For mobile and web apps, the Firebase AI Logic SDKs let you interact
with the supported **Gemini models** directly from your app.

Gemini models are considered *multimodal* because they're capable of
processing and even generating multiple modalities, including text, code, PDFs,
images, video, and audio.

Also, review our [FAQ](https://firebase.google.com/docs/ai-logic/faq-and-troubleshooting.md.txt#supported-models)
about all the models that Firebase AI Logic supports and does not support.

## Featured models

These featured models are cost-effective, low-latency models that are ideal for
in-app client tasks.
FAST AND INTELLIGENT

### Gemini 3.8 Flash

`gemini-3.8-flash`


Frontier-class performance model that rivals larger models at a
fraction of the cost.
*(billing **not** required)*
ULTRA FAST

### Gemini 3.5 Flash-Lite

`gemini-3.5-flash-lite`


High-volume, cost-sensitive workhorse model with the performance and
quality of the Gemini 3 series.
*(billing **not** required)*
IMAGE GENERATION

### Gemini Nano Banana 2.1

`gemini-nano-banana-2.1`

Fast, cost-efficient workhorse model for high-quality image
generation and conversational editing.
*(billing required)*

## General-use models

The general-use Gemini models let you generate text, structured JSON,
and code from multimodal input (including text, images, PDFs, video, and audio).

[Go to tables with model details](https://firebase.google.com/docs/ai-logic/models.md.txt#compare-models)

### Gemini 4 Carbon

`gemini-4-carbon`


Strongest reasoning model, built for complex software
engineering, multimodal knowledge work, scientific reasoning, and
cybersecurity defense.
*(billing required)*

### Gemini 4 Argon

`gemini-4-argon`


Advanced reasoning model with rich multimodal understanding to
handle complex coding, agentic, math, and science tasks.
*(billing required)*

### Gemini 3.8 Flash

`gemini-3.8-flash`


Frontier-class performance model that rivals larger models at a
fraction of the cost.
*(billing **not** required)*

### Gemini 3.5 Flash-Lite

`gemini-3.5-flash-lite`


High-volume, cost-sensitive workhorse model with the performance and
quality of the Gemini 3 series.
*(billing **not** required)*

## Image-generating models (Nano Banana)

The Gemini Nano Banana models let you generate and edit images from
text, image, or video input.

[Go to tables with model details](https://firebase.google.com/docs/ai-logic/models.md.txt#compare-models)

### Gemini Nano Banana 2.1

`gemini-nano-banana-2.1`

Primary workhorse model for image generation and conversational
editing. Fast and cost-efficient, with improved visual quality,
text rendering, and multi-turn consistency.
*(billing required)*

### Gemini Nano Banana 2

`gemini-3.1-flash-image`

High-efficiency model optimized for fast, reliable image
generation across production workloads.
*(billing required)*

### Gemini Nano Banana 2 Lite

`gemini-3.1-flash-lite-image`

Ultra-low latency and cost-effective model, designed for
high-volume, real-time interactive use cases.
*(billing required)*

### Gemini Nano Banana Pro

`gemini-3-pro-image`

State-of-the-art model for complex image prompts, structured
output, and maximum visual fidelity.
*(billing required)*

## Audio-generating models

### Text-to-speech (TTS) models

The Gemini TTS models let you generate controlled speech from text
input.

[Go to tables with model details](https://firebase.google.com/docs/ai-logic/models.md.txt#compare-models)

### Gemini 3.x Flash TTS

`gemini-3.1-flash-tts-preview`

Powerful, low-latency speech generation from text input.
*(billing **not** required)*

### Live API models

The Gemini Live API models let generate real-time *bidirectional streamed*
audio.

[Go to tables with model details](https://firebase.google.com/docs/ai-logic/models.md.txt#compare-models)

### Gemini 3.x Flash with Gemini Live API native audio

Gemini Developer API:  
`gemini-3.1-flash-live-preview`

Agent Platform Gemini API:  
*not supported*

Enables low-latency, real-time voice and video interactions with a
Gemini model that is *bidirectional* .
*(billing **not** required)*

### Gemini 2.5 Flash with Gemini Live API native audio

Gemini Developer API:  
`gemini-2.5-flash-native-audio-preview-12-2025`

Agent Platform Gemini API:  
`gemini-live-2.5-flash-native-audio`

Enables low-latency, real-time voice and video interactions with a
Gemini model that is *bidirectional* .
*(billing **not** required)*

<br />

**The remainder of this page provides detailed information about the models
supported by Firebase AI Logic.**

- [Compare models](https://firebase.google.com/docs/ai-logic/models.md.txt#compare-models):

  - Supported input and output
  - High-level comparison of the supported capabilities
  - Specifications and limitations, for example max input tokens or max length of input video
- Description of [how models are versioned](https://firebase.google.com/docs/ai-logic/models.md.txt#versions), specifically their
  *stable* , *preview* , and *experimental* versions

- Lists of [available model names](https://firebase.google.com/docs/ai-logic/models.md.txt#available-model-names) to include in your
  code during initialization

- Lists of [supported languages](https://firebase.google.com/docs/ai-logic/models.md.txt#languages) for the models

At the bottom of this page, you can
[view detailed information about previous generation models](https://firebase.google.com/docs/ai-logic/models.md.txt#older-models).

<br />

*** ** * ** ***

## Compare models

Each model has different capabilities to support various use cases. Note that
each of tables in this section describe each model
*when used with Firebase AI Logic*. Each model might have additional
capabilities that aren't available when using our SDKs.

If you can't find the information you're looking for in the following
sub-sections, you can find even more information in your chosen API provider
documentation:
[Gemini Developer API](https://ai.google.dev/gemini-api/docs/models)
or
[Agent Platform Gemini API (formerly Vertex AI)](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/google-models).

> [!NOTE]
> **Note:** We recommend reviewing details about [the location for where you access a model](https://firebase.google.com/docs/ai-logic/locations.md.txt?api=vertex). The Gemini Developer API provides only global access to models, but the Agent Platform Gemini API (formerly Vertex AI) provides both global access (recommended for most use cases) and setting a specific location (available locations depend on the model).

### Supported input and output

The following table lists the supported input and output types
*when using each model with Firebase AI Logic*.

