Qwen3.5-122B-A10B
by Alibaba (Qwen) · qwen/qwen3.5-122b-a10b · #194 cheapest of 422 paid models
Prices updated Sep 19, 2026, 9:29 PM UTC · refreshed hourly
The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.26
per 1M tokens
Output
$2.08
per 1M tokens
Blended (3:1)
$0.715
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Qwen3.5-122B-A10B (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.715 | $0.0286 | — |
| 50% | $0.715 | $0.0286 | −0% |
| 90% | $0.715 | $0.0286 | −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 | $0.000754 | $0.754 |
| Document summary | 8,000 | 1,000 | $0.00416 | $4.16 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.012 | $11.96 |
| Long-context analysis | 150,000 | 5,000 | $0.0494 | $49.40 |
Performance
Intelligence Index
15.6
AA composite quality
Coding Index
45.7
Math Index
—
Agentic Index
9.6
Output speed
133 tok/s
median
Time to first token
1.04s
median
Time to first answer
16.11s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| GPQA Diamond | 85.7% |
| Humanity's Last Exam | 25.2% |
| SciCode | 39.7% |
| IFBench | 75.7% |
| AA-LCR (Long Context Reasoning) | 76.3% |
| Terminal-Bench Hard | 31.1% |
| Terminal-Bench 2.1 | 47.6% |
| τ²-Bench (Telecom) | 93.6% |
| τ³-Bench Banking | 15.3% |
Specs
Context window
262K
tokens
Max output
66K
tokens
Input modalities
text, image, video
Tokenizer
Qwen3