Qwen: Qwen3.5-122B-A10B, Qwen — route, pricing & source

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...

OpenRoutermediumLast checked: May 14, 2026
Input
$0.2600 / 1M
/ 1M tokens
Output
$2.08 / 1M
/ 1M tokens
Cached input
Not available
Not available
Cache write
Not available
Not available

Context and limits

Context window
262.1K
Max output
65,536
Input modalities
text, image, video
Output modalities
text
Weight access
Closed
Availability
Unknown
Capability flags
VisionToolsJSONReasoningLong context

From source metadata + verification fields — confirm provider docs before production.

Benchmarks

Access and license

Official API
No
Open weights
No
Self-hostable
No
License
Open sourceApache 2.0Code/weights ship under an open license (often MIT / Apache‑2.0). MIT is a short permissive license: use/modify/redistribute freely with a copyright notice—always read the upstream project text.

Example costs

Scenario: 1K input + 300 output tokens / request

10,000 requests
$8.84
100,000 requests
$88.40
1,000,000 requests
$884.00

Cheaper alternatives

Lower-cost models for the same scenario

Mistral: Mistral Nemo
OpenRouter
$2.90
Meta: Llama 3.1 8B Instruct
OpenRouter
$3.50
IBM: Granite 4.0 Micro
OpenRouter
$5.00
Meta: Llama 3 8B Instruct
OpenRouter
$5.20
Sao10K: Llama 3 8B Lunaris
OpenRouter
$5.50

Source

Source
OpenRouter Models API
Confidence
medium
Route
OpenRouter
Last checked
May 14, 2026
Source notes
  • Includes Hugging Face benchmark data only when the dataset is public, ungated, allowlisted, and matched by reviewed aliases.
Open source
Skip to main content