Back to changelog

New Alibaba Qwen Models: Qwen3 Next, Max, Plus, Flash, Vision

Added support for qwen-max, qwen-max-latest, qwen-plus-latest, qwen-flash, qwen-vl-max, qwen-vl-plus and the new Qwen3 Next 80B A3B Instruct and Thinking models.

Alibaba Qwen models now available on LLM Gateway

We’ve added support for the latest Alibaba Qwen models through our unified API. These models bring strong reasoning, speed-focused variants, and multimodal (vision) capabilities.

🧠 New Qwen3 Next Generation Models

qwen3-next-80b-a3b-instruct — next-gen 80B instruct model

  • Pricing: Input $0.50 / 1M tokens, Output $2.00 / 1M tokens
  • Context: 129,024 tokens, Max output: 32,768 tokens
  • Capabilities: Streaming, Tools, JSON output Try in Playground

qwen3-next-80b-a3b-thinking — next-gen reasoning model

  • Pricing: Input $0.50 / 1M tokens, Output $6.00 / 1M tokens
  • Context: 131,072 tokens, Max output: 32,768 tokens
  • Capabilities: Streaming, Reasoning, Tools, JSON output Try in Playground

🚀 New Text Models

qwen-max — flagship performance

  • Pricing: Input $1.60 / 1M tokens, Output $6.40 / 1M tokens
  • Context: 131,072 tokens, Max output: 32,000 tokens
  • Capabilities: Streaming, Vision, Tools, JSON output Try in Playground

qwen-max-latest — rolling latest for Max:

  • Pricing: Input $1.60 / 1M tokens, Output $6.40 / 1M tokens
  • Context: 131,072 tokens, Max output: 32,000 tokens
  • Capabilities: Streaming, Vision, Tools, JSON output Try in Playground

qwen-plus-latest — balanced performance and cost

  • Pricing: Input $0.40 / 1M tokens, Output $1.20 / 1M tokens
  • Context: 1,000,000 tokens, Max output: 32,000 tokens
  • Capabilities: Streaming, Tools, JSON output Try in Playground

qwen-flash — fast, cost‑efficient responses

  • Pricing: Input $0.05 / 1M tokens, Output $0.40 / 1M tokens
  • Context: 1,000,000 tokens, Max output: 32,000 tokens
  • Capabilities: Streaming, Tools, JSON output Try in Playground

👀 New Vision Models

qwen-vl-max — high‑end multimodal (vision + text)

  • Pricing: Input $0.80 / 1M tokens, Output $3.20 / 1M tokens
  • Context: 131,072 tokens, Max output: 32,000 tokens
  • Capabilities: Streaming, Vision, JSON output Try in Playground

qwen-vl-plus — balanced multimodal

  • Pricing: Input $0.21 / 1M tokens, Output $0.64 / 1M tokens
  • Context: 131,072 tokens, Max output: 32,000 tokens
  • Capabilities: Streaming, Vision, JSON output Try in Playground

Use these models immediately via our OpenAI‑compatible endpoint — no extra setup required. Explore pricing and capabilities on the Models page.

    New Alibaba Qwen Models: Qwen3 Next, Max, Plus, Flash, Vision - Changelog - LLM Gateway