Qwen3 235B A22B Instruct 2507

Provider: Alibaba (Qwen) CN

Input price
$0.15
/ 1M tokens
Output price
$0.75
/ 1M tokens
Cache price
$0.05
/ 1M tokens (read)
Context
262K tokens
Max output 118K tokens

Overview

Alibaba's Qwen3 235B A22B Instruct 2507 is a flagship mixture-of-experts model with 22B active parameters, built for general multilingual text tasks.

Strengths

  • 262k token context window
  • 117k token max output capacity
  • Native function calling and JSON mode
  • Cached input priced at $0.05 per million

Best use cases

  • Large-scale multilingual text generation
  • Complex instruction-following pipelines
  • Structured data extraction via JSON mode

Pricing position

Input matches GPT-4o-mini at $0.15/1M, while output at $0.75/1M undercuts Gemini 2.5 Flash but exceeds Gemma 4 31B.

Caveats

No free tier is available, and it features a smaller context window than Flash variants.

Notes drafted by an LLM from the figures on this page (2026-11-10) and rewritten when the price changes.

Key facts

Price basis
Median third-party host price (no first-party API)
Max output
118K tokens
Knowledge cutoff
2025-06-30
Listed on OpenRouter
2025-07-21
Tracked since
2026-05-08
Last updated
2026-11-10

Features

Function callingJSON output

Price history

  • 2026-11-10 Price change $0.09 / $0.55 → $0.15 / $0.75

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.05
1M (small app) 1 0.5 $0.53
10M (mid scale) 10 5 $5.25
100M (large) 100 50 $52.50

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Alibaba (Qwen)

Similar-priced models

Source: OpenRouter API (qwen/qwen3-235b-a22b-2507)