Qwen3.5-122B-A10B

Provider: Alibaba (Qwen) CN Official API price

Input price
$0.26
/ 1M tokens
Output price
$2.08
/ 1M tokens
Context
262K tokens
Max output 66K tokens

Overview

Qwen3.5-122B-A10B is a flagship model from Alibaba (Qwen), developed in China. It is designed for demanding workloads that require advanced reasoning, extensive context handling, and multimodal capabilities.

Strengths

  • Handles very long conversations and complex documents with its 262,144 token context window.
  • Generates extremely long and detailed responses, up to 65,536 output tokens.
  • Processes and understands visual inputs, enabling multimodal applications.
  • Supports structured outputs through JSON mode and reliable function calling.
  • Demonstrates strong analytical and problem-solving abilities for complex tasks.

Best use cases

  • In-depth analysis of extensive legal documents or research papers across a large context.
  • Developing AI agents that can interact with external tools using function calling.
  • Processing and extracting structured data from diverse inputs, including visual content.
  • Generating comprehensive reports or detailed summaries requiring long output lengths.
  • Multimodal applications involving image understanding combined with reasoning tasks.

Pricing position

Qwen3.5-122B-A10B is positioned as the highest-priced model in Alibaba's Qwen family, significantly more expensive than models like Qwen3.5-9B ($0.04/M input). Its input price of $0.26/M aligns closely with peers such as GPT-5 Mini ($0.25/M) and DeepSeek V3.2 ($0.252/M). However, its output price of $2.08/M is among the highest, only matched by GPT-5 Mini among its similarly-priced peers.

Caveats

Given its premium pricing, Qwen3.5-122B-A10B may not be cost-effective for simpler tasks that do not require its advanced capabilities or extensive context. For basic interactions or shorter documents, cheaper Alibaba models like Qwen3.5-9B or Qwen3.5-Flash (which offers a 1M token context for $0.065/M input) could be more suitable alternatives. The model does not offer a free tier for initial exploration or low-volume usage.

Notes drafted by an LLM from the figures on this page (2026-05-21) and rewritten when the price changes.

Key facts

Price basis
Official API price
Max output
66K tokens
Listed on OpenRouter
2026-02-25
Tracked since
2026-05-08
Last updated
2026-11-10

Features

Image inputFunction callingJSON outputReasoning

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.13
1M (small app) 1 0.5 $1.30
10M (mid scale) 10 5 $13.00
100M (large) 100 50 $130.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Alibaba (Qwen)

Similar-priced models

Source: OpenRouter API (qwen/qwen3.5-122b-a10b)