How to Use the Qwen3.8 Max 0902 API

Qwen3.8 Max 0902 is the upgraded snapshot of Alibaba's flagship Qwen3.8 Max, released on September 2, 2026. It keeps what the flagship is known for, a 1M token context, text, image, and video understanding, deep thinking that is on by default, and five built-in tools, and sharpens the parts that matter for real work: coding on engineering-scale projects, long-horizon autonomous development, steadier multi-tool agent orchestration, and more reliable chart reasoning and document parsing.

Qwen3.8 Max 0902 is live on EmpirioLabs today through an OpenAI-compatible API, with function calling, strict JSON Schema structured output, streaming, and up to 128K output tokens. Try it in the playground or call it from any OpenAI-compatible client. The full spec and current rates live on the Qwen3.8 Max 0902 model page and the API docs.

Pricing

Billing is usage based with one flat input rate and one flat output rate at every prompt size, the same rates as Qwen3.8 Max, and there is no separate cache tier. Web search, text-to-image search, and image-to-image search add a small per-call fee that applies only when a call actually runs; the web extractor and code interpreter run at no extra cost. Thinking tokens bill as output tokens. Current rates always live on the model page and the pricing page, which stay in sync with what you are charged.

Quickstart

Point any OpenAI SDK at the EmpirioLabs base URL and pass qwen3-8-max-0902 as the model:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.empiriolabs.ai/v1",
    api_key="YOUR_EMPIRIOLABS_API_KEY",
)

resp = client.chat.completions.create(
    model="qwen3-8-max-0902",
    messages=[
        {"role": "user", "content": [
            {"type": "text", "text": "Summarize the trend in this chart and flag anything unusual."},
            {"type": "image_url", "image_url": {"url": "https://example.com/chart.png"}},
        ]},
    ],
    extra_body={"enable_thinking": True, "thinking_budget": 8192},
)

print(resp.choices[0].message.content)

The same model id works on /v1/responses, the Anthropic-shaped /v1/messages, and the Google-compatible /v1beta/models/qwen3-8-max-0902:generateContent route. The alternate ids qwen3.8-max-0902 and qwen3.8-max-2026-09-02 resolve to the same model.

Thinking

Deep thinking is on by default and streams back as reasoning_content alongside the answer. Control it with enable_thinking and thinking_budget (up to 262,144 tokens), or send reasoning_effort and the platform maps it to a budget sized for the model. Thinking tokens bill as output tokens, so disable thinking or set a small budget for short, latency-sensitive turns.

Built-in tools

Five built-in tools ride behind tool_* toggles and are all off by default: tool_web_search, tool_web_extractor, tool_code_interpreter, tool_web_search_image, and tool_image_search. The web extractor requires web search, and both the extractor and the code interpreter run only while thinking is enabled. When tools run, the response's usage.tool_usage map reports exactly how many calls were made, so you can audit per-tool billing.

Structured output

For an exact response shape, pass response_format with {"type": "json_schema", ...} and "strict": true: the model returns exactly the schema's keys with no extras. Plain JSON mode with {"type": "json_object"} is also supported.

Things worth knowing before your first call

• Pin the dated id when behavior must not change under you. qwen3-8-max follows Alibaba's current default Qwen3.8 Max build, while qwen3-8-max-0902 stays on this snapshot. Use the dated id for evals and production pipelines that need reproducible output.
• tool_choice: "required" does not work while thinking is on. The request is rejected with a clear error. Keep tool_choice: "auto" with thinking enabled, or set enable_thinking: false when you need to force a function call.
• JSON mode needs the word "json" in your messages. A {"type": "json_object"} request is rejected unless the word appears somewhere in the conversation. JSON Schema requests have no such requirement.

Qwen3.8 Max 0902 is available now in the playground and through the EmpirioLabs API.