Skip to content

Routing and reliabilityChecklist

Qwen4-Max-Preview retires Nov 25: what to move and how to check

Qwen4-Max-Preview was only ever offered on Token Plan, and its preview window closes at the end of Nov 25 (UTC+8). This checklist covers the timeline, why a plan key is not a production key, and a tested fallback order for the days you have left.

By INFRO Editorial

Published

6 min read

Luminous routing paths connecting one application node to many AI model endpoints

In short

Qwen4-Max-Preview runs from 10:00 on Nov 11 to 24:00 on Nov 25, 2026 (UTC+8), then is retired; it is available through Token Plan only, not pay-as-you-go 1. Find every caller, check whether any used a plan key from a backend, and move to a tested fallback order before the window closes.

Key takeaways

  • The preview window closes at 24:00 on Nov 25, 2026 (UTC+8), which is 16:00 UTC the same day; Alibaba says no changes will be made during the window and the model is retired after it.
  • qwen4-max-preview is available through Token Plan only, with a dedicated base URL and plan-specific key; Token Plan terms limit use to interactive coding and agent tools, not application backends.
  • The replacement is not named on the pages read, so pick one by testing: qwen3.8-max first, then qwen3.7-max for text-only traffic, then qwen3.7-plus, with a different vendor last.
  • max_tokens on qwen4-max-preview covers thinking plus the answer; older Qwen models keep the previous behavior, so output limits need per-model values.
  • The preview ran at a promotional quota rate, so a pay-as-you-go replacement will not reproduce what the plan consumed.

The timeline, in UTC and UTC+8

Alibaba's model page states the preview period runs from 10:00 on November 11, 2026 to 24:00 on November 25, 2026 (UTC+8), that no changes will be made during it, and that the model will be retired after the preview ends.1 Midnight at the end of Nov 25 in UTC+8 is 16:00 UTC on Nov 25. Set your own cutover deadline before that, not on it.

Model Studio's decommissioning policy gives preview models a shorter runway than stable ones: a notice no later than 14 days before End of Service, and End of Service 14 days after the start of retirement. Stable models get three months.2 Eleven days to twenty-five is fourteen days, so this window fits the preview rule (that is my reading; the policy page does not mention this model by name).

DateWhat the pages say
Nov 11, 10:00 UTC+8Preview opens, Token Plan only 1
Nov 13 (today)12 days to the end of the window
Nov 25, 24:00 UTC+8 (16:00 UTC)Preview ends; model retired after 1
From End of ServiceInference stops, API calls fail, related console features and documentation are retired 2
Preview-to-retirement timeline for qwen4-max-preview.

The policy also says default rate limits may be gradually reduced once retirement starts, and that a retirement can be paused, postponed or cancelled.2 Plan for the stated date. Do not plan for an extension.

What "Token Plan only" changes

qwen4-max-preview is not available pay-as-you-go.1 That affects both the migration and the audit of who was calling it.

Token PlanPay-as-you-go
BillingSubscription, consumed in plan quota units (Alibaba's name for them is on its pages) 3Per Model Studio's pay-as-you-go billing 2
EndpointDedicated https://token-plan.ap-southeast-1.maas.aliyuncs.com 1Workspace endpoint, https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1 4
KeyPlan-specific key, shown once; Team seats get one key each 3 5Model Studio API key
Permitted useInteractive use in compatible coding and agent tools; not automation scripts or application backends 6Not restricted that way on the pages read
RegionSingapore only, Global deployment, so inference runs globally and involves cross-border transfer 6Per workspace region
When quota runs outService pauses until the next cycle or until more quota is added 5Not applicable
How Token Plan access differs from pay-per-token billing.

Three consequences follow.

  • A plan key in a service is a policy problem. If any backend job, script or gateway connection used a Token Plan key for qwen4-max-preview, Alibaba's stated terms treat that as outside the permitted scope, with suspension or key revocation as the consequence.6 Do not carry that key forward to the replacement.
  • The preview ran at a promotional rate. Alibaba says usage of this model consumed as little as 20% of the standard rate, and 8% between 22:00 and 08:00 (UTC+8).5 A pay-as-you-go replacement will not reproduce that curve.
  • Billing names differ. The alias is qwen4.0-max-preview. Both ids work, but bills show the alias.5 Search logs and invoices for both.

