I/O is live! Tune in for livestreamed keynotes and sessions May 20-21 starting at 10 AM PT. Watch now.

Learn about supported models
Stay organized with collections Save and categorize content based on your preferences.

For mobile and web apps, the Firebase AI Logic SDKs let you interact with the supported Gemini models and Imagen 3 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. Imagen 3 models can be prompted with text to generate images.

The following table is a brief overview of supported models for Firebase AI Logic and their latest stable model names. This table also lists preview and experimental models that are available for prototyping use cases.

Model	Input	Output	Description
Gemini models with stable versions
Gemini 2.0 Flash `gemini-2.0-flash-001`	text, code, PDFs, images, video, audio	text, code, JSON (images & audio coming soon!)	Our multimodal model with next-gen features and improved capabilities, including superior speed, built-in tool use, and a 1M token context window (multimodal generation coming soon!)
Gemini 2.0 Flash‑Lite `gemini-2.0-flash-lite-001`	text, code, PDFs, images, video, audio	text, code, JSON	Our fastest and most cost efficient Flash model. It's an upgrade path for 1.5 Flash users who want better quality for the same price and speed.
*Gemini models with only* preview and experimental versions** (recommended for prototyping use cases only)
Gemini 2.5 Pro `gemini-2.5-pro-preview-05-06`	text, code, PDFs, images, video, audio	text, code, JSON	Our most advanced reasoning model, capable of solving complex problems.
Gemini 2.5 Flash `gemini-2.5-flash-preview-04-17`	text, code, PDFs, images, video, audio	text, code, JSON	Our thinking model that offers great, well-rounded capabilities. It's designed to offer a balance between price and performance.
Gemini 2.0 Flash‑Live ¹ `gemini-2.0-flash-live-preview-04-09`	text (streaming), audio (streaming)	text (streaming), audio (streaming)	Our multimodal model that supports low-latency realtime streaming of multimodal inputs and outputs.
Imagen 3 models (when using with Firebase AI Logic)
Imagen 3 `imagen-3.0-generate-002`	text	images	Generates realistic, high-quality images from natural language text prompts
Imagen 3 Fast ² `imagen-3.0-fast-generate-001`	text	images	Generates images for prototyping or low-latency use cases

^{1 Not supported when using the Gemini Developer API
with Firebase AI Logic SDKs.}
^{2 Not supported by the Gemini Developer API regardless
of how you access the API.}

Also, review our FAQ about all the models that Firebase AI Logic supports and does not support.

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

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, specifically their stable, auto-updated, preview, and experimental versions
Lists of available model names to include in your code during initialization
Lists of supported languages for the models

At the bottom of this page, you can view detailed information about older models.

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: Gemini models and Imagen models
Vertex AI Gemini API: Gemini models and Imagen models

Supported input and output

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

	Gemini 2.5 Pro	Gemini 2.5 Flash	Gemini 2.0 Flash	Gemini 2.0 Flash- Lite	Gemini 2.0 Flash- Live	Imagen 3 / Imagen 3 Fast
Input types
Text
Text (streaming)
Code
Documents (PDFs or plain-text)
Images
Video
Audio
Audio (streaming)
Output types
Text
Text (streaming)
Code
Structured output (like JSON)
Images			coming soon!
Audio			coming soon!
Audio (streaming)

To learn about supported file types, see Supported input files and requirements.

Supported capabilities and features

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

	Gemini 2.0 Flash	Gemini 2.0 Flash- Live
Generate text from text-only or multimodal inputs		streaming only
Generate images (Imagen 3)	coming soon!
Generate audio	coming soon!	streaming only
Generate structured output (like JSON)
Analyze documents (PDFs or plain-text)
Analyze images (vision)
Analyze video (vision)
Analyze audio		streaming only
Multi-turn chat
Function calling (tools)
Count tokens
System instructions
Bidirectional multimodal streaming

Specifications and limitations

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

Property	Gemini 2.5 Pro	Gemini 2.5 Flash	Gemini 2.0 Flash	Gemini 2.0 Flash- Lite	Gemini 2.0 Flash- Live	Imagen 3 / Imagen 3 Fast
Context window * Total token limit (combined input+output)	1,048,576 tokens	1,048,576 tokens	1,048,576 tokens	1,048,576 tokens	32,768 tokens	480 tokens
Output token limit *	65,536 tokens	65,536 tokens	8,192 tokens	8,192 tokens	---	---
Knowledge cutoff date	January 2025	January 2025	June 2024	June 2024	August 2024	---
PDFs (per request)
Max number of input PDF files **	3,000 files	3,000 files	3,000 files	3,000 files	---	---
Max number of pages per input PDF file **	1,000 pages	1,000 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	3,000 images	3,000 images	3,000 images	---	---
Max number of output images	---	---	coming soon!	---	---	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	10 files	---	---
Max length of all input video (frames only)	~60 minutes	~60 minutes	~60 minutes	~60 minutes	---	---
Max length of all input video (frames+audio)	~45 minutes	~45 minutes	~45 minutes	~45 minutes	---	---
Audio (per request)
Max number of input audio files	1 file	1 file	1 file	1 file	---	---
Max number of output audio files	---	---	coming soon!	---	---	---
Max length of all input audio	~8.4 hours	~8.4 hours	~8.4 hours	~8.4 hours	---	---
Max length of all output audio	---	---	coming soon!	---	---	---

^{*
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.}

^{**
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 and pricing 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.

