# Image and video model shutdowns, October 2026: what broke and fixes

URL: https://infro.io/blog/image-video-model-shutdowns-october-2026
Author: INFRO Editorial (https://infro.io/blog/editorial)
Publisher: INFRO
Published: 2026-10-27
Last modified: 2026-10-27
Last reviewed: 2026-10-27 (next review due 2026-11-26)
Topic: Agents and multimodal systems
Format: Guide

> On 22 October 2026 the Gemini API stopped serving veo-3.1-generate-preview, veo-3.1-fast-generate-preview and veo-3.1-lite-generate-preview (Google recommends gemini-omni-1.1-flash); on 23 October OpenAI shut down gpt-image-1 (replacements gpt-image-2.5-sunburst or -flare) and Google shut down deep-research-pro-preview-12-2025. xAI serves grok-imagine-image-quality with grok-imagine-image-2.0 at low quality from 2 November, and gemini-3.1-flash-image is deprecated in favour of Nano Banana 2.1 with no date. Moving is not a rename: Omni Flash uses the Interactions API, takes only 16:9 or 9:16 and no negative prompt, and GPT Image 2.5 changes quality values and sizes.

Key takeaways:
- Gemini API: veo-3.1-generate-preview, -fast- and -lite- stopped on 22 October 2026; Google names gemini-omni-1.1-flash, or the GA models on its enterprise agent platform.
- OpenAI: gpt-image-1 shut down on 23 October; gpt-image-1.5, gpt-image-1-mini and chatgpt-image-latest follow on 1 December, all to gpt-image-2.5-sunburst or -flare.
- Veo to Omni Flash is a rewrite: Omni uses the Interactions API, accepts only 16:9 or 9:16, upscales for 1080p and 4K, and does not support negative prompts.
- xAI does not refuse grok-imagine-image-quality after 2 November; it serves the slug with grok-imagine-image-2.0 at low quality, so the change is silent unless you watch the output.
- Google's Deep Research Pro preview agent shut down on 23 October; change the agent parameter to deep-research-preview-04-2026 or the -max- variant.

Five image, video and research ids changed status in a single fortnight. The Gemini API stopped serving the three Veo 3.1 preview ids on 22 October 2026; OpenAI shut down `gpt-image-1` on 23 October; Google's Deep Research Pro preview agent shut down the same day; xAI serves `grok-imagine-image-quality` with a different model from 2 November; and Google deprecated Nano Banana 2 without a date[1][2][3]. A shut-down id fails; a retired-but-redirected id keeps answering with something else. This guide lists every id, the replacement each vendor names, the parameter changes that break working code, and a checklist for the move.

## What changed, id by id

| Id | Where | Date | What happens | Vendor's replacement |
| --- | --- | --- | --- | --- |
| `veo-3.1-generate-preview` | Gemini API | 22 Oct 2026 | Shut down | `gemini-omni-1.1-flash`[1] |
| `veo-3.1-fast-generate-preview` | Gemini API | 22 Oct 2026 | Shut down | `gemini-omni-1.1-flash`[1] |
| `veo-3.1-lite-generate-preview` | Gemini API | 22 Oct 2026 | Shut down | `gemini-omni-1.1-flash`[1] |
| `gemini-omni-flash-preview` | Gemini API | 22 Oct 2026 | Shut down | `gemini-omni-1.1-flash`[1] |
| `gpt-image-1` | OpenAI API | 23 Oct 2026 | Shut down | `gpt-image-2.5-sunburst` or `gpt-image-2.5-flare`[2] |
| `deep-research-pro-preview-12-2025` | Gemini API agent | 23 Oct 2026 | Shut down | `deep-research-preview-04-2026`[1] |
| `grok-imagine-image-quality` | xAI API | 2 Nov 2026 | Served by `grok-imagine-image-2.0` at quality `low` | None required; the slug keeps answering[3] |
| `gemini-3.1-flash-image` (Nano Banana 2) | Gemini API | No date | Deprecated | `gemini-nano-banana-2.1`[1] |
| `gpt-image-1.5`, `gpt-image-1-mini`, `chatgpt-image-latest` | OpenAI API | 1 Dec 2026 | Scheduled shutdown | `gpt-image-2.5-sunburst` or `gpt-image-2.5-flare`[2] |

Table: Image, video and research model changes, from each vendor's deprecation page or release notes, read 2026-10-27.

Three of these deserve a second look.

**Veo is gone from the Gemini API, not from Google.** The video generation page says the Veo 3.1 preview "was shut down on October 22, 2026" and tells you to migrate to Gemini Omni Flash "or the GA models available through the Gemini Enterprise Agent Platform"[4]. If you call Veo through Vertex AI or another platform, that platform's own dates apply.

**OpenAI's image retirement comes in two waves.** `gpt-image-1` is marked "Shut down" on its model page[5], and the 1.5 generation, the mini model and `chatgpt-image-latest` follow on 1 December with the same two replacements[2]. Doing the migration once, to 2.5, covers both dates.

**The xAI change is silent.** From 2 November, requests to `grok-imagine-image-quality` "will be served by grok-imagine-image-2.0 with quality set to low, with no change to the request or response shape and at a lower per-image price"[3]. Nothing fails. The image is made by a different model at a different quality, and a test that checks only for a 200 will pass.

## gpt-image-1 to GPT Image 2.5: what breaks

Both replacements are token-priced and share rates: $5 per million text input tokens, $8 per million image input tokens and $30 per million image output tokens, with image output at $15 under Batch[6][7]. OpenAI describes Sunburst as its most capable model "for workflows where editing precision matters most" and Flare as its "fastest model for high-quality, everyday image generation"[6][8].

| Setting | gpt-image-1 | GPT Image 2.5 Sunburst and Flare |
| --- | --- | --- |
| Quality values | `low`, `medium`, `high` (earlier GPT Image models go up to `high`) | `low`, `medium`, `high`, `xhigh`, `max`, `auto`; default `auto`[7] |
| Sizes | Priced at `1024x1024`, `1024x1536`, `1536x1024`[5] | Same three recommended, plus custom `WIDTHxHEIGHT` in multiples of 16, aspect between 1:3 and 3:1, edges up to 3840 px, 655,360 to 8,294,400 pixels; above `2560x1440` experimental[7] |
| Transparent background | Not covered on the pages read; test your current output | `background: "transparent"` with `png` or `webp`[7] |
| Price shape | Per-image prices published per quality and size[5] | Tokens; OpenAI notes the GPT Image 2 calculator does not estimate 2.5 token use[6] |

Table: Image request settings, from OpenAI's model pages and image generation guide.

What this means in code:

- **A hard-coded quality map still works**, because `low`, `medium` and `high` remain valid. But the default moved to `auto`, so a request that omitted `quality` may now be rendered at a different setting. Set it explicitly.
- **Cost per image is no longer a lookup.** OpenAI warns that "equal token rates don't mean equal cost per image: token consumption can differ by model and quality setting"[7]. Read `usage` on real requests before you update a per-image price in your product.
- **Input fidelity.** OpenAI's guide says that for `gpt-image-2` you should omit `input_fidelity`, because the model processes every image input at high fidelity[7]. If your `gpt-image-1` edit calls set it, test what the 2.5 models do with it before shipping.
- **Latency.** The guide still warns that complex prompts may take up to 2 minutes[7]; keep your timeouts generous on `xhigh` and `max`.

## Veo 3.1 preview to Gemini Omni Flash: what breaks

This one is a rewrite, not a rename.

- **A different API.** Omni Flash is called with `client.interactions.create` and `model: "gemini-omni-1.1-flash"`. The SDK exposes `interaction.output_video`; over REST the video arrives as base64 data inside the `steps` array, under a `model_output` step[9].
- **Two aspect ratios.** `aspect_ratio` takes `"16:9"` (the default) or `"9:16"`[9]. Anything else in your old requests has to change.
- **Resolution is a different control.** `resolution` in `response_format` takes `360p`, `720p` (default), `1080p` or `4k`, and the two highest are generated by upscaling[9].
- **No negative prompt.** Omni Flash does not support system instructions, temperature, `top_p`, stop sequences or negative prompts; Google suggests putting negatives in the regular prompt, such as "Do not do X"[9].
- **Extension and inputs have limits.** Videos extend by 10 seconds at a time up to 40 seconds; uploaded input videos for editing or extension must be 10 seconds or less; video references are limited to 3 clips of up to 3 seconds; editing or extending uploaded videos is not available in the EEA, Switzerland and the UK[9].
- **Billing by output tokens.** Video output is $17.50 per million tokens, calculated at 5,792 tokens per second of 720p video, which Google says is about $0.10 per second under Standard pricing[10].

Omni Flash also does things Veo did not: Google's release notes list extension, first-and-last-frame interpolation and resolution control at its GA on 27 August[11]. Treat the move as a new model to qualify, with your own prompts, not as a drop-in.

## Nano Banana and Deep Research

Nano Banana 2.1 (`gemini-nano-banana-2.1`) went GA on 6 October as an update to Nano Banana 2, adding wide and panoramic aspect ratios (1:4, 4:1, 1:8, 8:1) at 1K, 2K and 4K; the same note deprecated `gemini-3.1-flash-image` with no shutdown date[11]. Google lists $30 per million image output tokens, which it equates to $0.0336 per 1K image, $0.0504 per 2K and $0.113 per 4K[10]. There is no deadline yet, which is exactly when a migration is cheapest.

For Deep Research, the change is the `agent` parameter in `interactions.create`: from `deep-research-pro-preview-12-2025` to `deep-research-preview-04-2026`, which Google describes as designed for speed and streaming to a client, or `deep-research-max-preview-04-2026` for maximum comprehensiveness[11].

## A migration checklist

- [ ] **Find every caller from traffic first**, then code, configuration and stored settings. Search for the literal ids above, including in job payloads queued before the dates.
- [ ] **Pick the replacement per workload**, not per model: Sunburst for precise edits, Flare for volume; Omni Flash for video; Nano Banana 2.1 for Gemini images.
- [ ] **Rewrite the request**, not just the model string: quality values and the `auto` default, custom sizes, the Interactions API and its aspect ratios, negatives moved into the prompt.
- [ ] **Re-price on real requests.** Token-priced image and video models have no fixed per-image price; read `usage` from a sample of your own prompts.
- [ ] **Re-check output, not status codes.** Especially for `grok-imagine-image-quality`, where the same request returns a different model's image from 2 November.
- [ ] **Diary the next dates**: OpenAI's 1 December image shutdowns, and any shutdown date Google sets for Nano Banana 2.
- [ ] **Put the model behind a name you control**, so the next retirement is a configuration change.

## Refusing retired models by name with INFRO

INFRO is a control plane in front of the provider accounts you already hold; each provider bills you directly, and INFRO's charge is a software subscription.

Its model catalog records vendor retirements from the vendors' own deprecation pages, including `openai/gpt-image-1` (23 October) and `google/veo-3.1`, `-fast` and `-lite` (22 October, for Google's own API). Before a shutdown, `GET /v1/models` carries a `retirement` object and an organization that sent the model in the last 30 days gets a `model.retiring` alert naming the keys and projects that called it. From 00:00 UTC on the shutdown date, a request for the model is refused before any provider call with `404`, type `model_not_found`, code `model_shut_down`, and a body naming the `shutdown_date` and the vendor's `replacement`. INFRO never answers with a different model on your behalf. Where the retirement covers one provider only, as with Veo on the Gemini API, a request still goes to another of your connections that serves the model.

Two limits to state plainly. INFRO cannot refuse what the vendor keeps serving: `grok-imagine-image-quality` is not a shutdown, xAI answers it with another model, and INFRO's catalog has no retirement for it; [traffic changes](https://infro.io/docs/observability/traffic-changes) flag a connection that starts answering with a model id it had not reported before, which only helps if the provider reports the new id. And INFRO does not serve Google's Deep Research agents, so that change is yours to make directly. For code that should not change at the next retirement, call a [route](https://infro.io/docs/routes) under a name of your own and point its target at the replacement.

## Questions

### What replaces gpt-image-1?

OpenAI lists gpt-image-2.5-sunburst or gpt-image-2.5-flare. Sunburst is described as the most capable model where editing precision matters most; Flare as the fastest for high-quality everyday generation. Both add xhigh and max quality settings and custom sizes in multiples of 16. gpt-image-1 was shut down on 23 October 2026.

### What replaces Veo 3.1 preview on the Gemini API?

Google's deprecations page names gemini-omni-1.1-flash for veo-3.1-generate-preview, veo-3.1-fast-generate-preview and veo-3.1-lite-generate-preview, which the Gemini API shut down on 22 October 2026. The video generation page also points to the GA models on Google's enterprise agent platform. Vertex AI runs its own schedule.

### Is migrating from Veo to Gemini Omni Flash just a model name change?

No. Omni Flash is called through the Interactions API with interactions.create, returns the video in the interaction's output, accepts only 16:9 or 9:16 aspect ratios, offers 360p, 720p, 1080p and 4K (the last two upscaled), and does not support negative prompts, system instructions or temperature. Plan a code change and a quality review.

### What happens to grok-imagine-image-quality on 2 November?

xAI's release notes say requests to the slug will be served by grok-imagine-image-2.0 with quality set to low, with no change to the request or response shape and at a lower per-image price. The request keeps working, but a different model answers it. grok-imagine-image (1.0) is not affected.

### Is Nano Banana 2 shut down?

No date is set. Google deprecated gemini-3.1-flash-image on 6 October 2026, when Nano Banana 2.1 (gemini-nano-banana-2.1) went GA, and its deprecations page lists no shutdown date. Migrate on your schedule, but before Google announces one.

## Sources

1. Gemini deprecations — Google. https://ai.google.dev/gemini-api/docs/deprecations (accessed 2026-10-27)
2. Deprecations — OpenAI. https://developers.openai.com/api/docs/deprecations (accessed 2026-10-27)
3. Release notes — xAI. https://docs.x.ai/developers/release-notes (accessed 2026-10-27)
4. Video generation in the Gemini API — Google. https://ai.google.dev/gemini-api/docs/video (accessed 2026-10-27)
5. GPT Image 1 model page — OpenAI. https://developers.openai.com/api/docs/models/gpt-image-1 (accessed 2026-10-27)
6. GPT-Image-2.5 Sunburst model page — OpenAI. https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst (accessed 2026-10-27)
7. Image generation — OpenAI. https://developers.openai.com/api/docs/guides/image-generation (accessed 2026-10-27)
8. GPT Image 2.5 Flare model page — OpenAI. https://developers.openai.com/api/docs/models/gpt-image-2.5-flare (accessed 2026-10-27)
9. Generate and edit videos with Gemini Omni Flash — Google. https://ai.google.dev/gemini-api/docs/omni (accessed 2026-10-27)
10. Gemini Developer API pricing — Google. https://ai.google.dev/gemini-api/docs/pricing (accessed 2026-10-27)
11. Release notes — Google. https://ai.google.dev/gemini-api/docs/changelog (accessed 2026-10-27)