Find every caller before you change anything

Alibaba says it emails accounts that called a retiring model in the last three months, and points to the Model Monitoring page for the Singapore and China (Beijing) regions to see which retiring models your account uses.2 Start there, then check your own side. The notice may have gone to a mailbox nobody reads.

  • Open Model Monitoring in each region you use and list calls to qwen4-max-preview and qwen4.0-max-preview.
  • Grep code, config, prompt-management tools and agent settings for both ids, including editor and coding-agent configs that point at the plan endpoint.
  • Group your request log by model id and key for the last 30 days. Note which keys are plan keys.
  • Flag any plan key used from a server, scheduler or CI job.
  • Record per caller: modalities (text only, or images and video), tool use, structured output, reasoning_effort, and the max_tokens they send.
  • Name an owner per caller and a cutover date earlier than Nov 25.

Fallback order

Alibaba's pages I read do not name a replacement for qwen4-max-preview. The Model Studio overview lists Qwen3.7-Plus and Qwen3.8-Flash beside it, and its quickstart calls qwen3.8-max on the workspace endpoint.4 The Token Plan tables list qwen3.8-max, qwen3.7-max and qwen3.7-plus as reasoning models; qwen3.7-max is marked text-only, while qwen3.8-max and qwen3.7-plus also take vision input.5 That is enough to propose an order. Treat it as a hypothesis to test.

  1. qwen3.8-max, the closest tier. Primary candidate for everything, including image and video inputs.
  2. qwen3.7-max, text-only traffic only. Skip it for any route that sends images.
  3. qwen3.7-plus, for vision traffic if step 1 is unavailable or over a rate limit.
  4. A different vendor's flagship, on a connection you already hold, for outages and policy blocks. Test it as a fallback-equivalence case, not an assumption; the earlier post on testing fallback equivalence covers the method.

Confirm each id is enabled for your pay-as-you-go workspace and region before it goes into a route. A model that appears in a Token Plan table is not proof it is open to your workspace.

Parameters that behave differently

Starting with qwen4-max-preview, max_tokens on Chat Completions equals max_completion_tokens and caps thinking and the final answer together. Existing Qwen models keep the earlier behavior, where the limit varies by model and thinking_budget.7 Thinking is on by default, reasoning_effort takes low, medium or xhigh (default), and it should not be set together with thinking_budget.1 Chat Completions also enables preserve_thinking by default, so return prior thinking in reasoning_content, not inside content.1

So one limit cannot be copied across the chain. Keep per-model settings and replay the same prompts against each.

replay.py
from openai import OpenAI

# Point at your gateway or at the pay-as-you-go workspace endpoint.
client = OpenAI(api_key="...", base_url="https://api.infro.io/v1")

CHAIN = [
    # model id,       extra params that must not be shared across models
    ("qwen3.8-max",  {"max_tokens": 4096}),
    ("qwen3.7-max",  {"max_tokens": 4096}),
    ("qwen3.7-plus", {"max_tokens": 4096}),
]

def run(prompt: str, model: str, params: dict):
    r = client.chat.completions.create(
        model=model,
        messages=[{"role": "user", "content": prompt}],
        **params,
    )
    c = r.choices[0]
    return c.finish_reason, r.usage.completion_tokens, c.message.content

Flag finish_reason == "length" as a failure, and compare completion-token counts per prompt against what qwen4-max-preview produced. Answer length is where the thinking-budget change shows up first.

Cutover checklist

  • Build a replay set from real prompts per caller: at least the tool-calling, structured-output and image cases.
  • Run every model in the chain on that set; record schema-valid rate, length stops, latency and tokens per request.
  • Set the per-model output limit and reasoning setting from the replay results, not from the old values.
  • Create pay-as-you-go keys for backend callers and revoke the plan key from any server that held it.
  • Re-estimate monthly spend from measured tokens at the list rates in your own pay-as-you-go account, not from plan consumption.
  • Ship the new chain to a small share of traffic first, with the old model still serving the rest, and watch error mix and truncation.
  • Move all traffic by about Nov 20, leaving five days of margin, then remove qwen4-max-preview from configs.
  • After Nov 25 (UTC+8), search logs for any remaining calls to either id.

