Status Start free

Models / Alibaba Qwen

Model vendor

Alibaba Qwen

Alibaba’s Qwen family spans chat, coder, vision and omni models. It’s one of the broadest open-weight lineups.

Get an API key See all prices

70Models routed

+304%Average vs list price

1Channels serving Alibaba Qwen

Popular models

Qwen3.8 27BnewQwen3.8 27B is Alibaba Qwen's open-weight dense vision-language model, released 2026-08, handling text, image, and video inputs across a 1M token context.$0.09 / $0.36in / out · 1M−82%Qwen3 VL 235B A22B InstructQwen3 VL 235B A22B Instruct is Alibaba Qwen's open-weight multimodal model, released 2025-09, combining strong text generation with visual understanding across images and video.$0.18 / $0.79in / out · 1M−54%Qwen3 30B A3BQwen3 30B A3B is Alibaba Qwen's open mixture-of-experts model, released 2025-04, balancing reasoning depth with efficient inference.$0.07 / $0.26in / out · 1M−46%

Alibaba Qwen models on MirAPI

ModelTypeContextInputOutputCache r / wOff listChannels

Qwen3.8 27BnewText1M~~$0.24~~$0.09~~$2.20~~$0.36$0.04 / —−82%1

Qwen3 VL 235B A22B InstructText262K~~$0.21~~$0.18~~$1.90~~$0.79$0.10 / —−54%1

Qwen3 30B A3BText41K~~$0.12~~$0.07~~$0.50~~$0.26— / —−46%1

Qwen3 235B A22B Thinking 2507Text128K~~$0.45~~$0.27~~$3.50~~$2.70— / —−25%1

Qwen3.5-27BText262K~~$0.26~~$0.27~~$2.60~~$2.16— / —−15%1

Qwen3.8 2.4T A95BnewText1.049M~~$2.00~~$1.80~~$6.00~~$5.40$0.45 / —−10%1

Qwen3.8 FlashnewText1M~~$0.15~~$0.14~~$0.47~~$0.42$0.01 / $0.18−10%1

Qwen3.7 FlashnewText1M~~$0.03~~$0.03~~$0.13~~$0.12$0.003 / $0.03−10%1

Qwen3.6 FlashText1M~~$0.19~~$0.17~~$1.13~~$1.01— / $0.21−10%1

Qwen3.5 397B A17BText262K~~$0.50~~$0.54~~$3.60~~$3.24— / —−8%1

Qwen3 30B A3B Instruct 2507Text262K~~$0.09~~$0.09~~$0.30~~$0.27— / —−8%1

qvq-maxText131K$1.08$4.32— / ——1

qwen-longText10M$0.06$0.26— / ——1

qwen-maxText33K$1.44$5.76— / ——1

qwen-mt-plusText16K$2.21$6.63— / ——1

qwen-mt-turboText16K$0.14$0.44— / ——1

qwen-vl-maxText131K$0.72$2.88— / ——1

qwen-vl-ocrText34K$0.06$0.14— / ——1

qwen-vl-plusText131K$0.19$0.57— / ——1

qwen3-coder-480b-a35b-instructText262K$1.35$6.75— / ——1

qwen3-coder-plusText1M$0.90$4.50— / ——1

qwen3-maxText262K$1.08$5.40— / ——1

qwen3-omni-flashText66K$0.39$1.49— / ——1

qwen3.5-flashText1M$0.09$0.36$0.009 / $0.11—1

qwen3.5-plusText1M$0.36$2.16— / ——1

qwen3.6-max-previewText262K$1.17$7.02$0.12 / $1.46—1

qwen3.8-maxText1M$1.80$5.40$0.23 / $2.25—1

qwq-plusText131K$0.72$2.16— / ——1

Qwen3.7 PlusText1M$0.36$1.44$0.04 / $0.45—1

Qwen3.6 35B A3BText262K$0.22$1.34— / ——1

Qwen3.6 PlusText1M$0.45$2.70$0.05 / $0.56—1

Qwen3.5-122B-A10BText262K$0.36$2.88— / ——1

Qwen3 Coder FlashText1M$0.27$1.35— / ——1

Qwen-PlusText1M$0.36$1.08$0.07 / ——1

Qwen3.7 MaxText1M$2.25$6.75$0.45 / $2.81—1

Qwen3.6 27BText262K$0.54$3.24— / ——1

Qwen3.5-35B-A3BText262K$0.23$1.80— / ——1

Qwen3 Next 80B A3B InstructText262K$0.45$1.80— / ——1

