---
name: Qwen3.5 122B-A10B
slug: qwen-3-5-122b-a10b
type: Multimodal
providers:
  - siliconflow-cn
  - nano-gpt
  - nvidia
  - novita-ai
  - merge-gateway
  - infomaniak
  - mixlayer
  - alibaba
  - openrouter
description: 'Qwen vision-language model for visual reasoning, documents, and agent tasks'
tags:
  - open-source
  - reasoning
  - tool-use
  - multimodal
  - qwen
is_open_source: true
context_window: 262144
max_output: 262144
pricing:
  - image: 0
    input: 0.4
    output: 3.2
    provider: alibaba
  - image: 0
    input: 0.5
    output: 3.97
    provider: infomaniak (FP8)
  - image: 0
    input: 0.115
    output: 0.917
    provider: merge-gateway
  - image: 0
    input: 0.4
    output: 3.2
    provider: mixlayer
  - image: 0
    input: 0.46
    output: 3.68
    provider: nano-gpt (TEE)
  - image: 0
    input: 0.437
    output: 3.496
    provider: nano-gpt
  - image: 0
    input: 0.4
    output: 3.2
    provider: novita-ai
  - image: 0
    input: 0
    output: 0
    provider: nvidia
  - image: 0
    input: 0.29
    output: 2.32
    provider: siliconflow-cn
  - image: 0
    input: 0.29
    output: 2.4
    provider: openrouter
release_date: '2026-02-23'
openrouter_id: qwen/qwen3.5-122b-a10b
capabilities:
  audio: true
  vision: true
  tool_use: true
  citations: false
  reasoning: true
---
Qwen3.5 122B-A10B is a Multimodal model.
Qwen vision-language model for visual reasoning, documents, and agent tasks