Skip to content

Architecture and migrationChecklist

DeepSeek previews retire on Foundry Dec 3 to Mar 6: cutover order

Foundry's schedule retires four DeepSeek V4 and V4.1 preview versions on three dates, and none lists a replacement. This checklist orders the moves, compares GA on Foundry with DeepSeek's own API, and shows how to keep one alias your code never has to change.

By INFRO Editorial

Published

7 min read

One application request entering a central AI gateway and branching to many model routes

In short

Move in date order: V4-Flash-0731 before Dec 3, then V4-Pro-0813 and V4.1-Flash before Dec 15, then V4.1-Flash-1017 before Mar 6. None of the four has a listed replacement, so choose per workload between GA V4 on Foundry and DeepSeek's API, and put a stable alias in front of both 14.

Key takeaways

  • Four Foundry preview versions retire on three dates: Dec 3 (V4-Flash-0731), Dec 15 (V4-Pro-0813 and V4.1-Flash) and Mar 6, 2027 (V4.1-Flash-1017), and the schedule lists no replacement for any of them.
  • A retired Foundry model returns 410 Gone, and a preview deployment is either force-upgraded or terminated, so the move has to finish before the date, not on it.
  • Moving the V4.1-Flash workloads to DeepSeek's deepseek-flash serves V4.1-Flash-1017 today and can retire two of the four deadlines in one cutover, at the cost of leaving Azure billing and support.
  • The version labels on Foundry and DeepSeek's changelog disagree about which Pro build is GA, so run your own eval instead of assuming the GA row equals the preview you use.
  • Keep one alias in your own configuration and move its targets with a weighted split, then remove the retired target before its date.

The four retirements as one sequence

Microsoft's Foundry schedule lists four DeepSeek preview versions with retirement dates, and the replacement cell is empty for each1. Three dates matter, because two versions share December 15.

RetiresFoundry preview versionDays from Nov 21Listed replacement
Thu Dec 3, 2026DeepSeek-V4-Flash-073112none
Tue Dec 15, 2026DeepSeek-V4-Pro-081324none
Tue Dec 15, 2026DeepSeek-V4.1-Flash (2026-09-10)24none
Sat Mar 6, 2027DeepSeek-V4.1-Flash-1017105none
Preview retirements from Foundry's schedule1. Weekdays and day counts are calculated from those dates.

Two rules from the lifecycle policy shape the plan. A retired model returns 410 Gone on every inference request. A preview deployment is either force-upgraded to a newer preview or to GA, or terminated with no replacement, and you cannot choose to stay on it2. Microsoft also says it does not recommend preview models in production3. Treat the dates as the day the call fails, and finish the day before. The pages say nothing about the time of day or time zone, and Mar 6 is a Saturday, so plan for Friday Mar 5.

Before the first move: inventory

Do this once, this week. Everything later depends on knowing which code calls which version.

  • List every Foundry deployment whose model is one of the four versions above, with its owner and the services that call it.
  • Record which calls use thinking mode, tools, JSON output, images or long outputs. DeepSeek's API documents thinking as the default mode and a 1M context with up to 384K output4; confirm what your Foundry deployment does with the same request.
  • Pull a week of logged requests per workload into a test set, with the expected outputs or a rubric.
  • Note whether finance relies on Azure billing, Azure support or an Azure spending commitment for these calls. Models sold by Azure are billed through your Azure subscription and covered by Microsoft support and Azure SLAs3; a move to DeepSeek's API leaves all three.
  • Find hard-coded model or deployment names in code, prompts, notebooks and CI. These are the edits an alias removes.

Which replacement for which deployment

There are three destinations. Only the first two are confirmed.

DestinationWhat is confirmedWhat to check
GA on FoundryDeepSeek-V4-Flash and DeepSeek-V4-Pro, both version 2026-04-23, GA, retiring 2028-02-221Version differs from your preview; vision and parameters
DeepSeek's own APIdeepseek-flash serves V4.1-Flash-1017; deepseek-v4-pro serves V4-Pro-08134Billing, data handling, concurrency limits
SageMakerNot confirmed (see below)Whether a listing exists at all
Replacement options for the four preview versions.