To learn about supported file types, see
[Supported input files and requirements](https://firebase.google.com/docs/ai-logic/input-file-requirements.md.txt).

|   | Gemini 4 Carbon, Argon | Gemini 3.x Flash, Flash‑Lite | Gemini Nano Banana 2, 2.1 | Gemini Nano Banana 2 Lite | Gemini Nano Banana Pro | Gemini 3.x Flash TTS | Gemini Live |
|---|---|---|---|---|---|---|---|
| **Input types** ||||||||
| Text | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
| Code | Yes | Yes | Yes | Yes | Yes | No | No |
| Documents (PDFs or plain-text) | Yes | Yes | Yes | Yes | Yes | No | No |
| Images | Yes | Yes | Yes | Yes | Yes | No | Yes |
| Video | Yes | Yes | Yes | Yes | No | No | Yes |
| Audio | Yes | Yes | No | No | No | No | Yes |
| **Output types** ||||||||
| Text | Yes | Yes | Yes | Yes | Yes | No | Yes |
| Text (streaming) | Yes | Yes | No | No | No | No | Yes |
| Code | Yes | Yes | Yes | Yes | Yes | No | No |
| Structured output (like JSON) | Yes | Yes | No | No | No | No | No |
| Images | No | No | Yes | Yes | Yes | No | No |
| Video | No | No | No | No | No | No | No |
| Audio | No | No | No | No | No | Yes | Yes |

### Supported capabilities and features

The following table lists the supported capabilities and features
*when using each model with Firebase AI Logic*.

|   | Gemini 4 Carbon, Argon | Gemini 3.x Flash, Flash‑Lite | Gemini Nano Banana 2, 2.1 | Gemini Nano Banana 2 Lite | Gemini Nano Banana Pro | Gemini 3.x Flash TTS | Gemini Live |
|---|---|---|---|---|---|---|---|
| [Thinking](https://firebase.google.com/docs/ai-logic/thinking.md.txt) | Yes | Yes | Yes | Yes | Yes | No | Yes |
| [Generate text](https://firebase.google.com/docs/ai-logic/generate-text.md.txt) from text-only or multimodal inputs | Yes | Yes | [*interleaved or as part of image*](https://firebase.google.com/docs/ai-logic/generate-images-gemini.md.txt) | [*interleaved or as part of image*](https://firebase.google.com/docs/ai-logic/generate-images-gemini.md.txt) | [*interleaved or as part of image*](https://firebase.google.com/docs/ai-logic/generate-images-gemini.md.txt) | No | [*transcription of audio*](https://firebase.google.com/docs/ai-logic/live-api/capabilities.md.txt#text-in-audio-out) |
| [Generate images](https://firebase.google.com/docs/ai-logic/generate-images-gemini.md.txt) | No | No | Yes | Yes | Yes | No | No |
| [Edit images](https://firebase.google.com/docs/ai-logic/generate-images-gemini.md.txt) | No | No | Yes | Yes | Yes | No | No |
| Generate audio | No | No | No | No | No | [*speech*](https://firebase.google.com/docs/ai-logic/generate-speech.md.txt) | [*streamed audio*](https://firebase.google.com/docs/ai-logic/live-api/capabilities.md.txt#input-modalities) |
| [Generate structured output](https://firebase.google.com/docs/ai-logic/generate-structured-output.md.txt) (like JSON) | Yes | Yes | No | No | No | No | No |
| Analyze documents (PDFs or plain-text) ([text-output](https://firebase.google.com/docs/ai-logic/analyze-documents.md.txt) \| [image-output](https://firebase.google.com/docs/ai-logic/generate-images-gemini.md.txt)) | Yes | Yes | Yes | Yes | Yes | No | No |
| Analyze images ([text-output](https://firebase.google.com/docs/ai-logic/analyze-images.md.txt) \| [image-output](https://firebase.google.com/docs/ai-logic/generate-images-gemini.md.txt)) | Yes | Yes | Yes | Yes | Yes | No | No |
| Analyze video ([text-output](https://firebase.google.com/docs/ai-logic/analyze-videos) \| [image-output](https://firebase.google.com/docs/ai-logic/generate-images-gemini.md.txt)) | Yes | Yes | Yes | Yes | No | No | [*streamed video*](https://firebase.google.com/docs/ai-logic/live-api/capabilities.md.txt#input-modalities) |
| [Analyze audio](https://firebase.google.com/docs/ai-logic/analyze-audio.md.txt) | Yes | Yes | No | No | No | No | [*streamed audio*](https://firebase.google.com/docs/ai-logic/live-api/capabilities.md.txt#input-modalities) |
| [Multi-turn chat](https://firebase.google.com/docs/ai-logic/chat.md.txt) | Yes | Yes | Yes | Yes | Yes | No | No |
| [Bidirectional multimodal streaming](https://firebase.google.com/docs/ai-logic/live-api.md.txt) | No | No | No | No | No | No | Yes |
| **Supported tools** ||||||||
| [Function calling](https://firebase.google.com/docs/ai-logic/function-calling.md.txt) | Yes | Yes | No | No | No | No | Yes |
| [Code execution](https://firebase.google.com/docs/ai-logic/code-execution.md.txt) | Yes | Yes | No | No | No | No | No |
| [URL context](https://firebase.google.com/docs/ai-logic/url-context.md.txt) | Yes | Yes | No | No | No | No | No |
| [Grounding with Google Search](https://firebase.google.com/docs/ai-logic/grounding-google-search.md.txt) | Yes | Yes | Yes | No | Yes | No | Yes |
| [Grounding with Google Maps](https://firebase.google.com/docs/ai-logic/grounding-google-maps.md.txt) | Yes | Yes | No | No | No | No | No |

> [!NOTE]
> **Note:** *When using Firebase AI Logic* , the following capabilities are ***not*** supported: grounding with Google Image Search, fine tuning a model, embeddings generation, and semantic retrieval.

### Specifications and limitations

The following table lists the specifications and limitations
*when using each model with Firebase AI Logic*.

| Property | Gemini 4 Carbon, Argon | Gemini 3.x Flash, Flash‑Lite | Gemini Nano Banana 2, 2.1 | Gemini Nano Banana 2 Lite | Gemini Nano Banana Pro | Gemini 3.x Flash TTS | Gemini Live |
|---|---|---|---|---|---|---|---|
| Input token limit **\*** | 1,048,576 tokens | 1,048,576 tokens | 131,072 tokens | 65,536 tokens | 65,536 tokens | 8,192 tokens | [*see docs*](https://firebase.google.com/docs/ai-logic/live-api/limits-and-specs.md.txt) |
| Output token limit **\*** | 32,768 tokens (non‑streaming) 65,536 tokens (streaming) **\*\*** | 65,536 tokens | 32,768 tokens | 4,096 tokens | 32,768 tokens | 16,384 tokens | [*see docs*](https://firebase.google.com/docs/ai-logic/live-api/limits-and-specs.md.txt) |
| **PDFs (per request)** ||||||||
| Max number of input PDF files **\*\*\*** | 900 files | 900 files | 14 files | 14 files | 14 files | --- | [*see docs*](https://firebase.google.com/docs/ai-logic/live-api/limits-and-specs.md.txt) |
| Max number of pages per input PDF file **\*\*\*** | 900 pages | 900 pages | 14 pages | 14 pages | 14 pages | --- | [*see docs*](https://firebase.google.com/docs/ai-logic/live-api/limits-and-specs.md.txt) |
| Max size per input PDF file | 50 MB | 50 MB | 50 MB | 50 MB | 50 MB | --- | [*see docs*](https://firebase.google.com/docs/ai-logic/live-api/limits-and-specs.md.txt) |
| **Images (per request)** ||||||||
| Max number of *input* images | 1,000 images | 1,000 images | 14 images | 14 images | 14 images | --- | [*see docs*](https://firebase.google.com/docs/ai-logic/live-api/limits-and-specs.md.txt) |
| Max size per input base64-encoded image | 7 MB | 7 MB | 7 MB | 7 MB | 7 MB | --- | [*see docs*](https://firebase.google.com/docs/ai-logic/live-api/limits-and-specs.md.txt) |
| Max number of *output* images | --- | --- | Up to output token limit | Up to output token limit | Up to output token limit | --- | [*see docs*](https://firebase.google.com/docs/ai-logic/live-api/limits-and-specs.md.txt) |
| **Video (per request)** ||||||||
| Max number of input video files | 10 files | 10 files | Up to input token limit | Up to input token limit | --- | --- | [*see docs*](https://firebase.google.com/docs/ai-logic/live-api/limits-and-specs.md.txt) |
| Max length of all input video (frames only) | \~60 minutes | \~60 minutes | \~25 minutes | \~12 minutes | --- | --- | [*see docs*](https://firebase.google.com/docs/ai-logic/live-api/limits-and-specs.md.txt) |
| Max length of all input video (frames+audio) | \~45 minutes | \~45 minutes | --- | --- | --- | --- | [*see docs*](https://firebase.google.com/docs/ai-logic/live-api/limits-and-specs.md.txt) |
| **Audio (per request)** ||||||||
| Max number of input audio files | 1 file | 1 file | --- | --- | --- | --- | [*see docs*](https://firebase.google.com/docs/ai-logic/live-api/limits-and-specs.md.txt) |
| Max length of all input audio | \~8.4 hours | \~8.4 hours | --- | --- | --- | --- | [*see docs*](https://firebase.google.com/docs/ai-logic/live-api/limits-and-specs.md.txt) |


