GPT-5 and o3 snapshots shut down on 2026-12-11: what replaces the 6 IDs
As of November 22, 2026, 19 days remain before the 2026-12-11 shutdown: the 2026-06-11 section of OpenAI's deprecations page still states that these six snapshots leave the API on 2026-12-11 (Dec 11, 2026 in the original), with a Jun 11, 2026 notice date; the current official replacements are gpt-5 and gpt-5-2025-08-07 → gpt-6.1-sol, gpt-5-mini → gpt-6.1-terra, gpt-5-nano → gpt-6-luna, gpt-5-pro → gpt-6.1-sol (with reasoning.mode: pro in the Responses API), o3 → gpt-6.1-sol, and o3-pro → gpt-6.1-sol (reasoning.mode: pro). Developers can also proactively upgrade to the newer-generation flagship gpt-6.2-sol at the same OpenAI official API list price ($2 input / $10 output per million tokens; note that gpt-6.2-sol is a newer upgrade option rather than the default replacement named in the deprecation table). The replacements recorded on 2026-10-26 were gpt-5.6-sol (for gpt-5, o3 and both pro rows), gpt-5.6-terra (gpt-5-mini) and gpt-5.6-luna (gpt-5-nano), now kept as historical context. The six dated snapshots remain gpt-5-2025-08-07, gpt-5-mini-2025-08-07, gpt-5-nano-2025-08-07, gpt-5-pro-2025-10-06, o3-2025-04-16 and o3-pro-2025-06-10, with each alias and snapshot paired in the same Model / system cell (such as gpt-5 | gpt-5-2025-08-07). QCode does not support gpt-6-luna or gpt-5.6-luna; gpt-6.1-sol, gpt-6.1-terra and gpt-6.2-sol are callable on QCode.
Updated 2026-11-22
One key for Claude, GPT and leading Chinese models, billed per token, up and running in minutes.
- Billed per token — live rates on /models
- Pay by card (Visa / Mastercard), Apple Pay, Google Pay or crypto
- Self-service: top up and activate instantly
Four numbers that matter
Shutdown date in the official table
The table columns are Shutdown date, Model / system and Recommended replacement; all six rows read Dec 11, 2026. Official definition: at the time of the shutdown, the model or endpoint will no longer be accessible.
Snapshots in this batch
One dated snapshot each for gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro, o3 and o3-pro, i.e. the Default snapshot on each model page. gpt-5-codex and gpt-5-chat-latest are not in this batch: the official table lists them as shut down on 2026-07-23.
Rows landing on sol / terra / luna
Four rows go to gpt-5.6-sol (gpt-5-pro and o3-pro with reasoning.mode: pro), gpt-5-mini goes to gpt-5.6-terra and gpt-5-nano to gpt-5.6-luna. OpenAI's model pages say Sol, Terra and Luna roughly correspond to the unsuffixed, mini and nano tiers of earlier GPT-5 families.
Max input tokens (gpt-5 → gpt-5.6-sol)
Official model pages: gpt-5 has a 400,000 context window and 272,000 max input tokens; gpt-5.6-sol has 1,050,000 and 922,000. The gpt-5.6-sol page adds that prompts with >272K input tokens are priced at 2x input and 1.5x output for the full request.
What is being retired
As of 2026-10-26, OpenAI will remove six older GPT-5 and o3 snapshots from the API on 2026-12-11. The 2026-06-11 section of the deprecations page says: “On June 11, 2026, we notified developers using older GPT-5 and o3 model snapshots of their deprecation and removal from the API on December 11, 2026.” Each of the six IDs is the dated snapshot for gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro, o3 or o3-pro, and the table puts each alias and its snapshot in one cell.
OpenAI promises at least 6 months' notice for generally available models; June 11 to December 11 is exactly six months by the calendar. In the 2026-10-26 copy the section still sits under Upcoming deprecations, and each Model / system cell pairs the alias with its snapshot.
The six official rows (each checked 2026-10-26)
Every row has the shutdown date Dec 11, 2026 and the notice date Jun 11, 2026. Current official replacements after the 2026-11-19 re-fetch
- 1gpt-5 | gpt-5-2025-08-07 →
gpt-6.1-sol - 2
gpt-5-mini|gpt-5-mini-2025-08-07 →gpt-6.1-terra - 3
gpt-5-nano|gpt-5-nano-2025-08-07 →gpt-6-luna - 4gpt-5-pro | gpt-5-pro-2025-10-06 →
gpt-6.1-sol(reasoning.mode: pro) - 5o3 | o3-2025-04-16 →
gpt-6.1-sol - 6o3-pro | o3-pro-2025-06-10 →
gpt-6.1-sol(reasoning.mode: pro). The earlier record, re-fetched and checked row by row on 2026-10-26 (the replacement column then copied the official text verbatim): ① gpt-5 | gpt-5-2025-08-07 →gpt-5.6-sol; ②gpt-5-mini|gpt-5-mini-2025-08-07 →gpt-5.6-terra; ③gpt-5-nano|gpt-5-nano-2025-08-07 →gpt-5.6-luna; ④ gpt-5-pro | gpt-5-pro-2025-10-06 →gpt-5.6-sol(reasoning.mode: pro); ⑤ o3 | o3-2025-04-16 →gpt-5.6-sol; ⑥ o3-pro | o3-pro-2025-06-10 →gpt-5.6-sol(reasoning.mode: pro). Compared with the 2026-10-08 copy, the Model / system column pairs each alias with its dated snapshot (gpt-5 | gpt-5-2025-08-07, o3 | o3-2025-04-16 and so on); the shutdown dates are unchanged.
Timeline
OpenAI notifies developers using older GPT-5 and o3 snapshots that these six snapshots are deprecated and will be removed from the API on 2026-12-11 (see the 2026-06-11 section of the deprecations page).
Re-fetched on 2026-10-26 and compared with the 2026-10-08 copy: all six rows are still under Upcoming deprecations, the date is still Dec 11, 2026 and the replacements are unchanged; the Model / system column now pairs alias and snapshot. The 2026-10-23 batch has its own page.
Shutdown date: the six snapshots leave the API. By OpenAI's definition the model is no longer accessible at that point; OpenAI also notes that in some cases developers may be able to provision dedicated capacity, via its sales team, for continued access after the shutdown date.
Confirmed vs not stated by OpenAI
Confirmed (verbatim on official pages)
All of this can be read verbatim on the official pages fetched on 2026-10-26: the 2026-06-11 notice and the Dec 11, 2026 shutdown; the six snapshot IDs and their replacements, including reasoning.mode: pro on two rows: gpt-5 | gpt-5-2025-08-07 → gpt-5.6-sol, gpt-5-mini | gpt-5-mini-2025-08-07 → gpt-5.6-terra, gpt-5-nano | gpt-5-nano-2025-08-07 → gpt-5.6-luna, gpt-5-pro | gpt-5-pro-2025-10-06 → gpt-5.6-sol (reasoning.mode: pro), o3 | o3-2025-04-16 → gpt-5.6-sol, o3-pro | o3-pro-2025-06-10 → gpt-5.6-sol (reasoning.mode: pro).
Official definition: at the time of the shut down, the model or endpoint is no longer accessible; on 2026-10-26 the section still sits under Upcoming deprecations. Note: gpt-5.6-luna is not supported on QCode.
⚠️ Not stated / watch out
First, the 2026-10-26 table puts gpt-5 and gpt-5-2025-08-07 in one cell, and the row carries a single shutdown date, 2026-12-11; whether the alias will later point at a newer model is not stated. Second, the table promises neither equivalent output nor equal pricing. Third, as of 2026-10-26 there is no rescheduling wording. Fourth, we have not verified how reasoning.mode: pro behaves on QCode. Fifth, gpt-5.1 is not in this batch; OpenAI lists it for 2027-04-01 with gpt-6-sol as the replacement.
API users vs Codex and third-party tool users
Calling the API or an SDK directly
More than the model string changes. Per the official model pages, gpt-5 supports reasoning.effort minimal, low, medium and high, while gpt-5.6-sol and gpt-6.1-terra support none, low, medium (default), high, xhigh and max, so minimal is not on the new list. gpt-5 takes up to 272,000 input tokens and gpt-5.6-sol up to 922,000; requests above 272K are billed at the long-context price for the whole request.
When moving to gpt-6.1-terra, watch one critical API pitfall: the official model page states verbatim "Tool calling requires the Responses API." Projects still sending tools to legacy /v1/chat/completions will fail if they only swap the model name, and must switch to the Responses API or another supported tool path.
Official prices: gpt-5 $1.25 input / $10 output per million tokens, gpt-5.6-sol $4 / $20 (marked as promotional pricing, available until 2026-11-30), and gpt-6.1-terra $1.00 input / $5.00 output per million tokens.
Using Codex or a third-party tool
In Codex the model lives in the model entry of config.toml (official wording: To specify a model, add a model entry to your configuration file); also check codex exec --model in scripts. gpt-5-codex is not in this batch: the official table lists it as shut down on 2026-07-23 with gpt-5.6-sol as the replacement.
A custom provider or gateway must be a compatible Responses API endpoint; current Codex releases don't support wire_api = "chat". If you typed gpt-5 or o3 into a model dropdown or custom model field in tools such as Cursor or Cline, change it by the same table.
