The AI arena is free today

Open Superagent
QwenReleased on Feb 24, 2026

Qwen3.5-122B-A10B: Benchmarks, Pricing & Context Window

Qwen3.5-122B-A10B is a language model from Qwen, released in February 2026, with multimodal input, a 262K-token context window, and pricing from $0.290/M input and $2.40/M output.

Qwen3.5-122B-A10B is a multimodal Mixture-of-Experts model with 122 billion total parameters and 10 billion activated parameters. It combines strong reasoning, coding, long-context, and visual understanding performance with

Input
TextImageVideo
Output
Text

Qwen3.5-122B-A10B benchmarks

Capability tiers

Standing within each category, adjusted for leaderboard depth.

Real tasks performance

High-confidence performance for Qwen3.5-122B-A10B across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.

Performance by conversation depth

How Qwen3.5-122B-A10B holds up as conversations get longer.

Quality Tracker

Qwen3.5-122B-A10B Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

LLM Stats Logollm-stats.com - Fri Sep 11 2026
Notice missing or incorrect data?

Qwen3.5-122B-A10B pricing

Providers

Qwen3.5-122B-A10B starts at $0.290 per million input tokens and $2.40 per million output tokens via DeepInfra. See all 2 providers below with their per-token pricing, latency, throughput, and modality support.

ProviderInput $/MCached input $/MOutput $/MContext in / outTTFT p95 sOutput p5 c/sModalities in / out
DeepInfra logoDeepInfra
$0.290$2.40262.1K/262.1K
/
Novita logoNovita
$0.400$3.20262.1K/64.0K
/

Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.

Loading chart...
Loading chart...
Loading chart...

Qwen3.5-122B-A10B model size

Qwen3.5-122B-A10B has 122 billion parameters. See how it compares to other models in the same parameter range.

Parameters
122BMoE
Very large (80–200B)
122B
1B7B70B405B

Qwen3.5-122B-A10B context window

Input and output token limits for Qwen3.5-122B-A10B, plus how it ranks on long-context understanding.

InputOutput
262Ktokens
262Ktokens
394 pages of text
262K
8K128K1M

Try now

huggle
Qwen3.5-122B-A10Bin Huggle

Make it with
Qwen3.5-122B-A10B.

Qwen3.5-122B-A10B

Qwen3.5-122B-A10B latency

Qwen3.5-122B-A10B time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.

Qwen3.5-122B-A10B examples

Recent arena outputs from Qwen3.5-122B-A10B, picked from the highest-ranked matchups.

Qwen3.5-122B-A10B license

Qwen3.5-122B-A10B is released under the Apache 2.0 license, which permits commercial use, has 122.0B parameters.

License
Apache 2.0
Commercial use allowed
Parameters
122.0B

Apache License 2.0 - allows commercial use

Qwen3.5-122B-A10B resources

Official sources for Qwen3.5-122B-A10B: provider documentation, official playground, source repository, model weights.

Qwen3.5-122B-A10B vs other models

The most-compared alternatives to Qwen3.5-122B-A10B are GLM-5.1, Gemini 3 Pro, Claude Opus 4.5. Open any pair side-by-side for benchmarks, pricing, context, and latency.

Models like Qwen3.5-122B-A10B

Models ranked just above and below Qwen3.5-122B-A10B by LLM Stats score.

 

GLM-5.1

Score pending
 

Gemini 3 Pro

Score pending
 

Claude Opus 4.5

Score pending
 

ERNIE 5.0

Score pending
 

Solar Pro 4

Score pending
 

Gemini 2.5 Pro Preview 06-05

Score pending

FAQ

Common questions about Qwen3.5-122B-A10B.

When was Qwen3.5-122B-A10B released?

Qwen3.5-122B-A10B was released on February 24, 2026 by Qwen. This is the official Qwen3.5-122B-A10B release date tracked on LLM Stats.

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

Qwen3.5-122B-A10B pricing starts at $0.29 per million input tokens and $2.40 per million output tokens via DeepInfra, the lowest price among tracked providers.

How big is Qwen3.5-122B-A10B?

Qwen3.5-122B-A10B has 122 billion parameters. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created Qwen3.5-122B-A10B?

Qwen3.5-122B-A10B was created by Qwen.

What is the license for Qwen3.5-122B-A10B?

Qwen3.5-122B-A10B is released under the Apache 2.0 license. This is an open-source / open-weight license that permits self-hosting.

Is Qwen3.5-122B-A10B multimodal?

Yes, Qwen3.5-122B-A10B is multimodal and can accept both text and images as input.

Where can I use Qwen3.5-122B-A10B?

Qwen3.5-122B-A10B is available through 2 providers including DeepInfra, Novita.

Where is the Qwen3.5-122B-A10B paper or technical report?

Qwen3.5-122B-A10B has a paper or technical report available at https://qwen.ai/blog?id=qwen3.5. Use that source for architecture, training, release and evaluation details.

What models should I compare Qwen3.5-122B-A10B against?

Common Qwen3.5-122B-A10B comparisons include Qwen3.5-122B-A10B vs GLM-5.1, Qwen3.5-122B-A10B vs Gemini 3 Pro, Qwen3.5-122B-A10B vs Claude Opus 4.5. Compare them side by side for benchmark scores, pricing, context window, latency and provider availability.