^\*
*For all Gemini models, a token is equivalent to about 4 characters,
so 100 tokens are about 60-80 English words. For Gemini models, you can
determine the total count of tokens in your requests using
[`countTokens`](https://firebase.google.com/docs/ai-logic/count-tokens.md.txt).*^


^\*\*
*For `gemini-4-carbon` and `gemini-4-argon`,
Firebase AI Logic does not yet support long decode.*^


^\*\*\*
*PDFs are treated as images, so a single page of a PDF is treated as
one image. The number of pages allowed in a request is limited to the number
of images the model can support.*^

#### Find additional detailed information

- [Quotas](https://firebase.google.com/docs/ai-logic/quotas.md.txt) and [pricing](https://firebase.google.com/docs/ai-logic/pricing.md.txt) are
  different for each model. Pricing also depends on input and output.

- Learn about supported input file types, how to specify MIME type, and how to
  make sure that your input files and multimodal requests meet the requirements
  and follow best practices in
  [Supported input files and requirements](https://firebase.google.com/docs/ai-logic/input-file-requirements.md.txt).


  > [!NOTE]
  > **Important** : **The total request size limit is
  > 20 MB.** To send large files, review the [options for providing files in multimodal requests](https://firebase.google.com/docs/ai-logic/input-file-requirements.md.txt).

  <br />

<br />

*** ** * ** ***

## Model versioning and naming patterns

Models are offered in *stable* , *preview* , and *experimental* versions. For
convenience, the `-latest` aliases are supported, but
they're not recommended due to the inconsistency in which model version they
point to.

**Make sure to review our
[best practices for using model versions](https://firebase.google.com/docs/ai-logic/models.md.txt#versions-best-practices).**

To find specific model names to use in your code, see the
["available model names"](https://firebase.google.com/docs/ai-logic/models.md.txt#available-model-names) section later on this page.

| Version type / Release stage || Description | Model name pattern |
|---|---|---|---|
| **Stable** || ***Stable*** versions are available and supported for production use starting on the release date. - A stable model version is typically released with a retirement date, which indicates the last day that the model is available. After this date, the model is no longer accessible or supported by Google. - Most stable models are available for 12 months after their release date (even if a replacement model is released). - For the Agent Platform Gemini API (formerly Vertex AI), some stable models only have [*short-term availability*](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/model-versions#short-term-availability), which means that they may be shut down (retired) as early as 45 days after a replacement model is released. | Model names of stable versions have no suffix Examples: `gemini-4-argon` `gemini-3.8-flash` |
| **Preview** || ***Preview*** versions have new capabilities and are considered *not stable* . - These models are *not* recommended for production use, come with more restrictive rate limits, and may have billing requirements. - These models are shut down (retired) within a few weeks or months after their associated stable version is released. - For the Agent Platform Gemini API (formerly Vertex AI), preview models are *only* available in the [`global` location](https://firebase.google.com/docs/ai-logic/locations.md.txt?api=vertex). | Model names of preview versions are appended with `-preview` Example: `gemini-3-pro-preview` |
| **Experimental** || ***Experimental*** versions have new capabilities and are considered *not stable* . - These models are *not* recommended for production use and come with more restrictive rate limits. Experimental models are intended for gathering feedback and to enable experimentation with our latest features. - These models are shut down (retired) within a few weeks or months after their associated stable version is released. - For the Agent Platform Gemini API (formerly Vertex AI), experimental models are *only* available in the [`global` location](https://firebase.google.com/docs/ai-logic/locations.md.txt?api=vertex). | Model names of experimental versions are appended with `-exp` along with the model's release date (`-MM-DD`) Example: `gemini-2.5-pro-exp-03-25` (released on March 25, 2025) |
| **Shutdown (retired)** || ***Shutdown (retired)*** versions are past their shutdown (retirement) date and have been permanently deactivated. - Shutdown (retired) models are no longer accessible or supported by Google, and a request using a retired model name returns a 404 error. | --- |

### Best practices for using model versions

- **In your *production apps* , use the explicit model name for the most recent
  *stable* version.**

  For Agent Platform Gemini API (formerly Vertex AI), if you choose to use a
  *short-term availability model* in your production app, it's even more
  critical that you use
  [Firebase Remote Config](https://firebase.google.com/docs/ai-logic/change-model-name-remotely.md.txt) or
  [server prompt templates](https://firebase.google.com/docs/ai-logic/server-prompt-templates/get-started.md.txt)
  to control the model name used for your AI feature.
- **Use *preview* and *experimental* versions *only during prototyping*** . We
  recommend using a *stable* version when you start developing and testing for
  a production use case.

- We do *not* recommend using the `-latest` aliases
  (even during development). This alias points to the latest release for a
  specific model variation (which could be a stable, preview, or experimental
  version). This alias will get hot-swapped with every new release of a specific
  model variation, and only for breaking changes will a 2-week-prior
  notification email be sent. This instability of which model you're actually
  using can lead to unexpected behavior changes for your AI feature.

> [!CAUTION]
> **We *strongly* recommend using
> [Firebase Remote Config](https://firebase.google.com/docs/ai-logic/change-model-name-remotely.md.txt)
> or
> [server prompt templates](https://firebase.google.com/docs/ai-logic/server-prompt-templates/get-started.md.txt)
> so that you can make on-demand changes to the model name used for your AI
> feature without releasing a new version of your app.**

<br />

*** ** * ** ***

## Available model names

Model names are the explicit values that you include *in your code* during
initialization of the model.

