Qwen3.5-122B-A10B vs o4 Mini

API pricing, benchmark indices and specs — updated 19 October 2026.

Qwen · A · Open weights

Params

125.1 B

Context

—

30d

1.0 M

apache-2.0 · commercial OK

openai · B · API-only

Input / 1M

$1.10

Output / 1M

$4.40

AA index

16.7

proprietary · 200K context

Specification comparison

Differences are highlighted; identical values are muted.

Specification	Qwen3.5-122B-A10B	o4 Mini
Deployment	Open weights · also via API	API-only (closed weights)
Parameters	125.1 B	n/a — API-only
Architecture	Qwen3_5MoeForConditionalGeneration	n/a — API-only
Context length	262,144	200,000
Licence	apache-2.0	Proprietary
Commercial use	Allowed	Per API terms
Languages	—	n/a — API-only
Downloads 30d	1,003,508	n/a — API-only
Downloads all time	6.8 M	n/a — API-only
Quantizations on the Hub	SAFETENSORS	n/a — API-only
Gated	No	n/a — API-only
First seen on the Hub	2026-02-24	n/a — API-only
API input price / 1M tokens	$0.40	$1.10
API output price / 1M tokens	$3.20	$4.40
Est. cost per 1M input + 1M output tokens	$3.60	$5.50
Cached input / 1M tokens	—	$0.28
AA Intelligence Index	17.7	16.7
AA Coding Index	43.3	—
AA Agentic Index	—	—
Max output tokens	65,536	100,000
API providers	4	1
Tool calling	Yes	Yes
Reasoning mode	Yes	Yes

Estimated cost of 1M input + 1M output tokens via OpenRouter

Qwen3.5-122B-A10B $3.60

o4 Mini $5.50

Qwen3.5-122B-A10B is 1.5× cheaper at list price.

On RTX 4090 · 24 GB · 8K context unless noted

Qwen3.5-122B-A10B · fp16 294.5 GB / 24 GB

❌ Won’t fit