# Qwen3.5 9B (Alibaba) — API pricing and providers

> Small open-weight multimodal chat. Model id `qwen/qwen3.5-9b`. Text model by Alibaba.

- Page: https://infro.io/models/qwen/qwen3.5-9b
- Vendor: Alibaba (https://infro.io/models/alibaba)
- Modality: Text
- Endpoint through INFRO: `POST /v1/chat/completions` at https://api.infro.io/v1
- List rate: $0.17 per 1M input tokens and $0.25 per 1M output tokens
- Rates checked: 2026-10-05

Rates are Alibaba's published list price: what the customer's own provider account bills, not an INFRO charge. INFRO is a BYOK control plane; it charges a software subscription and adds 0% to model spend.

## Providers that serve it

| Provider | Model id sent |
| --- | --- |
| Together AI | `Qwen/Qwen3.5-9B` |
| OpenRouter | `qwen/qwen3.5-9b` |

## Questions

### How much does the Qwen3.5 9B API cost?

Alibaba's published list rate for Qwen3.5 9B is $0.17 per 1M input tokens and $0.25 per 1M output tokens (checked 2026-10-05). The provider account you connect bills you at the rate on that account, so a negotiated rate replaces the list rate. INFRO adds 0% to model spend.

### Which providers serve Qwen3.5 9B?

In INFRO's provider registry, Qwen3.5 9B can be served by Together AI and OpenRouter. You connect your own account with any of them, and INFRO routes and fails over between the ones you connect.

### What is the Qwen3.5 9B model ID?

Request it from INFRO as "qwen/qwen3.5-9b". INFRO sends each provider its own id: Together AI "Qwen/Qwen3.5-9B", OpenRouter "qwen/qwen3.5-9b".

### How do I call Qwen3.5 9B through an OpenAI-compatible API?

Point an OpenAI SDK, or any HTTP client, at https://api.infro.io/v1 with an INFRO gateway key and send model "qwen/qwen3.5-9b" to POST /v1/chat/completions. INFRO runs the request on a provider account you connected and returns the provider's response with an estimated cost.

### Does INFRO mark up Qwen3.5 9B usage?

No. Alibaba or the provider you connect bills model usage to your own account. INFRO charges a software subscription for routing, failover, observability, budgets and policy, and takes 0% of model spend.