Important: The total request size limit is 20 MB. To send large files, review the options for providing files in multimodal requests.

Model versioning and naming patterns

Models are offered in stable, preview, and experimental versions. For convenience, aliases without explicit version values are supported.

To find specific model names to use in your code, see the "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.	Model names of stable versions are appended with a specific three-digit version number Example: `gemini-2.0-flash-001` Example: `imagen-3.0-generate-002`
	Auto-updated stable alias	*Auto-updated* stable aliases always point to the latest stable version of that model. If a new stable version is released, the auto-updated alias automatically starts pointing to that new stable version.	Model names of aliases have no appendage Example: `gemini-2.0-flash`
Preview		*Preview* versions have new capabilities and are considered not stable. Preview versions always point to the latest preview version of that model. If a new preview version is released, any existing preview version automatically starts pointing to that new preview version. These models not recommended for production use, come with more restrictive rate limits, and may have billing requirements.	Model names of preview versions are appended with `-preview` along with the model's release date (`-MM-DD`) Example: `gemini-2.5-flash-preview-04-17` (released on April 17, 2025)
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.	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)
Retired		*Retired* versions are past their retirement date and have been permanently deactivated. Retired models are no longer accessible or supported by Google. Requests referencing a retired model ID typically returns a 404 error.	---

Available model names

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

Programmatically list all available models

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

Gemini Developer API: Call the models.list endpoint
Vertex AI Gemini API: Call the publishers.models.list endpoint

Note that this returned list will include all models supported by the API providers, but Firebase AI Logic only supports the Gemini and Imagen models described on this page. Also note that auto-updated aliases (for example, gemini-2.0-flash) aren't listed because they're a convenience alias for the base model.

Gemini model names

For initialization examples for your platform, see the getting started guide.

For details about the release stages (especially for use cases and billing), see model versioning and naming patterns.

Gemini 2.5 Pro model names

Model name	Description	Release stage	Release date	Retirement date
`gemini-2.5-pro-preview-05-06`	Preview version of Gemini 2.5 Pro	Preview	2025-05-06	To be determined
`gemini-2.5-pro-preview-03-25`	Preview version pointing to `gemini-2.5-pro-preview-05-06` (which is the latest preview version)	Preview	2025-03-25	To be determined

Gemini 2.5 Flash model names

Model name	Description	Release stage	Release date	Retirement date
`gemini-2.5-flash-preview-04-17`	Preview version of Gemini 2.5 Flash	Preview	2025-04-17	To be determined

Gemini 2.0 Flash model names

Model name	Description	Release stage	Release date	Retirement date
`gemini-2.0-flash-001`	Latest stable version of Gemini 2.0 Flash	Stable	2025-02-05	No earlier than 2026-02-05
`gemini-2.0-flash`	Auto-updated alias pointing to the latest stable version of 2.0 Flash (currently `gemini-2.0-flash-001`)	Stable	2025-02-10	---

Gemini 2.0 Flash‑Lite model names

Model name	Description	Release stage	Release date	Retirement date
`gemini-2.0-flash-lite-001`	Latest stable version of Gemini 2.0 Flash‑Lite	Stable	2025-02-25	No earlier than 2026-02-25
`gemini-2.0-flash-lite`	Auto-updated alias pointing to the latest stable version of 2.0 Flash-Lite (currently `gemini-2.0-flash-lite-001`)	Stable	2025-02-25	---

Gemini 2.0 Flash‑Live model names

Only available when using the Vertex AI Gemini API as your API provider.

Model name	Description	Release stage	Release date	Retirement date
`gemini-2.0-flash-live-preview-04-09` ¹	Preview version for Gemini 2.0 Flash‑Live	Preview	2025-04-09	To be determined

^{1 Not supported when using the Gemini Developer API
with Firebase AI Logic SDKs.}

Imagen model names

For initialization examples for your platform, see the generate images with Imagen guide.

For details about the release stages (especially for use cases and billing), see model versioning and naming patterns.

