What is Qwen3.5-122B-A10B good for?

Reasoning, coding, agents and visual understanding, which Alibaba built the Qwen3.5 series for. Apache 2.0 weights, servable on a single high-memory GPU.

When is Qwen3.5-122B-A10B not a good fit?

Audio input or image output. Memory follows the full 122B parameters, not the 10B active, so it is beyond a single consumer GPU.

What is the cheapest way to run Qwen3.5-122B-A10B?

Hosted, unless you push serious volume. Alibaba Cloud charges $0.40 in / $3.20 out per 1M tokens. The cheapest rental that fits is 8x RTX 3060 at $346 a month, which costs the same as about 399M tokens a month on that API.

Can I self-host Qwen3.5-122B-A10B?

Yes. The weights are Apache 2.0 licensed. At 4-bit it needs about 70 GB of GPU memory, which starts at roughly $346 a month on the cheapest rental that fits.

Open weights · Apache 2.0

Qwen3.5-122B-A10B

A 122B MoE with 10B active across 256 experts using Gated Delta Networks, with native multimodal support for text, images and video.

Jump to: Specs Pricing Self-hosting Similar models FAQ More from Alibaba Cloud

Visit website Compare vs other LLMs →

List price via Alibaba Cloud

Input: $0.40 /1M tokens
Output: $3.20 /1M tokens

Cheapest: $0.12 / $0.92 per 1M tokens via EmpirioLabs AI

3 providers

Key Specifications

Context window: 262K tokens
Max output: 66K tokens
Released: Feb 2026
Parameters: 122B, 10B active
Inputs: Text, image, video

Capabilities Show details: Reasoning Thinks before it answers, always on or as a switchable mode. Function calling Connect to external tools, APIs, and systems. Structured output Return responses in structured formats like JSON. Code execution Write and execute code in a sandboxed environment. MCP Connect to services via Model Context Protocol.

Hosted API pricing

Input tokens M Output tokens M

Provider	Input /1M tokens	Output /1M tokens	Cost at 10M in + 2M out
EmpirioLabs AI Cheapest	$0.12	$0.92	$3.04	View
Alibaba Cloud Creator	$0.40	$3.20	$10.40	View
Novita	$0.40	$3.20	$10.40	View

Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.

Estimated cost to self-host

Qwen3.5-122B-A10B needs about 70 GB of GPU memory at 4-bit with 32K context. The cheapest rental that fits is 8× RTX 3060 at about $346 a month.

That costs the same as roughly 399M tokens a month on Alibaba Cloud's API. Self-hosting is more expensive below that volume.

Single node ≤ 8

Precision	Memory	Cheapest fit (32K context)(Full 262K context)	Cost /mo	Break-even vs API
4-bitINT4 / FP4	70 GB76 GB	8× RTX 3060	$346$346	399M tokens /mo399M tokens /mo
8-bitFP8 / INT8	125 GB130 GB	8× RTX 3090	$979$979	1B tokens /mo1B tokens /mo
16-bitFP16 / BF16	247 GB252 GB	8× RTX A6000	$3,168$3,168	4B tokens /mo4B tokens /mo

Estimates based on median on-demand rates for Nvidia GPUs. Memory is weights plus KV cache for one request, using FP8 KV cache where supported and FP16/BF16 otherwise. Break-even assumes a 5:1 input-to-output ratio. No guarantee of runtime support, usable performance, or that a matching quantized build exists. How we estimate costs.

Similarly priced models

The models nearest Qwen3.5-122B-A10B by blended rate, each at its own cheapest provider.

Model	Blended /1M	Input /1M	Output /1M	Context	Cutoff	vs Qwen3.5-122B-A10B
MiniMax-M2.7 MiniMax	$0.225	$0.15	$0.60	205K		−11%
Mistral Small 4 Mistral	$0.225	$0.15	$0.60	256K		−11%
Qwen3.8-27B Alibaba Cloud	$0.225	$0.17	$0.50	262K		−11%
Qwen3-Coder-Next Alibaba Cloud	$0.23	$0.08	$0.98	262K		−9%
Llama 4 Scout Meta	$0.24	$0.16	$0.64	10M	Aug 2024	−5%
Qwen3.5-122B-A10B This model Alibaba Cloud	$0.2533	$0.12	$0.92	262K
Llama 4 Maverick Meta	$0.2833	$0.20	$0.70	1M	Aug 2024	+12%
Qwen3-VL-30B-A3B Instruct Alibaba Cloud	$0.2833	$0.20	$0.70	262K		+12%
Muse Glimmer 30B Meta	$0.30	$0.20	$0.80	131K	Jan 2026	+18%
Qwen2.5-7B Instruct Alibaba Cloud	$0.30	$0.30	$0.30	33K		+18%
Qwen3-235B-A22B FP8 Alibaba Cloud	$0.30	$0.20	$0.80	33K		+18%

Prices are USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.

Packet·ai

B200 @ $3.75/h on demand

No contract, no spot interrupts, no cluster minimums

Full root SSH, web dashboard, CI/CD ready

Reserve Now

Frequently Asked Questions

What is Qwen3.5-122B-A10B good for?: Reasoning, coding, agents and visual understanding, which Alibaba built the Qwen3.5 series for. Apache 2.0 weights, servable on a single high-memory GPU.
When is Qwen3.5-122B-A10B not a good fit?: Audio input or image output. Memory follows the full 122B parameters, not the 10B active, so it is beyond a single consumer GPU.
What is the cheapest way to run Qwen3.5-122B-A10B?: Hosted, unless you push serious volume. Alibaba Cloud charges $0.40 in / $3.20 out per 1M tokens. The cheapest rental that fits is 8x RTX 3060 at $346 a month, which costs the same as about 399M tokens a month on that API.
Can I self-host Qwen3.5-122B-A10B?: Yes. The weights are Apache 2.0 licensed. At 4-bit it needs about 70 GB of GPU memory, which starts at roughly $346 a month on the cheapest rental that fits.

More from Alibaba Cloud

Model	Context	Input /1M	Output /1M
Qwen3-Coder-Next Open weights	262K	$0.08	$0.98
Qwen3-VL-30B-A3B Instruct Open weights	262K	$0.20	$0.70
Qwen3.8-27B Open weights	262K	$0.17	$0.50
Qwen-MT-Turbo	16K	$0.16	$0.49
Qwen2.5-7B Instruct Open weights	33K	$0.30	$0.30
Qwen3-235B-A22B FP8 Open weights	33K	$0.20	$0.80
Qwen3-VL-8B Open weights	262K	$0.15	$0.50
Qwen3.5-397B-A17B Open weights	262K	$0.17	$1.03