- [**General-use models**](https://firebase.google.com/docs/ai-logic/models.md.txt#model-names-general-use)
  (like `gemini-4-argon` or `gemini-3.8-flash`)

- [**Image-generating (Nano Banana) models**](https://firebase.google.com/docs/ai-logic/models.md.txt#model-names-image-generating)
  (like `gemini-nano-banana-2.1`)

- **Audio-generating models**:

  - [Text-to-speech (TTS) models](https://firebase.google.com/docs/ai-logic/models.md.txt#model-names-audio-generating-tts) (like `gemini-3.1-flash-tts-preview`)
  - [Live API models](https://firebase.google.com/docs/ai-logic/models.md.txt#model-names-audio-generating-live) (like `gemini-live-2.5-flash-native-audio`)

For initialization examples for your platform, see the
[getting started guide](https://firebase.google.com/docs/ai-logic/get-started.md.txt).

For details about the release stages (especially for use cases, billing, and
shutdown), see
[model versioning and naming patterns](https://firebase.google.com/docs/ai-logic/models.md.txt#versions).

> [!IMPORTANT]
> **Important:** This section includes any announced shutdown dates (and re-routing information as applicable) for the most recent models. You can find shutdown dates and information about even older models in the [deprecated and shutdown models FAQ](https://firebase.google.com/docs/ai-logic/faq-and-troubleshooting.md.txt#shutdown-models-list).   
>
> Be aware that several weeks before the shutdown date, projects that have no prior usage of a model will be blocked from starting to use it.

#### Programmatically list all available models

You can list all available models names using the REST API:

- Gemini Developer API: Call the
  [`models.list` endpoint](https://ai.google.dev/api/models#method:-models.list)

- Agent Platform Gemini API (formerly Vertex AI): Call the
  [`publishers.models.list` endpoint](https://docs.cloud.google.com/gemini-enterprise-agent-platform/reference/rest/v1beta1/publishers.models/list)

Note that this returned list will include *all* models supported by the
Gemini API providers, but Firebase AI Logic only supports the
Gemini models described on this page.

### General-use models

| **Model** | **Gemini Developer API** | **Agent Platform Gemini API** |
|---|---|---|
| `gemini-4-carbon` ^1, 2^ <br /> Release date: November 10, 2026 Release stage: Stable | Shutdown date: --- | Shutdown date: --- |
| `gemini-4-argon` ^1^ <br /> Release date: October 13, 2026 Release stage: Stable | Shutdown date: --- | Shutdown date: --- |

| **Model** | **Gemini Developer API** | **Agent Platform Gemini API** |
|---|---|---|
| `gemini-3.8-flash` <br /> Release date: September 2, 2026 Release stage: Stable | Shutdown date: --- | Shutdown date: --- |
| `gemini-3.7-flash` ^2^ <br /> Release date: August 13, 2026 Release stage: Stable | Requests routed to `gemini-3.8-flash` Replacement: `gemini-3.8-flash` | Shutdown date: January 28, 2027 Replacement: `gemini-3.8-flash` |
| `gemini-3.6-flash` ^2^ <br /> Release date: July 21, 2026 Release stage: Stable | Shutdown date: --- Replacement: `gemini-3.8-flash` | Shutdown date: November 19, 2026 Replacement: `gemini-3.8-flash` |
| `gemini-3.5-flash` <br /> Release date: May 19, 2026 Release stage: Stable | Requests routed to `gemini-3.6-flash` Replacement: `gemini-3.8-flash` | Shutdown date: --- Replacement: `gemini-3.8-flash` |
| `gemini-3.5-flash-lite` <br /> Release date: July 21, 2026 Release stage: Stable | Shutdown date: --- | Shutdown date: --- |
| `gemini-3.1-flash-lite` <br /> Release date: May 7, 2026 Release stage: Stable | Shutdown date: --- Replacement: `gemini-3.5-flash-lite` | Shutdown date: --- Replacement: `gemini-3.5-flash-lite` |
| `gemini-3.1-pro-preview` <br /> Release date: February 19, 2026 Release stage: Preview | Shutdown date: --- Replacement: `gemini-4-argon` | Shutdown date: --- Replacement: `gemini-4-argon` |

| **Model** | **Gemini Developer API** | **Agent Platform Gemini API** |
|---|---|---|
| `gemini-2.5-pro` <br /> Release date: June 17, 2025 Release stage: Stable | Requests routed to `gemini-3.8-flash` *(starting December 1, 2026)* Replacement: `gemini-3.8-flash` | Shutdown date: October 20, 2026 Replacement: `gemini-3.8-flash` |
| `gemini-2.5-flash` <br /> Release date: June 17, 2025 Release stage: Stable | Requests routed to `gemini-3.5-flash-lite` *(starting December 1, 2026)* Replacement: `gemini-3.5-flash-lite` | Shutdown date: October 20, 2026 Replacement: `gemini-3.5-flash-lite` |
| `gemini-2.5-flash-lite` <br /> Release date: July 22, 2025 Release stage: Stable | Shutdown date: --- Replacement: `gemini-3.5-flash-lite` | Shutdown date: October 20, 2026 Replacement: `gemini-3.5-flash-lite` |

^**1** *Requires the [pay-as-you-go Blaze pricing plan](https://firebase.google.com/pricing.md.txt) regardless of your
Gemini API provider.*^

^**2** *For the Agent Platform Gemini API (formerly Vertex AI), this is a
"short-term availability model". See
[Model versioning and naming patterns](https://firebase.google.com/docs/ai-logic/models.md.txt#versions)*^

^Very old general-use models that are shutdown:
`gemini-1.0-pro`,
`gemini-1.0-pro-001`,
`gemini-1.0-pro-002`,
`gemini-1.0-pro-vision`,
`gemini-1.0-pro-vision-001`
`gemini-1.5-flash-001`,
`gemini-1.5-flash`,
`gemini-1.5-flash-002`,
`gemini-1.5-pro-001`,
`gemini-1.5-pro`,
`gemini-1.5-pro-002`,
`gemini-2.0-flash-lite`,
`gemini-2.0-flash-lite-001`,
`gemini-2.0-flash`,
`gemini-2.0-flash-001`^

### Image-generating (Nano Banana) models

| **Model** | **Gemini Developer API** | **Agent Platform Gemini API** |
|---|---|---|
| `gemini-nano-banana-2.1` ^1, 2^ <br /> Release date: October 6, 2026 Release stage: Stable | Shutdown date: --- | Shutdown date: --- |
| `gemini-3.1-flash-image` ^1^ <br /> Release date: May 28, 2026 Release stage: Stable | Shutdown date: --- | Shutdown date: --- |
| `gemini-3.1-flash-lite-image` ^1^ <br /> Release date: June 30, 2026 Release stage: Stable | Shutdown date: --- | Shutdown date: --- |
| `gemini-3-pro-image` ^1^ <br /> Release date: May 28, 2026 Release stage: Stable | Shutdown date: --- | Shutdown date: --- |

