Qwen3 235B A22B
by Alibaba (Qwen) · qwen/qwen3-235b-a22b · #158 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:31 AM UTC · refreshed hourly
Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.455
per 1M tokens
Output
$1.82
per 1M tokens
Blended (3:1)
$0.796
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Qwen3 235B A22B (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.796 | $0.0482 | — |
| 50% | $0.796 | $0.0482 | −0% |
| 90% | $0.796 | $0.0482 | −0% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.000773 | $0.7735 |
| Document summary | 8,000 | 1,000 | $0.00546 | $5.46 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0173 | $17.29 |
| Long-context analysis | 150,000 | 5,000 | $0.0773 | $77.35 |
Performance
Intelligence Index
—
AA composite quality
Coding Index
—
Math Index
—
Agentic Index
—
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,058 |
| UI components | 1,004 |
| Data viz | 1,038 |
| 3D | 918 |
| Game dev | 987 |
| Code categories | 1,036 |
Specs
Context window
131K
tokens
Max output
8K
tokens
Input modalities
text
Tokenizer
Qwen3