# alibaba/qwen3.8-omni-flash API

> alibaba/qwen3.8-omni-flash is a model that you can call through the ScalingTensor API. Chat models available through the ScalingTensor API.

- Model ID: `alibaba/qwen3.8-omni-flash`
- Provider: alibaba
- Tasks: Chat
- Price: From $0.15 per 1M input tokens; output, cache and context tiers priced separately

### Token pricing rule

Coefficients are USD per 1M tokens. len is total input context including cache; p is input excluding separately priced cache and modalities; c is output. cr is cache read, cc is cache write, cc1h is one-hour cache write.

```text
tier("base", p * 0.15 + c * 0.47 + cr * 0.016005 + cc * 0.15 + cc1h * 0.15)
```

- Web page: https://scalingtensor.com/models/alibaba/qwen3.8-omni-flash

## How to call it

Authenticate with the `apiKey` request header. Send POST https://restapi.scalingtensor.com/api/chat/completion with model and the example parameters below. A response code of 0 means success; data contains content, tokensIn, tokensOut and costMicros.

```bash
curl --request POST 'https://restapi.scalingtensor.com/api/chat/completion' \
  --header 'apiKey: YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "max_tokens": 2048,
  "model": "alibaba/qwen3.8-omni-flash"
}'
```

## Input parameters

Send these parameters directly in the request body alongside model.

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `messages` | object[] | Required | — |
| `seed` | integer | Optional | — |
| `stop` | string[] | Optional | — |
| `tools` | array | Optional | — |
| `top_k` | integer | Optional | Min: 0 |
| `top_p` | number | Optional | Min: 0 · Max: 1 |
| `stream` | boolean | Optional | Default: false |
| `max_tokens` | integer | Optional | Max: 131072 |
| `temperature` | number | Optional | Min: 0 · Max: 2 · Default: 1 |
| `tool_choice` | string | Optional | — |
| `response_format` | object | Optional | — |
| `presence_penalty` | number | Optional | Min: -2 · Max: 2 |
| `frequency_penalty` | number | Optional | Min: -2 · Max: 2 |
| `messages[].role` | string | Optional | enum: ["system","user","assistant"] |
| `messages[].content` | string | Optional | — |

## FAQ

### How much does the alibaba/qwen3.8-omni-flash API cost?

alibaba/qwen3.8-omni-flash costs From $0.15 per 1M input tokens; output, cache and context tiers priced separately on ScalingTensor. There is no subscription; usage is charged to your prepaid wallet.

### How do I call the alibaba/qwen3.8-omni-flash API?

Send POST /api/chat/completion with "model": "alibaba/qwen3.8-omni-flash" and a messages array using your apiKey header. Read data.content from the successful response. Usage is reported in tokensIn, tokensOut and costMicros.

### Which parameters does alibaba/qwen3.8-omni-flash accept?

Required: messages. Optional: seed, stop, tools, top_k, top_p, stream, max_tokens, temperature, tool_choice and response_format and 2 more. The parameter table on this page describes each one.

### Do I need a alibaba account to use alibaba/qwen3.8-omni-flash?

No. You call alibaba/qwen3.8-omni-flash with your ScalingTensor API key and pay from your ScalingTensor wallet. The same key works for every other model in the catalog.