Dec 3: DeepSeek-V4-Flash-0731

This is the nearest deadline and the one with the least time to evaluate. DeepSeek describes 0731 as the same architecture and size as the earlier Flash preview, re-post-trained5. DeepSeek's own API no longer serves a V4 Flash: it was retired, and the old names are routed to V4.1-Flash-10175. So the like-for-like choice on Foundry is GA V4-Flash, which is a 2026-04-23 build and therefore older than 0731. Run your test set against both before you accept it. If the workload can take V4.1 behavior, deepseek-flash is the other candidate.

One oddity: in the schedule text I read, the replacement cell beside GA V4-Flash names the 0731 preview, which retires first. Do not follow that pointer, and recheck the live page.

Dec 15: DeepSeek-V4-Pro-0813

The two vendors' labels disagree here. DeepSeek's change log says the GA release of V4-Pro rolled out on August 135, and its pricing page lists deepseek-v4-pro as DeepSeek-V4-Pro-08134. Foundry lists 0813 as a preview and the 2026-04-23 version as GA1. Do not assume the Foundry GA row is the build you have been running. The DeepSeek API is the closest match by name; GA V4-Pro keeps you inside Azure. The choice is your eval result against your need for Azure billing and support. Mind the ceiling: DeepSeek lists a concurrency limit of 500 for Pro4.

Dec 15: DeepSeek-V4.1-Flash (2026-09-10)

Foundry's next preview, V4.1-Flash-1017, retires on Mar 6, so moving there only schedules a second cutover. GA V4-Flash is a different generation. DeepSeek presents V4.1 Flash as having native multimodal visual understanding5, and the pricing page marks vision as supported for deepseek-flash4. If your calls carry images, test GA V4-Flash on them before choosing it.

The cleaner option is deepseek-flash on DeepSeek's API. It already serves V4.1-Flash-10176, so the same move also covers the Mar 6 deadline.

Mar 6, 2027: DeepSeek-V4.1-Flash-1017

This one has the longest runway and the least certain end. Foundry says previews launch with a "not sooner than" date, typically 90 days out, and are sometimes extended until a replacement exists2. Treat the date as firm and check the schedule monthly for a GA V4.1 Flash or a later preview. If nothing appears by early February, deepseek-flash is the fallback.

Prices to compare, and what to leave out

DeepSeek's list rates, per 1M tokens in USD, as on its pricing page today4:

Flash peakFlash off-peakPro peakPro off-peak
Input, cache hit0.0060.0030.0440.022
Input, cache miss0.300.151.320.66
Output1.200.603.961.98
DeepSeek list rates. Off-peak is half of peak. Peak is 01:00–04:00 and 06:00–10:00 UTC, Monday to Friday, excluding Chinese public holidays4.

I did not read Azure's rates for the GA V4 deployments, so compare those from your own Azure price sheet and contract. DeepSeek deducts usage from a balance on your DeepSeek account4, which lands in different cost data than an Azure line item. Thinking is the default mode4, so measure output tokens on your own prompts rather than reusing rate-card arithmetic.

SageMaker: confirm before you plan on it

AWS's JumpStart overview names providers such as AI21 Labs, Cohere, Databricks, Hugging Face, Meta, Mistral AI, Stability AI and Alexa, and does not name DeepSeek7. I could not confirm a V4 Flash, V4 Pro or V4.1 Flash listing, so I would not build a December plan on one. If your cloud team has a verified model card, the trade-offs (instance-hours, capacity, data location) are in DeepSeek V4 on SageMaker JumpStart: self-host or call the API?. Also remember that a JumpStart build is a pinned set of weights, not whatever deepseek-flash serves next month.

Keep one alias through all four moves

DeepSeek's own names move under you. deepseek-flash was served by V4.1-Flash and now by V4.1-Flash-1017 with the calling method unchanged5. deepseek-v4-flash still works only because it is routed to another model6. The same applies to your own deployment names on Foundry. Put one name in application code and move the targets behind it. The wider argument is in model aliases vs pinned snapshots.

app.py
from openai import OpenAI

client = OpenAI(base_url="https://api.infro.io/v1", api_key=INFRO_API_KEY)

# "deepseek-flash-prod" is a route name, not a vendor model id.
resp = client.chat.completions.create(
    model="deepseek-flash-prod",
    messages=[{"role": "user", "content": "Summarize this ticket."}],
)

If you run a gateway, this is what a route is for. An INFRO route is a name your application sends as model, resolved to an ordered list of your own provider connections and the model each should serve8. The weighted strategy picks the first target in proportion to weight and falls through the rest, and a weight of 0 is a standby that takes no first attempt, which suits a gradual migration8. The trace names the route and the connection that served the request8. INFRO takes 0% of model spend and your providers invoice you directly9. Confirm in the connection list that the provider kinds you need are served before you rely on this path.

