import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "alibaba/qwen3.8-omni-flash", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "alibaba/qwen3.8-omni-flash", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"alibaba/qwen3.8-omni-flash","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
Qwen3.8 Omni Flash has a 1,000,000 token context window and can return up to 131,072 tokens.
It accepts audio, images, text and video as input and returns text. All four input types can go into the same prompt, so a recording or a clip does not need a separate transcription step first.
Qwen3.8 Omni Flash is priced at input $0.195 / 1M tokens, output $0.611 / 1M tokens, cached input $0.0208 / 1M tokens. Reasoning tokens are charged at the output rate.
No. Audio and video are input modalities only — the model listens and watches, but answers in text. There is no parameter on the chat completions endpoint to request an audio response.
Reasoning is off by default. Set enable_thinking to true to switch it on, and use thinking_budget to cap how many reasoning tokens a request may spend. Those tokens are billed at the output rate.
Yes. It supports function calling including parallel tool calls, structured (JSON schema) output, streaming and context caching.
Qwen3.8 Omni Flash was built by Alibaba Cloud as the speed- and cost-optimised omni tier of the Qwen3.8 family. It became available on September 17, 2026.
It is served on the OpenAI-compatible chat completions endpoint. Point any OpenAI SDK at https://api.aimlapi.com/v1 and set the model to alibaba/qwen3.8-omni-flash. The short alias qwen3.8-omni-flash also resolves to it.
