Qwen3 235B A22B API
128K context · Released Feb 11, 2026 · By Alibaba · Apache 2.0
Qwen3 235B A22B costs $0.13 per million input tokens and $0.51 per million output tokens, against an official rate of $0.22 and $0.88 — 42% below official pricing. It is a Alibaba model under the Apache 2.0 licence, with a 128K context window, callable through an OpenAI-compatible endpoint with the model id `qwen/qwen3-235b-a22b-instruct`. This model is listed for reference and is not currently served by an upstream provider, so requests for it return no available channel.
Not currently available. No configured upstream serves this model, so a request for it returns no available channel. The rate below is what it will cost when it is enabled.
Input
$0.13/M
$0.22/M
Output
$0.51/M
$0.88/M
Savings
42%
off official
- No markup
- OpenAI SDK compatible
- No minimum spend
- Apache 2.0
A sparse MoE that punches well above its price. The workhorse choice when you want Apache 2.0 and don't need frontier reasoning.
Copy this and go
The model id is already filled in. Nothing in this snippet needs editing except your key.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://router.xark.io/api/v1" # ← the only line that changes
)
response = client.chat.completions.create(
model="qwen/qwen3-235b-a22b-instruct",
messages=[{"role": "user", "content": "Hello"}]
)
Qwen3 235B A22B pricing across providers
Rates as published by each provider. We update these when they change; if you spot one that's stale, tell us and we'll fix it.
| Provider | Input | Output |
|---|---|---|
| AI Token Router | $0.13/M | $0.51/M |
| Official (Alibaba) | $0.22/M | $0.88/M |
| OpenRouter | $0.21/M | $0.85/M |
| DeepInfra | $0.15/M | $0.60/M |
| Together AI | $0.20/M | $0.80/M |
Cached input on Qwen3 235B A22B is billed at $0.026/M — roughly 80% below the standard input rate. For agent loops with a large fixed system prompt this is usually the number that matters most.
What it's good at
- General chat and assistant backends
- RAG answer synthesis
- Self-hostable-later architectures