identifier for your platform

libertai/qwen3.5-122b-a10bqwen/qwen3.5-122b-a10bdeepinfra/Qwen/Qwen3.5-122B-A10Bnovita/qwen/qwen3.5-122b-a10b

Frequently asked questions

Qwen3.5-122B-A10B pricing, context and availability

How much does Qwen3.5-122B-A10B cost?

Qwen3.5-122B-A10B costs $0.25 per 1M input tokens and $1.75 per 1M output tokens at its cheapest provider via Libertai. Across 4 serving providers, input prices range from $0.25 to $0.40 per 1M tokens.

What is the context window of Qwen3.5-122B-A10B?

Qwen3.5-122B-A10B accepts up to 262K tokens of context and can return up to 262K output tokens.

Which providers serve Qwen3.5-122B-A10B?

Qwen3.5-122B-A10B is available from 4 serving providers, each with its own pricing and model ID. Libertai is currently the cheapest.

What can Qwen3.5-122B-A10B do?

Qwen3.5-122B-A10B supports image input (vision), tool use, reasoning and structured output.

Other Alibaba models

compare pricing across the Alibaba lineup

Qwen3 32B$0.08/1M · 8 providers Qwen3.6 35B A3B$0.10/1M · 7 providers QwQ 32B$0.15/1M · 7 providers Qwen3 Next 80B A3B Instruct$0.09/1M · 6 providers Qwen3 235B A22b Instruct 2507$0.09/1M · 6 providers Qwen3 Next 80B A3B Thinking$0.14/1M · 6 providers Qwen3.6 27B$0.15/1M · 6 providers Qwen3 30B A3B$0.09/1M · 5 providers

Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI