{"slug": "qwen3-8-max", "title": "Qwen3.8-Max", "summary": "Alibaba Cloud released Qwen3.8-Max-0902, an upgraded snapshot of its Qwen3.8-Max large language model, featuring enhanced coding capabilities for complex engineering projects, improved collaborative agent performance, and refined native vision understanding across chart reasoning and document parsing. The model retains a 1M context window, thinking mode, and full tool ecosystem, with pricing set at $2 per 1M input tokens and $6 per 1M output tokens.", "body_md": "### Qwen3.8-Max\n\nCopy success!\n\n[Try AI](https://www.qwencloud.com/try-ai/chat?models=qwen3.8-max-0902)\n\n[Add to Compare](/compare?models=qwen3.8-max-0902)\n\n## Overview\n\nQwen3.8-Max-0902（alias qwen3.8-max-2026-09-02）is an upgraded snapshot of qwen3.8-max. Coding capability breaks new ground, handling more complex engineering-scale projects and long-horizon autonomous development. Collaborative agent performance is significantly enhanced, with greater composure in multi-tool orchestration and end-to-end task delivery. Native vision understanding is refined across chart reasoning, document parsing, and multimodal perception — sharper and more reliable. Retains the 1M context window, thinking mode, and full tool ecosystem, evolving at a higher level of intelligence.\n\n#### Input\n\nImageTextVideo\n\n#### Output\n\nText\n\n## Features\n\n#### Prefix Completion\n\nEnable Partial Mode when calling the Qwen API to make the model continue strictly from your provided prefix text.[View docs](https://docs.qwencloud.com/developer-guides/text-generation/partial-mode)\n\n#### Function Calling\n\nUse function calling to connect large language models with external tools and systems.[View docs](https://docs.qwencloud.com/developer-guides/text-generation/function-calling)\n\n#### Cache\n\nContext Cache stores shared prefixes for long-context requests to reduce repeated computation, improve latency, and lower cost.[View docs](https://docs.qwencloud.com/developer-guides/text-generation/context-cache#implicit-cache)\n\n#### Structured Outputs\n\nStructured Outputs help ensure the model returns a JSON string in the expected format.[View docs](https://docs.qwencloud.com/developer-guides/text-generation/structured-output)\n\n## Pricing\n\n- Input$2Per 1M tokens\n- Output$6Per 1M tokens\n- Input(Implicit Cache)$0.25Per 1M tokens\n- Explicit Cache Creation$2.5Per 1M tokens\n- Explicit Cache Read$0.17Per 1M tokens\n\n## Rate Limits & Context\n\n- Max Input991K\n- Max Output131K\n- Max Input (Thinking)983K\n- Max Output (Thinking)131K\n- Context1M\n- Max Reasoning262K\n- TPMTokens Per Minute1M\n- RPMRequests Per Minute15K\n\n## Built-in Tools\n\n[code_interpreter](https://docs.qwencloud.com/developer-guides/text-generation/code-interpreter)Responses API\n\n[i2i_search](https://docs.qwencloud.com/developer-guides/text-generation/image-search)Responses API\n\n[t2i_search](https://docs.qwencloud.com/developer-guides/text-generation/image-search)Responses API\n\n[web_extractor](https://docs.qwencloud.com/developer-guides/text-generation/web-scraping)Responses API\n\n[web_search](https://docs.qwencloud.com/developer-guides/text-generation/web-search)Responses API\n\n## API Reference\n\n[Call API](https://home.qwencloud.com/api-keys)\n\nCopy success!\n\n123456789101112131415161718192021222324252627282930\n\n``` python\nfrom openai import OpenAI\nimport os\n\nclient = OpenAI(\n    # If the environment variable is not set, replace it with your Model Studio API key: api_key=\"sk-xxx\"\n    api_key=os.getenv(\"DASHSCOPE_API_KEY\"),\n    base_url=\"https://dashscope-intl.aliyuncs.com/compatible-mode/v1\",\n)\n\nmessages = [{\"role\": \"user\", \"content\": \"Who are you\"}]\ncompletion = client.chat.completions.create(\n    model=\"qwen3.8-max-0902\",  # You can replace this with another deep thinking models\n    messages=messages,\n    extra_body={\"enable_thinking\": True},\n    stream=True\n)\nis_answering = False  # Indicates whether the response phase has started\nprint(\"\\n\" + \"=\" * 20 + \"Thinking process\" + \"=\" * 20)\nfor chunk in completion:\n    if not chunk.choices:\n        continue\n    delta = chunk.choices[0].delta\n    if hasattr(delta, \"reasoning_content\") and delta.reasoning_content is not None:\n        if not is_answering:\n            print(delta.reasoning_content, end=\"\", flush=True)\n    if hasattr(delta, \"content\") and delta.content:\n        if not is_answering:\n            print(\"\\n\" + \"=\" * 20 + \"Full response\" + \"=\" * 20)\n            is_answering = True\n        print(delta.content, end=\"\", flush=True)\n```\n\n123456789101112131415161718192021222324252627282930\n\n``` python\nfrom openai import OpenAI\nimport os\n\nclient = OpenAI(\n    # If the environment variable is not set, replace it with your Model Studio API key: api_key=\"sk-xxx\"\n    api_key=os.getenv(\"DASHSCOPE_API_KEY\"),\n    base_url=\"https://dashscope-intl.aliyuncs.com/compatible-mode/v1\",\n)\n\nmessages = [{\"role\": \"user\", \"content\": \"Who are you\"}]\ncompletion = client.chat.completions.create(\n    model=\"qwen3.8-max-0902\",  # You can replace this with another deep thinking models\n    messages=messages,\n    extra_body={\"enable_thinking\": True},\n    stream=True\n)\nis_answering = False  # Indicates whether the response phase has started\nprint(\"\\n\" + \"=\" * 20 + \"Thinking process\" + \"=\" * 20)\nfor chunk in completion:\n    if not chunk.choices:\n        continue\n    delta = chunk.choices[0].delta\n    if hasattr(delta, \"reasoning_content\") and delta.reasoning_content is not None:\n        if not is_answering:\n            print(delta.reasoning_content, end=\"\", flush=True)\n    if hasattr(delta, \"content\") and delta.content:\n        if not is_answering:\n            print(\"\\n\" + \"=\" * 20 + \"Full response\" + \"=\" * 20)\n            is_answering = True\n        print(delta.content, end=\"\", flush=True)\n```\n\n", "url": "https://wpnews.pro/news/qwen3-8-max", "canonical_source": "https://www.qwencloud.com/models/qwen3.8-max-0902", "published_at": "2026-09-02 06:46:55+00:00", "updated_at": "2026-09-02 07:23:07.298465+00:00", "lang": "en", "topics": ["large-language-models", "generative-ai", "ai-products"], "entities": ["Alibaba Cloud", "Qwen3.8-Max-0902", "Qwen3.8-Max"], "alternates": {"html": "https://wpnews.pro/news/qwen3-8-max", "markdown": "https://wpnews.pro/news/qwen3-8-max.md", "text": "https://wpnews.pro/news/qwen3-8-max.txt", "jsonld": "https://wpnews.pro/news/qwen3-8-max.jsonld"}}