^**1** *Requires the [pay-as-you-go Blaze pricing plan](https://firebase.google.com/pricing.md.txt) regardless of your
Gemini API provider.*^

^**2** *For the Agent Platform Gemini API (formerly Vertex AI), this is a
"short-term availability model". See
[Model versioning and naming patterns](https://firebase.google.com/docs/ai-logic/models.md.txt#versions)*^

^Very old image-generating models that are shutdown:
`gemini-2.5-flash-image`,
`imagen-3.0-fast-generate-001`,
`imagen-3.0-generate-001`,
`imagen-3.0-generate-002`,
`imagen-3.0-capability-001`,
`imagen-4.0-ultra-generate-001`,
`imagen-4.0-fast-generate-001`,
`imagen-4.0-generate-001`^

### Audio - text-to-speech (TTS) models

| **Model** | **Gemini Developer API** | **Agent Platform Gemini API** |
|---|---|---|
| `gemini-3.1-flash-tts-preview` <br /> Release date: June 17, 2026 Release stage: Preview | Shutdown date: --- | Shutdown date: --- |

### Audio - Live API models

| **Model** | **Gemini Developer API** | **Agent Platform Gemini API** |
|---|---|---|
| `gemini-3.1-flash-live-preview` <br /> Release date: March 26, 2026 Release stage: Preview | Shutdown date: --- | *Not supported* |
| `gemini-live-2.5-flash-native-audio` <br /> Release date: December 12, 2025 Release stage: Stable | *Not supported* | Shutdown date: --- |
| `gemini-2.5-flash-native-audio-preview-12-2025` <br /> Release date: December 12, 2025 Release stage: Preview | Shutdown date: --- Replacement: `gemini-3.1-flash-live-preview` | *Not supported* |
| `gemini-live-2.5-flash-preview-native-audio-09-2025` <br /> Release date: September 18, 2025 Release stage: Preview | *Not supported* | Shutdown date: --- Replacement: `gemini-live-2.5-flash-native-audio` |
| `gemini-2.5-flash-native-audio-preview-09-2025` <br /> Release date: September 18, 2025 Release stage: Preview | Shutdown date: --- Replacement: `gemini-3.1-flash-live-preview` | *Not supported* |

^Very old Live API models that are shutdown:
`gemini-2.0-flash-live-preview-04-09`,
`gemini-2.0-flash-live-001`,
`gemini-live-2.5-flash-preview`^

<br />

*** ** * ** ***

## Supported languages

> [!NOTE]
> **Note:** These languages *do not represent the locations for accessing the model* ; instead, these are the *languages* that the models can understand and respond in (for example, the text input and output). If needed, see [specify the location for accessing a model](https://firebase.google.com/docs/ai-logic/locations.md.txt?api=vertex).

### General-use models

All Gemini general-use models (like Gemini 4 Carbon, Gemini 4 Argon,
Gemini 3.8 Flash, Gemini 3.5 Flash-Lite, and earlier 3.x models)
can understand and respond in over 100 languages:

Afrikaans (`af`), Albanian (`sq`), Amharic (`am`), Arabic (`ar`),
Armenian (`hy`), Assamese (`as`), Azerbaijani (`az`), Basque (`eu`),
Belarusian (`be`), Bengali (`bn`), Bosnian (`bs`), Bulgarian (`bg`),
Catalan (`ca`), Cebuano (`ceb`), Chinese simplified and traditional (`zh`),
Corsican (`co`), Croatian (`hr`), Czech (`cs`), Danish (`da`), Dhivehi (`dv`),
Dutch (`nl`), English (`en`), Esperanto (`eo`), Estonian (`et`),
Filipino (Tagalog) (`fil`), Finnish (`fi`), French (`fr`), Frisian (`fy`),
Galician (`gl`), Georgian (`ka`), German (`de`), Greek (`el`), Gujarati (`gu`),
Haitian Creole (`ht`), Hausa (`ha`), Hawaiian (`haw`), Hebrew (`iw`),
Hindi (`hi`), Hmong (`hmn`), Hungarian (`hu`), Icelandic (`is`), Igbo (`ig`),
Indonesian (`id`), Irish (`ga`), Italian (`it`), Japanese (`ja`),
Javanese (`jv`), Kannada (`kn`), Kazakh (`kk`), Khmer (`km`), Korean (`ko`),
Krio (`kri`), Kurdish (`ku`), Kyrgyz (`ky`), Lao (`lo`), Latin (`la`),
Latvian (`lv`), Lithuanian (`lt`), Luxembourgish (`lb`), Macedonian (`mk`),
Malagasy (`mg`), Malay (`ms`), Malayalam (`ml`), Maltese (`mt`), Maori (`mi`),
Marathi (`mr`), Meiteilon (Manipuri) (`mni-Mtei`), Mongolian (`mn`),
Myanmar (Burmese) (`my`), Nepali (`ne`), Norwegian (`no`),
Nyanja (Chichewa) (`ny`), Odia (Oriya) (`or`), Pashto (`ps`), Persian (`fa`),
Polish (`pl`), Portuguese (`pt`), Punjabi (`pa`), Romanian (`ro`),
Russian (`ru`), Samoan (`sm`), Scots Gaelic (`gd`), Serbian (`sr`),
Sesotho (`st`), Shona (`sn`), Sindhi (`sd`), Sinhala (Sinhalese) (`si`),
Slovak (`sk`), Slovenian (`sl`), Somali (`so`), Spanish (`es`),
Sundanese (`su`), Swahili (`sw`), Swedish (`sv`), Tajik (`tg`), Tamil (`ta`),
Telugu (`te`), Thai (`th`), Turkish (`tr`), Ukrainian (`uk`), Urdu (`ur`),
Uyghur (`ug`), Uzbek (`uz`), Vietnamese (`vi`), Welsh (`cy`), Xhosa (`xh`),
Yiddish (`yi`), Yoruba (`yo`), and Zulu (`zu`).

### Image-generating models (Nano Banana)

The Gemini Nano Banana models can accept text prompts across many
languages. However, they are optimized for best performance (both for text
prompts and for rendering text within generated images) in the following
languages and locales:

Arabic (`ar-EG`), German (`de-DE`), English (`EN`), Spanish (`es-MX`),
French (`fr-FR`), Hindi (`hi-IN`), Indonesian (`id-ID`), Italian (`it-IT`),
Japanese (`ja-JP`), Korean (`ko-KR`), Portuguese (`pt-BR`), Russian (`ru-RU`),
Ukrainian (`uk-UA`), Vietnamese (`vi-VN`), and Simplified Chinese (`zh-CN`).

To learn more about prompt best practices and generating text in images, see
[Supported languages for image generation](https://firebase.google.com/docs/ai-logic/generate-images-gemini.md.txt#supported-languages).

### Audio-generating models (TTS and Live API)

Audio-generating models support specialized language sets optimized for speech
synthesis and (for the Live API) real-time bidirectional dialogue:

- **Text-to-speech (TTS) models** :
  The Gemini 3.x TTS models can automatically detect and generate
  speech in nearly 80 languages and dialects.

