Model tracker / Alibaba
Qwen3.5 9B
Qwen3.5 9B is a fast open-weight model from Alibaba. At DeepInfra it costs $0.10 per million input tokens and $0.15 per million output tokens, with a 262K-token context window. 2 providers serve it, and DeepInfra is the cheapest.
- Made by
- Alibaba Group (Qwen, Alibaba Cloud)
- Status
- Generally available
- Tier
- Fast
- Weights
- Open
- Context window
- 262,144 tokens
- Max output
- 81,920 tokens
- Input
- text, image, video
- API id
Qwen/Qwen3.5-9B
Qwen3.5 9B price at 2 providers
US dollars per million tokens. Blended is 3 input tokens for every output token, one number to compare on. The cheapest blended price is highlighted.
| Provider | Input | Output | Cached input | Blended | Batch | Checked |
|---|---|---|---|---|---|---|
| DeepInfra | $0.10 | $0.15 | – | $0.113 | – | 2026-10-15 |
| Together AI | $0.17 | $0.25 | – | $0.19 | – | 2026-10-15 |
Qwen3.5 9B benchmarks
| Benchmark | Score | What it measures | Reported by |
|---|---|---|---|
| GPQA Diamond | 81.7% | graduate-level science questions answered correctly | Alibaba |
Scores reported by a model's maker aren't independently checked.
Models like Qwen3.5 9B
Other fast models closest in price, at each maker's own price or the cheapest provider.
| Model | Input | Output | Context | Weights |
|---|---|---|---|---|
| Qwen3.5 9B | $0.10 | $0.15 | 262K | Open |
| gpt-oss-20b OpenAI | $0.07 | $0.25 | 131K | Open |
| Ministral 3 3B Mistral AI | $0.10 | $0.10 | 256K | Open |
| gpt-oss-120b OpenAI | $0.05 | $0.25 | 131K | Open |
| NVIDIA Nemotron 3.5 Lightning 30B A3B NVIDIA | $0.06 | $0.16 | 262K | Open |
| Ministral 3 8B Mistral AI | $0.15 | $0.15 | 256K | Open |
Compare them all in the model tracker →
Qwen3.5 9B on dbggr
Qwen3.5 9B FAQ
How much does Qwen3.5 9B cost?
Qwen3.5 9B costs $0.10 per million input tokens and $0.15 per million output tokens at DeepInfra. Prices are list prices in US dollars, last checked 15 October 2026.
What is Qwen3.5 9B's context window?
Qwen3.5 9B takes up to 262,144 tokens in one request and writes up to 81,920 tokens in one response.
Is Qwen3.5 9B open weight?
Yes. Alibaba publishes the weights, so you can run Qwen3.5 9B yourself or at any host that serves it.
Where can I use Qwen3.5 9B?
Qwen3.5 9B is available from DeepInfra and Together AI. At DeepInfra, call it as Qwen/Qwen3.5-9B.