Migration checklist (before 2026-12-11)
- 1Search snapshots: grep code, environment variables, config files and eval scripts for gpt-5-2025-08-07,
gpt-5-mini-2025-08-07,gpt-5-nano-2025-08-07, gpt-5-pro-2025-10-06, o3-2025-04-16 and o3-pro-2025-06-10. - 2Search aliases: also search the quoted strings gpt-5,
gpt-5-mini,gpt-5-nano, gpt-5-pro, o3 and o3-pro as whole words so that o3 does not match o3-mini. The 2026-10-26 table puts each alias and its snapshot in one cell, with a single shutdown date on the row, 2026-12-11; OpenAI does not say whether an alias will later point at a newer model, so we suggest changing it too. - 3Replace per row: gpt-5 and o3 →
gpt-5.6-sol,gpt-5-mini→gpt-5.6-terra,gpt-5-nano→gpt-5.6-luna(not supported on QCode); on QCode use another GPT model such asgpt-5.6-terrainstead (our suggestion, not an official mapping). - 4Pro rows: set model to
gpt-5.6-soland add reasoning.mode: pro, which OpenAI documents for the Responses API. - 5Check parameters: adjust values such as reasoning.effort against the new model documentation, and budget for the long-context price if inputs can exceed 272K.
- 6Verify: send a batch of real requests to the endpoint you actually use and confirm that the model in responses and usage logs is the new ID.
Using the replacements on QCode
As of November 22, 2026, qcode.cc/models supports gpt-6.1-sol and gpt-6.1-terra, as well as the newer-generation gpt-6.2-sol and gpt-6.2-astra (gpt-6.2-sol carries the same OpenAI official API list price as gpt-6.1-sol at $2.00 input / $10.00 output per million tokens); gpt-6-astra is callable on QCode too.
The official replacement for gpt-5-nano, gpt-6-luna, is still not supported: QCode does not support gpt-6-luna or gpt-5.6-luna, so teams migrating off gpt-5-nano can start with gpt-6.1-terra instead (our suggestion, not an official mapping). Historical record (2026-10-26): the earlier replacements gpt-5.6-sol and gpt-5.6-terra were callable on QCode, alongside gpt-6.1-sol and gpt-6-sol.
GPT models use the OpenAI endpoints, not the Anthropic endpoint: set the OpenAI SDK base_url to https://api.qcode.cc/openai/v1 (requests go to /openai/v1/chat/completions), and in the Codex CLI TOML config set base_url = https://api.qcode.cc/openai (requests go to /openai/v1/responses). Billing is per token; see /models for each model's price.
For GPT models, when a single request's input (including cached tokens) exceeds 272K tokens, the whole request is billed at the long-context price: input and cache-read prices ×2, output ×1.5, the same rule as OpenAI's; each model's rate is in the >272K row under its price on /models. The status of old snapshots on this site follows /models.
Not ready for a monthly plan? Pay-as-you-go Packs start at $4 for a one-time quota you use within 7 days; if you already have a Personal Plan, add a booster pack when you need more quota.
Frequently asked questions
When are gpt-5 and o3 shut down?
On 2026-12-11. As of November 19, 2026, about 3 weeks remain: OpenAI's deprecations page still gives six rows the shutdown date Dec 11, 2026 — gpt-5-2025-08-07, o3-2025-04-16 and the matching snapshots of gpt-5-mini, gpt-5-nano, gpt-5-pro and o3-pro — with a notice date of 2026-06-11; the current replacements are gpt-5 and o3 → gpt-6.1-sol, gpt-5-mini → gpt-6.1-terra, gpt-5-nano → gpt-6-luna, and both pro rows → gpt-6.1-sol with reasoning.mode: pro. The 2026-10-08 record: the deprecations page gave those same six rows the shutdown date Dec 11, 2026 and the notice date 2026-06-11, with the gpt-5.6 family in the replacement column. By the official definition, the model is no longer accessible at shutdown.
My code only says gpt-5, without a date. Am I affected?
Treat it as affected. The 2026-10-26 table puts gpt-5 and gpt-5-2025-08-07 in the same cell; the row has one shutdown date, 2026-12-11, and one replacement. Whether the alias will later point at a newer model is not stated, so we suggest changing it before 2026-12-11.
What changes for gpt-5-pro and o3-pro?
At least two things: set model to gpt-5.6-sol and add reasoning.mode: pro. OpenAI says GPT-5.6 and GPT-6 models support standard and pro reasoning modes in the Responses API and that standard is the default, so swapping only the ID drops you to standard. gpt-5-pro and o3-pro were already Responses API only; gpt-5-pro only supports reasoning.effort: high, while gpt-5.6-sol defaults to medium, so set high explicitly if you need it.