Where a gateway helps

A gateway does not make a retired model answer. What it can do is keep the model id out of application code. If a Model Studio pay-as-you-go endpoint is connected as an OpenAI-compatible connection,8 a named route can hold the chain above as priority targets over your own connection, with failure rules deciding retry, move on or stop per failure kind. INFRO's failover retries a route that times out or returns a 5xx before the response starts. A retirement error is not that case, so remove the retired model from the route before the date, not after. INFRO also records vendor deprecation dates and, from the shutdown date, refuses a retiring model before any provider call and names the replacement. Check in the console whether this model is recorded. You still need the replay results above to choose the order.

Questions readers ask

Will calls to qwen4-max-preview fail on a particular error code after the window?
Model Studio's policy says API calls to a retired model will fail 2. The pages read do not give the error body or status, so treat any non-success response as a retirement signal and test your client's handling now.
Can I keep the Token Plan key and just point production at another plan model?
The Token Plan terms describe use inside interactive coding and agent tools and say automated scripts and application backends are not permitted, with suspension or key revocation as the stated consequence 5. Move backend traffic to a pay-as-you-go workspace key instead.

From the team that builds it

Where this shows up in INFRO

INFRO is a control plane in front of the provider accounts you already hold. The capabilities below are the parts of it this article touches, each with the documentation that defines its behaviour.

  • Model retirements

    Available with a plan

    INFRO records each vendor's model deprecations and shutdown dates, warns organizations still sending a retiring model, and from the shutdown date refuses it before any provider call, naming the replacement.

  • Health-aware routing

    Available with a plan

    Named routes use priority or weighted targets over your own connections, with health checks, retries and failover.

    Read the documentation for Health-aware routing
  • Routing rules

    Available with a plan

    If-rules on a route send matching requests to their own targets, by metadata, feature, end user, key, project, prompt size, streaming, images, tools or time of day. Failure rules decide per failure kind whether to retry, move on or stop.

    Read the documentation for Routing rules
  • Automatic failover

    Available with a plan

    A route that times out or 5xxs before the response starts is retried elsewhere without your client seeing it.

    Read the documentation for Automatic failover
  • Provider connections

    Available with a plan

    Connect provider accounts you already hold. Each credential is encrypted when saved, scoped to your organization and never shown again; applications use INFRO gateway keys instead.

    Read the documentation for Provider connections
  • Usage and cost per request

    Available with a plan

    Every request records its model, latency, token or unit counts, and estimated provider cost, queryable by project and key.

    Read the documentation for Usage and cost per request

INFRO accounts are self-serve. Provider usage is billed to you by your providers; INFRO charges a software subscription and takes 0% of model spend. See plans.

Sources

Numbered in order of first citation. Each was opened and checked against the claim on the date shown.

  1. 1.qwen4-max-preview (opens in a new tab) — Alibaba Cloud Model Studio. Accessed Nov 13, 2026.
  2. 2.Model decommissioning policy (opens in a new tab) — Alibaba Cloud Model Studio. Accessed Nov 13, 2026.
  3. 3.Token Plan overview (opens in a new tab) — Alibaba Cloud Model Studio. Accessed Nov 13, 2026.
  4. 4.Model service overview (opens in a new tab) — Alibaba Cloud Model Studio. Accessed Nov 13, 2026.
  5. 5.Token Plan (Team Edition) (opens in a new tab) — Alibaba Cloud Model Studio. Accessed Nov 13, 2026.
  6. 6.Token Plan (Personal Edition) (opens in a new tab) — Alibaba Cloud Model Studio. Accessed Nov 13, 2026.
  7. 7.API compatibility upgrades (opens in a new tab) — Alibaba Cloud Model Studio. Accessed Nov 13, 2026.
  8. 8.Connect a provider (opens in a new tab) — INFRO. Accessed Nov 13, 2026.

About this article

Read on 2026-11-13: Alibaba Cloud Model Studio's qwen4-max-preview page, the model decommissioning policy, the Token Plan overview and Team and Personal Edition pages, the API compatibility notice, the Model Studio service overview, and INFRO's provider docs. The replacement model for qwen4-max-preview, the post-retirement error response and pay-as-you-go per-token rates were not on any page read, so they are left out.

Last checked against its sources on . The next review is due by . No separate named reviewer is recorded for this article.

How articles are written, sourced and corrected is set out in the editorial standards.