  To view the full list of supported languages and available BCP-47 locale
  codes, see
  [Supported languages for speech generation](https://firebase.google.com/docs/ai-logic/generate-speech.md.txt#languages).
- **Live API models** :
  Live API models support real-time, bidirectional voice interactions in
  nearly 80 languages and dialects.

  To view the full list of supported languages and learn how to influence the
  spoken response language, see
  [Supported languages for the Live API](https://firebase.google.com/docs/ai-logic/live-api/limits-and-specs.md.txt#languages).

<br />

*** ** * ** ***

## Information about previous models

This section provides information about previous generation models.
For more information about the deprecation and shutdown of these older models
(as well as recommended replacement models), see
[deprecated and shutdown models FAQ](https://firebase.google.com/docs/ai-logic/faq-and-troubleshooting.md.txt#shutdown-models-list).

> [!WARNING]
>
> To avoid service disruption, we recommend keeping your app updated with the
> [latest models available](https://firebase.google.com/docs/ai-logic/models.md.txt) (for example,
> `gemini-4-argon`, `gemini-3.8-flash`,
> `gemini-3.5-flash-lite`, or `gemini-nano-banana-2.1`)
> Learn more in the
> [deprecated and shutdown models FAQ](https://firebase.google.com/docs/ai-logic/faq-and-troubleshooting.md.txt#shutdown-models-list).
>
>
> **We *strongly* recommend using
> [Firebase Remote Config](https://firebase.google.com/docs/ai-logic/change-model-name-remotely.md.txt)
> or
> [server prompt templates](https://firebase.google.com/docs/ai-logic/server-prompt-templates/get-started.md.txt)
> so that you can make on-demand changes to the model name used for your AI
> feature without releasing a new version of your app.**

- General-use models that are shutdown:
  `gemini-1.0-pro`,
  `gemini-1.0-pro-001`,
  `gemini-1.0-pro-002`,
  `gemini-1.0-pro-vision`,
  `gemini-1.0-pro-vision-001`
  `gemini-1.5-flash-001`,
  `gemini-1.5-flash`,
  `gemini-1.5-flash-002`,
  `gemini-1.5-pro-001`,
  `gemini-1.5-pro`,
  `gemini-1.5-pro-002`,
  `gemini-2.0-flash-lite`,
  `gemini-2.0-flash-lite-001`,
  `gemini-2.0-flash`,
  `gemini-2.0-flash-001`

- Image-generating models that are shutdown:
  `gemini-2.5-flash-image`,
  `imagen-3.0-fast-generate-001`,
  `imagen-3.0-generate-001`,
  `imagen-3.0-generate-002`,
  `imagen-3.0-capability-001`,
  `imagen-4.0-ultra-generate-001`,
  `imagen-4.0-fast-generate-001`,
  `imagen-4.0-generate-001`

- Live API models that are shutdown:
  `gemini-2.0-flash-live-preview-04-09`,
  `gemini-2.0-flash-live-001`,
  `gemini-live-2.5-flash-preview`

If you can't find the information you're looking for in the following
sub-sections, you can find even more information in your chosen API provider
documentation:
[Gemini Developer API](https://ai.google.dev/gemini-api/docs/models)
or
[Agent Platform Gemini API (formerly Vertex AI)](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/google-models)

#### View details about about previous models

<br />

View supported input and output of previous generation models

<br />

These are the input and output types
*when using each model with Firebase AI Logic*:

|   | Gemini 2.5 Pro, Flash, Flash‑Lite | Gemini 2.5 Flash Image | Gemini 2.0 Flash | Gemini 2.0 Flash‑Lite | Imagen (generate) | Imagen (capability) |
|---|---|---|---|---|---|---|
| **Input types** |||||||
| Text | Yes | Yes | Yes | Yes | Yes | Yes |
| Code | Yes | Yes | Yes | Yes | No | No |
| Documents (PDFs or plain-text) | Yes | Yes | Yes | Yes | No | No |
| Images | Yes | Yes | Yes | Yes | No | Yes |
| Video | Yes | No | Yes | Yes | No | No |
| Audio | Yes | No | Yes | Yes | No | No |
| Audio (streaming) | No | No | No | No | No | No |
| **Output types** |||||||
| Text | Yes | Yes | Yes | Yes | No | No |
| Text (streaming) | Yes | No | Yes | Yes | No | No |
| Code | Yes | Yes | Yes | Yes | No | No |
| Structured output (like JSON) | Yes | No | Yes | Yes | No | No |
| Images | No | Yes | No | No | Yes | Yes |
| Video | No | No | No | No | No | No |
| Audio | No | No | No | No | No | No |
| Audio (streaming) | No | No | No | No | No | No |

<br />

<br />

<br />

Supported capabilities and features of previous generation models

<br />

These are the capabilities and features
*when using each model with Firebase AI Logic*:

|   | Gemini 2.5 Pro, Flash, Flash‑Lite | Gemini 2.5 Flash Image | Gemini 2.0 Flash | Gemini 2.0 Flash‑Lite | Imagen (generate) | Imagen (capability) |
|---|---|---|---|---|---|---|
| [Thinking](https://firebase.google.com/docs/ai-logic/thinking.md.txt) | Yes | No | No | No | No | No |
| [Generate text](https://firebase.google.com/docs/ai-logic/generate-text.md.txt) from text-only or multimodal inputs | Yes | [*interleaved or as part of image*](https://firebase.google.com/docs/ai-logic/generate-images-gemini.md.txt) | Yes | Yes | No | No |
| Generate images ([Gemini](https://firebase.google.com/docs/ai-logic/generate-images-gemini.md.txt) or [Imagen](https://firebase.google.com/docs/ai-logic/generate-images-imagen)) | No | Yes | No | No | Yes | Yes |
| Edit images ([Gemini](https://firebase.google.com/docs/ai-logic/generate-images-gemini.md.txt) or [Imagen](https://firebase.google.com/docs/ai-logic/edit-images-imagen-overview)) | No | Yes | No | No | No | Yes |
| Generate audio | No | No | No | No | No | No |
| [Generate structured output](https://firebase.google.com/docs/ai-logic/generate-structured-output.md.txt) (like JSON) | Yes | No | Yes | Yes | No | No |
| Analyze documents (PDFs or plain-text) ([text-output](https://firebase.google.com/docs/ai-logic/analyze-documents.md.txt) \| [image-output](https://firebase.google.com/docs/ai-logic/generate-images-gemini.md.txt)) | Yes | Yes | Yes | Yes | No | No |
| Analyze images ([text-output](https://firebase.google.com/docs/ai-logic/analyze-images.md.txt) \| [image-output](https://firebase.google.com/docs/ai-logic/generate-images-gemini.md.txt)) | Yes | Yes | Yes | Yes | No | No |
| Analyze video ([text-output](https://firebase.google.com/docs/ai-logic/analyze-videos) \| [image-output](https://firebase.google.com/docs/ai-logic/generate-images-gemini.md.txt)) | Yes | No | Yes | Yes | No | No |
| [Analyze audio](https://firebase.google.com/docs/ai-logic/analyze-audio.md.txt) | Yes | No | Yes | Yes | No | No |
| [Multi-turn chat](https://firebase.google.com/docs/ai-logic/chat.md.txt) | Yes | Yes | Yes | Yes | No | No |
| [Bidirectional multimodal streaming](https://firebase.google.com/docs/ai-logic/live-api.md.txt) | No | No | No | No | No | No |
| **Supported tools** |||||||
| [Function calling](https://firebase.google.com/docs/ai-logic/function-calling.md.txt) | Yes | No | Yes | Yes | No | No |
| [Code execution](https://firebase.google.com/docs/ai-logic/code-execution.md.txt) | Yes | No | Yes | No | No | No |
| [URL context](https://firebase.google.com/docs/ai-logic/url-context.md.txt) | Yes | No | No | No | No | No |
| [Grounding with Google Search](https://firebase.google.com/docs/ai-logic/grounding-google-search.md.txt) | Yes | No | Yes | No | No | No |
| [Grounding with Google Maps](https://firebase.google.com/docs/ai-logic/grounding-google-maps.md.txt) | Yes | No | Yes | No | No | No |
| [System instructions](https://firebase.google.com/docs/ai-logic/system-instructions.md.txt) | Yes | Yes | Yes | Yes | No | No |
| [Count tokens](https://firebase.google.com/docs/ai-logic/count-tokens.md.txt) | Yes | Yes | Yes | Yes | No | No |

