Qwen3 235B A22B Thinking 2507
by Alibaba (Qwen) · qwen/qwen3-235b-a22b-thinking-2507 · #260 cheapest of 452 paid models
Prices updated Nov 17, 2026, 5:41 PM UTC · refreshed nightly
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
$0.45
per 1M tokens
Output
$3.50
per 1M tokens
Blended (3:1)
$1.21
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% | $1.21 | $0.0494 | — |
| 50% | $1.21 | $0.0494 | −0% |
| 90% | $1.21 | $0.0494 | −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 | $0.001275 | $1.27 |
| Document summary | 8,000 | 1,000 | $0.0071 | $7.10 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0205 | $20.50 |
| Long-context analysis | 150,000 | 5,000 | $0.085 | $85.00 |
Performance
Intelligence Index
—
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 | 1,044 |
| UI components | 933 |
| Data viz | 950 |
| 3D | 977 |
| Game dev | 946 |
| Code categories | 1,022 |
Specs
Context window
128K
tokens
Max output
16K
tokens
Input modalities
text
Tokenizer
Qwen3