Remove the old target before its retirement date. A 410 Gone is a client-side error, not a timeout or 5xx, and I did not confirm that failover covers it, so a leftover standby is not a safe net. INFRO also records vendor shutdown dates and refuses a retired model before any provider call, naming the replacement9; check the console to see whether these ids are in that record. To judge each target before shifting weight, build a dataset from logged requests and run it through an experiment, which shows an estimated cost and stops at a spend cap you set.

Cutover checklist

  • Alias created, and every caller switched to it before any model changes.
  • Eval run per workload on each candidate, comparing quality, latency and cost together, as Microsoft advises2.
  • Dec 3 workload moved and the old target removed by Dec 2.
  • Dec 15 workloads (Pro and V4.1 Flash) moved and removed by Dec 14.
  • If V4.1 Flash moved to deepseek-flash, Mar 6 workload marked done; otherwise a dated reminder on Feb 1 to re-read the schedule.
  • Billing owner told which spend now arrives in Azure and which on DeepSeek's balance.
  • Concurrency checked against DeepSeek's limits: 2,500 for Flash and 500 for Pro4.
  • Retired ids deleted from code, prompts and CI so nothing quietly calls them.

Questions readers ask

Will Foundry upgrade my preview deployment for me on the retirement date?
Not reliably. The lifecycle policy says preview deployments are force-upgraded to a newer preview or to GA, or retired with no replacement, and that there is no option to stay on a retiring preview 2. The replacement column for all four DeepSeek previews is empty 1, so plan on a manual move.
Can I keep calling deepseek-v4-flash on DeepSeek's API?
For now the name is accepted and served by DeepSeek-V4.1-Flash-1017 at the Flash price 6, but the changelog calls the routing temporary 5. Use deepseek-flash, or better, your own alias that points at it.

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.

  • 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
  • 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.

  • Model availability from your keys

    Available with a plan

    INFRO reads the model list your own provider key returns every three hours, and stops offering a model your key has stopped listing, with the date it stopped.

  • Experiments

    Available with a plan

    A dataset run through the gateway across up to six variants (a model or route, a prompt version, settings), judged by your evaluators and compared side by side, with the request count and estimated provider cost shown before it starts and a spend cap it stops at. On every plan.

  • Datasets

    Available with a plan

    Inputs and expected outputs built from logged requests in one click, uploaded as JSONL or CSV, or sent from code, kept until you delete them. On every plan.

  • 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.Model retirement schedule - Microsoft Foundry (opens in a new tab) — Microsoft Learn. Accessed Nov 21, 2026.
  2. 2.Microsoft Foundry Models lifecycle and support policy (opens in a new tab) — Microsoft Learn. Accessed Nov 21, 2026.
  3. 3.Foundry Models sold by Azure (opens in a new tab) — Microsoft Learn. Accessed Nov 21, 2026.
  4. 4.Models & Pricing (opens in a new tab) — DeepSeek API Docs. Accessed Nov 21, 2026.
  5. 5.Change Log (opens in a new tab) — DeepSeek API Docs. Accessed Nov 21, 2026.
  6. 6.Your First API Call (opens in a new tab) — DeepSeek API Docs. Accessed Nov 21, 2026.
  7. 7.Amazon SageMaker JumpStart (opens in a new tab) — Amazon Web Services. Accessed Nov 21, 2026.
  8. 8.Routes (opens in a new tab) — INFRO Docs. Accessed Nov 21, 2026.
  9. 9.INFRO documentation (opens in a new tab) — INFRO Docs. Accessed Nov 21, 2026.

About this article

Read on 2026-11-21: Microsoft's Foundry retirement schedule, lifecycle policy and models-sold-by-Azure pages; DeepSeek's first-call, pricing and change log pages; AWS's SageMaker JumpStart page; INFRO's docs overview and Routes page. Left out as unconfirmed: any DeepSeek V4 listing on SageMaker, Azure's rates for the GA V4 deployments, and the retirement time of day and time zone.

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.