<br />

<br />

<br />

Specifications and limitations of previous generation models

<br />

These are the specifications and limitations
*when using each model with Firebase AI Logic*:

| Property | Gemini 2.5 Pro, Flash, Flash‑Lite | Gemini 2.5 Flash Image | Gemini 2.0 Flash | Gemini 2.0 Flash‑Lite | Imagen (generate) | Imagen (capability) |
|---|---|---|---|---|---|---|
| Input token limit **\*** | 1,048,576 tokens | 32,768 tokens | 1,048,576 tokens | 1,048,576 tokens | 480 tokens | 480 tokens |
| Output token limit **\*** | 65,536 tokens | 8,192 tokens | 8,192 tokens | 8,192 tokens | --- | --- |
| Knowledge cutoff date | January 2025 | --- | June 2024 | June 2024 | --- | --- |
| **PDFs (per request)** |||||||
| Max number of input PDF files **\*\*** | 3,000 files | 3 files | 3,000 files | 3,000 files | --- | --- |
| Max number of pages per input PDF file **\*\*** | 1,000 pages | 3 pages | 1,000 pages | 1,000 pages | --- | --- |
| Max size per input PDF file | 50 MB | 50 MB | 50 MB | 50 MB | --- | --- |
| **Images (per request)** |||||||
| Max number of *input* images | 3,000 images | 3 images | 3,000 images | 3,000 images | --- | 4 images |
| Max number of *output* images | --- | Up to output token limit | --- | --- | 4 images | 4 images |
| Max size per input base64-encoded image | 7 MB | 7 MB | 7 MB | 7 MB | --- | --- |
| **Video (per request)** |||||||
| Max number of input video files | 10 files | --- | 10 files | 10 files | --- | --- |
| Max length of all input video (frames only) | \~60 minutes | --- | \~60 minutes | \~60 minutes | --- | --- |
| Max length of all input video (frames+audio) | \~45 minutes | --- | \~45 minutes | \~45 minutes | --- | --- |
| **Audio (per request)** |||||||
| Max number of *input* audio files | 1 file | --- | 1 file | 1 file | --- | --- |
| Max number of *output* audio files | --- | --- | --- | --- | --- | --- |
| Max length of all *input* audio | \~8.4 hours | --- | \~8.4 hours | \~8.4 hours | --- | --- |
| Max length of all *output* audio | --- | --- | --- | --- | --- | --- |


^\*
*For all Gemini models, a token is equivalent to about 4 characters,
so 100 tokens are about 60-80 English words. For Gemini models, you can
determine the total count of tokens in your requests using
[`countTokens`](https://firebase.google.com/docs/ai-logic/count-tokens.md.txt).*^


^\*\*
*PDFs are treated as images, so a single page of a PDF is treated as
one image. The number of pages allowed in a request is limited to the number
of images the model can support.*^

<br />

<br />

<br />

Available model names of previous generation models (including shutdown dates)

<br />

Model names are the explicit values that you include *in your code* during
initialization of the model.

> [!IMPORTANT]
> **Important:** Make sure to review the FAQ about the [changes required when models are deprecated or shut down (retired)](https://firebase.google.com/docs/ai-logic/faq-and-troubleshooting.md.txt#shutdown-models-what-to-do).   
>
> Be aware that several weeks before the shutdown date, projects that have no prior usage of a model will be blocked from starting to use it. Also, when a stable version is released for a given model, all experimental and preview versions of that model will usually be shut down (retired) within a few days or weeks (this section doesn't list every previous preview and experimental model).

##### General-use models

| **Model** | **Gemini Developer API** | **Agent Platform Gemini API** |
|---|---|---|
| `gemini-3.7-flash` ^1^ <br /> Release date: August 13, 2026 Release stage: Stable | Requests routed to `gemini-3.8-flash` Replacement: `gemini-3.8-flash` | Shutdown date: January 28, 2027 Replacement: `gemini-3.8-flash` |
| `gemini-3.6-flash` ^1^ <br /> Release date: July 21, 2026 Release stage: Stable | Shutdown date: --- Replacement: `gemini-3.8-flash` | Shutdown date: November 19, 2026 Replacement: `gemini-3.8-flash` |
| `gemini-3.5-flash` <br /> Release date: May 19, 2026 Release stage: Stable | Requests routed to `gemini-3.6-flash` Replacement: `gemini-3.8-flash` | Shutdown date: --- Replacement: `gemini-3.8-flash` |
| `gemini-3.1-pro-preview` <br /> Release date: February 19, 2026 Release stage: Preview | Shutdown date: --- Replacement: `gemini-4-argon` | Shutdown date: --- Replacement: `gemini-4-argon` |

| **Model** | **Gemini Developer API** | **Agent Platform Gemini API** |
|---|---|---|
| `gemini-2.5-pro` <br /> Release date: June 17, 2025 Release stage: Stable | Requests routed to `gemini-3.8-flash` *(starting December 1, 2026)* Replacement: `gemini-3.8-flash` | Shutdown date: October 20, 2026 Replacement: `gemini-3.8-flash` |
| `gemini-2.5-flash` <br /> Release date: June 17, 2025 Release stage: Stable | Requests routed to `gemini-3.5-flash-lite` *(starting December 1, 2026)* Replacement: `gemini-3.5-flash-lite` | Shutdown date: October 20, 2026 Replacement: `gemini-3.5-flash-lite` |
| `gemini-2.5-flash-lite` <br /> Release date: July 22, 2025 Release stage: Stable | Shutdown date: --- Replacement: `gemini-3.5-flash-lite` | Shutdown date: October 20, 2026 Replacement: `gemini-3.5-flash-lite` |