What replaces gpt-5-mini and gpt-5-nano?
Per the current official table: gpt-5-mini-2025-08-07 → gpt-6.1-terra and gpt-5-nano-2025-08-07 → gpt-6-luna. When checked on 2026-10-26 the table read gpt-5-mini-2025-08-07 → gpt-5.6-terra and gpt-5-nano-2025-08-07 → gpt-5.6-luna, since superseded by gpt-6.1-terra and gpt-6-luna. On QCode, gpt-6.1-terra is available; gpt-6-luna and gpt-5.6-luna are not supported on QCode; use gpt-6.1-terra, gpt-6-sol or gpt-6.1-sol instead (our suggestion, not an official mapping). OpenAI's model pages say Terra roughly corresponds to the mini tier and Luna to the nano tier of earlier GPT-5 families.
What do Codex users need to change?
The model entry in config.toml and any model named after codex exec --model in scripts. OpenAI's wording: To specify a model, add a model entry to your configuration file. gpt-5-codex is not in this batch; the official table lists it as shut down on 2026-07-23, replaced by gpt-5.6-sol. With a custom provider, use a compatible Responses API endpoint; current Codex releases don't support a Chat Completions-only endpoint.
Can I call the official replacements on QCode?
Partly: as of November 19, 2026, QCode supports gpt-6.1-sol and gpt-6.1-terra, billed per token with prices on /models; gpt-6-luna and gpt-5.6-luna are not supported on QCode; use gpt-6.1-terra, gpt-6-sol or gpt-6.1-sol instead. The 2026-10-26 answer was: the official replacements then, gpt-5.6-sol and gpt-5.6-terra, were callable on QCode; gpt-5.6-luna was not supported then. Whether the old snapshots can still be called after the shutdown date is not promised here; /models is authoritative.
Sources
Shutdown dates and current replacements: OpenAI's official deprecations page https://developers.openai.com/api/docs/deprecations, re-fetched on 2026-11-19 (the 2026-06-11 section, the Dec 11, 2026 shutdown date, the Jun 11, 2026 notice date, and the gpt-6.1-sol / gpt-6.1-terra / gpt-6-luna replacement column), cross-checked against the same page as fetched on 2026-10-26. Official list prices: OpenAI's pricing page https://developers.openai.com/api/docs/pricing (gpt-6.2-sol and gpt-6.1-sol at $2.00 input / $10.00 output per million tokens), fetched 2026-11-19. Sources as of 2026-10-26: Shutdown dates, snapshot IDs and replacements: OpenAI's official deprecations page https://developers.openai.com/api/docs/deprecations (and its .md version), fetched 2026-10-26, using the 2026-06-11 section, the notice-period policy and the deprecation definition, cross-checked against the 2026-10-23, 2026-07-23 and 2027-04-01 sections of the same page. Model ID, Default snapshot, the snapshot definition, context and max input, supported reasoning.effort values and prices: OpenAI's model pages for gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro, o3, o3-pro and GPT-5.6 Sol / Terra / Luna plus the models overview, fetched the same day. reasoning.mode: OpenAI's reasoning models guide. Codex configuration: the Models and Config basics pages of OpenAI's Codex docs. QCode setup: the docs.qcode.cc page on endpoints and API paths (fetched 2026-10-26). Official dates such as Dec 11, 2026 are written in ISO format on this page.
Replace the six old snapshots before 2026-12-11
As of November 19, 2026, the current official replacements gpt-6.1-sol and gpt-6.1-terra are callable on QCode, billed per token, with prices on /models; on 2026-10-26 the official replacements were gpt-5.6-sol and gpt-5.6-terra. Whether an old snapshot stays callable follows /models.
Related reading
OpenAI legacy model retirement dates 2026
Replacements and fixes for the 2026-09-28 and 2026-10-23 batches.
AI API deprecations December 2026 to February 2027: the model shutdown calendar (2026-11)
Every announced OpenAI and Anthropic model shutdown by date: Opus 4.8 fast mode on 2026-11-30, three image models on 2026-12-01, gpt-5 and o3 on 2026-12-11, gpt-4o and gpt-4.1 on 2027-01-14, plus what Not sooner than really means.
GPT-6.1 Sol API guide
The model OpenAI's overview suggests for balancing intelligence and cost.
Crypto payment guide
Nine coins, 56 networks, zero platform fee for AI coding API credits.
Not affiliated with OpenAI. Dates, snapshot IDs and replacement mappings on this page are taken from OpenAI's official deprecations page and model pages fetched on 2026-10-26; the official pages prevail. Model availability is as listed on /models. This is not OpenAI's migration guide and makes no promise that any old ID stays available after its shutdown date.