Qwen3.8 Max (0902)newText1M$67.50$67.50— / ——1

Qwen3 VL 30B A3B ThinkingText262K$67.50$67.50— / ——1

Qwen Image 2.1 PronewImage66K——— / —soon—

Qwen Image 2.1 TurbonewImage66K——— / —soon—

Qwen3.8 Max PrimenewText1M$4.00$12.00— / —soon—

Qwen3.8 Omni FlashnewText1M$0.15$0.47— / —soon—

Qwen Image 3newImage66K——— / —soon—

Qwen Image 3 PronewImage66K——— / —soon—

Qwen3 ASR 0.6BnewTranscription—$3.33—— / —soon—

Qwen3 ASR 1.7BnewTranscription—$7.50—— / —soon—

Qwen3 Reranker 8BnewReranking41K——— / —soon—

Qwen-Audio-3.0-TTS FlashnewSpeech—$15.00—— / —soon—

Qwen-Audio-3.0-TTS PlusnewSpeech—$20.00—— / —soon—

Qwen3.5 Plus 2026-04-20Text1M$0.30$1.80— / —n/a—

Qwen3.5-9BText262K$0.10$0.15— / —n/a—

Qwen3 Coder NextText262K$0.12$0.80— / —n/a—

Qwen3.5 Plus 2026-02-15Text1M$0.26$1.56— / —n/a—

Qwen3.5-FlashText1M$0.07$0.26— / —n/a—

Qwen3 Embedding 4BEmbeddings33K$0.02—— / —n/a—

Qwen3 Embedding 8BEmbeddings41K$0.01—— / —n/a—

Qwen3 VL 30B A3B InstructText262K$0.15$0.60— / —n/a—

Qwen3 VL 8B InstructText262K$0.25$0.75— / —n/a—

Qwen3 Next 80B A3B ThinkingText262K$0.15$1.20— / —n/a—

Qwen3 235B A22B Instruct 2507Text262K$0.09$0.55— / —n/a—

Qwen3 Coder 30B A3B InstructText262K$0.07$0.28— / —n/a—

Qwen3 Coder 480B A35BText262K$0.30$1.00— / —n/a—

Qwen3 14BText41K$0.12$0.24— / —n/a—

Qwen3 32BText131K$0.08$0.28— / —n/a—

Qwen2.5 VL 72B InstructText128K$0.80$1.00— / —n/a—

Qwen2.5 Coder 32B InstructText33K$0.66$1.00— / —n/a—

Qwen2.5 7B InstructText33K$0.10$0.20— / —n/a—

Qwen2.5 72B InstructText33K$0.36$0.40— / —n/a—

Browse the full catalog

Migration

A drop-in replacement for the OpenAI API

MirAPI accepts the OpenAI wire format, so the official SDKs, LangChain, agent frameworks and your own wrapper all work as they are. Change the base URL and use model IDs as they appear in our catalog:

Endpoints

/v1/chat/completionsChat & tool calls

/v1/embeddingsText embeddings

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.mirapi.ai/v1",   # changed
    api_key=os.environ["MIRAPI_API_KEY"],   # changed
)

resp = client.chat.completions.create(
    model="qwen3.8-27b",
    messages=[{"role": "user", "content": "Hello"}],
)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.mirapi.ai/v1",  // changed
  apiKey: process.env.MIRAPI_API_KEY,      // changed
});

const res = await client.chat.completions.create({
  model: "qwen3.8-27b",
  messages: [{ role: "user", content: "Hello" }],
});

curl https://api.mirapi.ai/v1/chat/completions \
  -H "Authorization: Bearer $MIRAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.8-27b",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Other vendors

OpenAI84 Google52 Anthropic18 xAI17 Zhipu AI16 ByteDance13 MiniMax14 DeepSeek15 Moonshot AI7 Mistral AI26

One key covers Alibaba Qwen and 10 more vendors.

1M free tokens to start. No card required.

Start free Read the docs