Qwen3-Omni Captioner API

alibaba/qwen3-omni-30b-a3b-captioner
The Qwen3-Omni Captioner is a fine-tuned model, focused on audio input and generating detailed, low-hallucination descriptive captions from audio clips.
Context
64K tokens
Input
$4.953 / 1M tokens
Output
$3.978 / 1M tokens
Released
Nov 14, 2025

How to use Qwen3-Omni Captioner API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to alibaba/qwen3-omni-30b-a3b-captioner.
import requests

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "alibaba/qwen3-omni-30b-a3b-captioner",
      "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-omni-30b-a3b-captioner",
    "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-omni-30b-a3b-captioner","messages":[{"role":"user","content":"Hello!"}]}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.

Qwen3-Omni Captioner API Pricing

TypePrice
Input
$4.953 / 1M tokens
Output
$3.978 / 1M tokens

Qwen3-Omni Captioner vs other models

ModelInputOutputContextBest for
$4.953 / 1M tokens
$3.978 / 1M tokens
64K tokens
Chat + assistants
$6.5 / 1M tokens
$39 / 1M tokens
1M tokens
Reasoning + agents
$2.6 / 1M tokens
$13 / 1M tokens
1M tokens
Balanced coding + agents
$3.9 / 1M tokens
$19.5 / 1M tokens
1M tokens
Long-context, multimodal & agentic workflows
$0.65 / 1M tokens
$3.9 / 1M tokens
1M tokens
Reasoning + agents

Frequently asked questions

Qwen3-Omni Captioner has a 65,536 tokens context window and can return up to 32,768 tokens.

Qwen3-Omni Captioner takes audio as input and returns text.

Use alibaba/qwen3-omni-30b-a3b-captioner as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

Qwen3-Omni Captioner became available on November 14, 2025.

Qwen3-Omni Captioner is priced at input $4.953 / 1M tokens, output $3.978 / 1M tokens.

Yes, Qwen3-Omni Captioner can stream responses as they are generated.

Qwen3-Omni Captioner was built by Alibaba Cloud.

It generates descriptive captions for audio content—covering speech, ambient sounds, music, and emotions—rather than producing a word-for-word transcription.

It supports audio input up to 40 minutes long.

Audio is converted at a rate of 1 second of audio equaling 25 tokens.

Start building with Qwen3-Omni Captioner

Get API Key
1000+ models, one API.