Imagen 3 model names

Model name	Description	Release stage	Release date	Retirement date
`imagen-3.0-generate-002`	Latest stable version of Imagen 3	Stable	2025-01-23	No earlier than 2026-01-23
`imagen-3.0-generate-001` ²	Initial stable version of Imagen 3	Stable	2024-07-31	No earlier than 2025-07-31

Imagen 3 Fast model names

Model name	Description	Release stage	Release date	Retirement date
`imagen-3.0-fast-generate-001` ²	Initial stable version of Imagen 3 Fast	Stable	2024-07-31	No earlier than 2025-07-31

^{2 Not supported by the Gemini Developer API regardless
of how you access the API.}

Supported languages

Gemini

All the Gemini models can understand and respond in the following languages:

Arabic (ar), Bengali (bn), Bulgarian (bg), Chinese simplified and traditional (zh), Croatian (hr), Czech (cs), Danish (da), Dutch (nl), English (en), Estonian (et), Finnish (fi), French (fr), German (de), Greek (el), Hebrew (iw), Hindi (hi), Hungarian (hu), Indonesian (id), Italian (it), Japanese (ja), Korean (ko), Latvian (lv), Lithuanian (lt), Norwegian (no), Polish (pl), Portuguese (pt), Romanian (ro), Russian (ru), Serbian (sr), Slovak (sk), Slovenian (sl), Spanish (es), Swahili (sw), Swedish (sv), Thai (th), Turkish (tr), Ukrainian (uk), Vietnamese (vi)
Gemini 2.0 Flash, Gemini 1.5 Pro and Gemini 1.5 Flash models can understand and respond in the following additional languages:

Afrikaans (af), Amharic (am), Assamese (as), Azerbaijani (az), Belarusian (be), Bosnian (bs), Catalan (ca), Cebuano (ceb), Corsican (co), Welsh (cy), Dhivehi (dv), Esperanto (eo), Basque (eu), Persian (fa), Filipino (Tagalog) (fil), Frisian (fy), Irish (ga), Scots Gaelic (gd), Galician (gl), Gujarati (gu), Hausa (ha), Hawaiian (haw), Hmong (hmn), Haitian Creole (ht), Armenian (hy), Igbo (ig), Icelandic (is), Javanese (jv), Georgian (ka), Kazakh (kk), Khmer (km), Kannada (kn), Krio (kri), Kurdish (ku), Kyrgyz (ky), Latin (la), Luxembourgish (lb), Lao (lo), Malagasy (mg), Maori (mi), Macedonian (mk), Malayalam (ml), Mongolian (mn), Meiteilon (Manipuri) (mni-Mtei), Marathi (mr), Malay (ms), Maltese (mt), Myanmar (Burmese) (my), Nepali (ne), Nyanja (Chichewa) (ny), Odia (Oriya) (or), Punjabi (pa), Pashto (ps), Sindhi (sd), Sinhala (Sinhalese) (si), Samoan (sm), Shona (sn), Somali (so), Albanian (sq), Sesotho (st), Sundanese (su), Tamil (ta), Telugu (te), Tajik (tg), Uyghur (ug), Urdu (ur), Uzbek (uz), Xhosa (xh), Yiddish (yi), Yoruba (yo), Zulu (zu)

Imagen

General availability: English
Preview: Chinese (simplified), Chinese (traditional), Hindi, Japanese, Korean, Portuguese, Spanish

Information about older models

Firebase AI Logic supports the older active Gemini models (like Gemini 1.5 models).

Firebase AI Logic does not support the older Imagen models (like Imagen 2).

Model	Input	Output	Optimized for
Gemini 1.5 Pro `gemini-1.5-pro-002`	text, code, PDFs, images, video, audio	text, code, JSON	Supports complex reasoning tasks requiring more intelligence; 2M long context
Gemini 1.5 Flash `gemini-1.5-flash-002`	text, code, PDFs, images, video, audio	text, code, JSON	Offers fast and versatile performance across a diverse variety of tasks
Gemini 1.0 Pro Vision `gemini-1.0-pro-vision-001`	~~text, code, PDFs, images, video (frames only)~~	~~text, code~~	~~Handles text, images, and video for text or code responses. Cannot be used for chat.~~
Gemini 1.0 Pro `gemini-1.0-pro-002`	~~text, code~~	~~text, code~~	~~Natural language tasks, multi-turn text and code chat, and code generation~~

View supported input and output of older models

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

	Gemini 1.5 Pro	Gemini 1.5 Flash	Gemini 1.0 Pro Vision	Gemini 1.0 Pro
Input types
Text
Code
Documents (PDFs or plain-text)
Images
Video
Audio
Audio (streaming)
Output types
Text
Code
Structured output (like JSON)
Images, Video, and Audio

Supported capabilities and features of older models

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

	Gemini 1.5 Pro	Gemini 1.5 Flash	Gemini 1.0 Pro Vision	Gemini 1.0 Pro
Generate text from text-only input
Generate text from multimodal input
Generate images
Generate audio
Generate structured output (like JSON)
Analyze documents (PDFs or plain-text)
Analyze images (vision)
Analyze video (vision)
Analyze audio
Multi-turn chat
Function calling (tools)
Count tokens and billable characters
System instructions
Bidirectional multimodal streaming

Specifications and limitations of older models