Question 1

What is Qwen3.5 122B A10B?

Accepted Answer

Qwen3.5 122B A10B is a model from Qwen, released on Feb 24, 2026. The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of overall performance, this model is second only to Qwen3.5-397B-A17B. Its text capabilities significantly outperform those of Qwen3-235B-2507, and its visual capabilities surpass those of Qwen3-VL-235B.

Question 2

How much does Qwen3.5 122B A10B cost?

Accepted Answer

On the Respan gateway, input starts at $0.12 per 1M tokens on EmpirioLabs, and output starts at $0.92 per 1M tokens on EmpirioLabs, after gateway discounts. Averaged across 3 providers, it costs $0.25 per 1M input tokens and $1.96 per 1M output tokens.

Question 3

Which providers serve Qwen3.5 122B A10B on Respan?

Accepted Answer

3 providers serve Qwen3.5 122B A10B: EmpirioLabs, OpenRouter, and Novita.

Question 4

What is Qwen3.5 122B A10B's context window?

Accepted Answer

Qwen3.5 122B A10B accepts up to 262K tokens of context on its largest provider route.

Question 5

How do I use Qwen3.5 122B A10B with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "qwen3.5-122b-a10b". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Qwen3.5 122B A10B?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 141 tokens per second, and the lowest response latency was 2.0 seconds on OpenRouter. Speed varies with request size and provider.

Question 7

How does Qwen3.5 122B A10B score on benchmarks?

Accepted Answer

Qwen3.5 122B A10B has 4 published benchmark scores, including Mystery Game Puzzles 17% and LMArena Elo 1416. Each score links to where it was published; the data is collected by llmmetric.com.

Provider	Context	Input	Output
EmpirioLabs`empiriolabs/qwen3-5-122b-a10b`	256K	$0.12/M	$0.92/M
OpenRouter`openrouter/qwen/qwen3.5-122b-a10b`	262K	$0.26/M	$2.08/M
NovitaSave 10%`novita/qwen/qwen3.5-122b-a10b`	262K	$0.36/M	$2.88/M

Qwen3.5 122B A10B

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Benchmarks

Reasoning1

Arena3

Apps

Qwen3.5 122B A10B FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.