Qwen3.5-9B (batch)
by Alibaba (Qwen) · qwen/qwen3.5-9b:batch · #87 cheapest of 422 paid models
Prices updated Sep 19, 2026, 6:21 PM UTC · refreshed hourly
Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.17
per 1M tokens
Output
$0.25
per 1M tokens
Blended (3:1)
$0.19
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Qwen3.5-9B (batch) (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.19 | $0.0176 | — |
| 50% | $0.19 | $0.0176 | −0% |
| 90% | $0.19 | $0.0176 | −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 | $0.00016 | $0.16 |
| Document summary | 8,000 | 1,000 | $0.00161 | $1.61 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0056 | $5.60 |
| Long-context analysis | 150,000 | 5,000 | $0.0267 | $26.75 |
Performance
Intelligence Index
13.7
AA composite quality
Coding Index
28.7
Math Index
—
Agentic Index
—
Output speed
68 tok/s
median
Time to first token
0.80s
median
Time to first answer
30.25s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| GPQA Diamond | 80.6% |
| Humanity's Last Exam | 14.9% |
| IFBench | 66.7% |
| AA-LCR (Long Context Reasoning) | 70.0% |
| Terminal-Bench Hard | 24.2% |
| Terminal-Bench 2.1 | 29.2% |
| τ²-Bench (Telecom) | 86.8% |
| τ³-Bench Banking | 7.0% |
Specs
Context window
262K
tokens
Max output
236K
tokens
Input modalities
text, image, video
Tokenizer
Qwen3