Qwen3-VL-235B-A22B-Instruct vs GPT-4.1 Mini

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

Qwen · A · Open weights

Params

235.7 B

Context

—

30d

916 K

apache-2.0 · commercial OK

openai · B · API-only

Input / 1M

$0.40

Output / 1M

$1.60

AA index

10.2

proprietary · 1.0M context

Specification comparison

Differences are highlighted; identical values are muted.

Specification	Qwen3-VL-235B-A22B-Instruct	GPT-4.1 Mini
Deployment	Open weights · also via API	API-only (closed weights)
Parameters	235.7 B	n/a — API-only
Architecture	Qwen3VLMoeForConditionalGeneration	n/a — API-only
Context length	131,072	1,047,576
Licence	apache-2.0	Proprietary
Commercial use	Allowed	Per API terms
Languages	—	n/a — API-only
Downloads 30d	916,424	n/a — API-only
Downloads all time	9.2 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	2025-09-22	n/a — API-only
API input price / 1M tokens	$0.21	$0.40
API output price / 1M tokens	$1.90	$1.60
Est. cost per 1M input + 1M output tokens	$2.11	$2.00
Cached input / 1M tokens	$0.10	$0.10
AA Intelligence Index	9.9	10.2
AA Coding Index	—	20.2
AA Agentic Index	—	—
Max output tokens	32,768	32,768
API providers	3	2
Tool calling	Yes	Yes
Reasoning mode	No	No

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

Qwen3-VL-235B-A22B-Instruct $2.11

GPT-4.1 Mini $2.00

GPT-4.1 Mini is 1.1× cheaper at list price.

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

Qwen3-VL-235B-A22B-Instruct · fp16 554.3 GB / 24 GB

❌ Won’t fit