Qwen3 235B A22B Thinking 2507
by Alibaba (Qwen) · qwen/qwen3-235b-a22b-thinking-2507 · #199 cheapest of 422 paid models
Prices updated Sep 19, 2026, 6:21 PM UTC · refreshed hourly
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.23
per 1M tokens
Output
$2.30
per 1M tokens
Blended (3:1)
$0.747
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Qwen3 235B A22B Thinking 2507 (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.747 | $0.0258 | — |
| 50% | $0.747 | $0.0258 | −0% |
| 90% | $0.747 | $0.0258 | −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 | $0.000805 | $0.805 |
| Document summary | 8,000 | 1,000 | $0.00414 | $4.14 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0115 | $11.50 |
| Long-context analysis | 150,000 | 5,000 | $0.046 | $46.00 |
Performance
Intelligence Index
12.7
AA composite quality
Coding Index
22.1
Math Index
—
Agentic Index
1.3
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,065 |
| UI components | 960 |
| Data viz | 963 |
| 3D | 1,026 |
| Game dev | 980 |
| Code categories | 1,048 |
Specs
Context window
131K
tokens
Max output
118K
tokens
Input modalities
text
Tokenizer
Qwen3