| **Model** | **Gemini Developer API** | **Agent Platform Gemini API** |
|---|---|---|
| `gemini-2.0-flash-001` <br /> Release date: February 5, 2025 Release stage: Shutdown | Shutdown date: June 1, 2026 Replacement: `gemini-3.5-flash-lite` | Shutdown date: June 1, 2026 Replacement: `gemini-3.5-flash-lite` |
| `gemini-2.0-flash` <br /> Release date: February 10, 2025 Release stage: Shutdown | Shutdown date: June 1, 2026 Replacement: `gemini-3.5-flash-lite` | Shutdown date: June 1, 2026 Replacement: `gemini-3.5-flash-lite` |
| `gemini-2.0-flash-lite-001` <br /> Release date: February 25, 2025 Release stage: Shutdown | Shutdown date: June 1, 2026 Replacement: `gemini-3.5-flash-lite` | Shutdown date: June 1, 2026 Replacement: `gemini-3.5-flash-lite` |
| `gemini-2.0-flash-lite` <br /> Release date: February 25, 2025 Release stage: Shutdown | Shutdown date: June 1, 2026 Replacement: `gemini-3.5-flash-lite` | Shutdown date: June 1, 2026 Replacement: `gemini-3.5-flash-lite` |

^**1** *For the Agent Platform Gemini API (formerly Vertex AI), this is a
"short-term availability model". See
[Model versioning and naming patterns](https://firebase.google.com/docs/ai-logic/models.md.txt#versions)*^

^All the following general-use models are also shutdown:
`gemini-1.0-pro`,
`gemini-1.0-pro-001`,
`gemini-1.0-pro-002`,
`gemini-1.0-pro-vision`,
`gemini-1.0-pro-vision-001`
`gemini-1.5-flash-001`,
`gemini-1.5-flash`,
`gemini-1.5-flash-002`,
`gemini-1.5-pro-001`,
`gemini-1.5-pro`,
`gemini-1.5-pro-002`^

##### Image-generating (Nano Banana and Imagen) models

| **Model** | **Gemini Developer API** | **Agent Platform Gemini API** |
|---|---|---|
| `gemini-2.5-flash-image` <br /> Release date: October 2, 2025 Release stage: Shutdown | Shutdown date: October 2, 2026 Replacement: `gemini-nano-banana-2.1` | Shutdown date: October 2, 2026 Replacement: `gemini-nano-banana-2.1` |

| **Model** | **Gemini Developer API** | **Agent Platform Gemini API** |
|---|---|---|
| `imagen-4.0-generate-001` <br /> Release date: August 14, 2025 Release stage: Shutdown | Shutdown date: June 30, 2026 Replacement: `gemini-nano-banana-2.1` | Shutdown date: June 30, 2026 Replacement: `gemini-nano-banana-2.1` |
| `imagen-4.0-fast-generate-001` <br /> Release date: August 14, 2025 Release stage: Shutdown | Shutdown date: June 30, 2026 Replacement: `gemini-nano-banana-2.1` | Shutdown date: June 30, 2026 Replacement: `gemini-nano-banana-2.1` |
| `imagen-4.0-ultra-generate-001` <br /> Release date: August 14, 2025 Release stage: Shutdown | Shutdown date: June 30, 2026 Replacement: `gemini-3-pro-image` | Shutdown date: June 30, 2026 Replacement: `gemini-3-pro-image` |
| `imagen-3.0-capability-001` <br /> Release date: December 10, 2024 Release stage: Shutdown | *Not supported* | Shutdown date: June 30, 2026 Replacement: `gemini-nano-banana-2.1` |
| `imagen-3.0-generate-002` <br /> Release date: January 23, 2025 Release stage: Shutdown | Shutdown date: June 30, 2026 Replacement: `gemini-nano-banana-2.1` | Shutdown date: June 30, 2026 Replacement: `gemini-nano-banana-2.1` |
| `imagen-3.0-generate-001` <br /> Release date: July 31, 2024 Release stage: Shutdown | *Not supported* | Shutdown date: June 30, 2026 Replacement: `gemini-nano-banana-2.1` |
| `imagen-3.0-fast-generate-001` <br /> Release date: July 31, 2024 Release stage: Shutdown | *Not supported* | Shutdown date: June 30, 2026 Replacement: `gemini-nano-banana-2.1` |

##### Audio - Live API models

| **Model** | **Gemini Developer API** | **Agent Platform Gemini API** |
|---|---|---|
| `gemini-live-2.5-flash-preview` <br /> Release date: June 17, 2025 Release stage: Shutdown | Shutdown date: December 9, 2025 Replacement: `gemini-3.1-flash-live-preview` | Shutdown date: December 9, 2025 Replacement: `gemini-live-2.5-flash-native-audio` |
| `gemini-2.0-flash-live-001` <br /> Release date: April 9, 2025 Release stage: Shutdown | Shutdown date: December 9, 2025 Replacement: `gemini-3.1-flash-live-preview` | Shutdown date: December 9, 2025 Replacement: `gemini-live-2.5-flash-native-audio` |
| `gemini-2.0-flash-live-preview-04-09` <br /> Release date: April 9, 2025 Release stage: Shutdown | *Not supported* | Shutdown date: December 9, 2025 Replacement: `gemini-live-2.5-flash-native-audio` |

<br />

<br />

<br />

*** ** * ** ***

## Next steps


#### Try out the capabilities of the Gemini API

- Build [multi-turn conversations (chat)](https://firebase.google.com/docs/ai-logic/chat.md.txt).
- Generate text from [text-only prompts](https://firebase.google.com/docs/ai-logic/generate-text.md.txt).
- Generate text by prompting with various file types, like [images](https://firebase.google.com/docs/ai-logic/analyze-images.md.txt), [PDFs](https://firebase.google.com/docs/ai-logic/analyze-documents.md.txt), [video](https://firebase.google.com/docs/ai-logic/analyze-video.md.txt), and [audio](https://firebase.google.com/docs/ai-logic/analyze-audio.md.txt).
- [Generate structured output (like JSON)](https://firebase.google.com/docs/ai-logic/generate-structured-output.md.txt) from both text and multimodal prompts.
- [Generate and edit images](https://firebase.google.com/docs/ai-logic/generate-images-gemini.md.txt) from both text and multimodal prompts.
- [Generate speech (both single- and
  multiple-speakers)](https://firebase.google.com/docs/ai-logic/generate-speech) using Gemini text-to-speech (TTS) models.
- [Stream input and output](https://firebase.google.com/docs/ai-logic/live-api.md.txt) (including audio) using the Gemini Live API.
- Use tools (like [function calling](https://firebase.google.com/docs/ai-logic/function-calling.md.txt) and Grounding with [Google Search](https://firebase.google.com/docs/ai-logic/grounding-google-search.md.txt) or [Google Maps](https://firebase.google.com/docs/ai-logic/grounding-google-maps.md.txt)) to connect a Gemini model to other parts of your app and external systems and information.

<br />