Learn about supported models

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 about all the models that Firebase AI Logic supports and does not support.

General-use models

Go to tables with model details

Gemini 3.x general-use models

OUR ADVANCED THINKING MODEL

gemini-3.1-pro-preview

Advanced intelligence, complex problem-solving skills, and powerful agentic and vibe coding capabilities. (billing required)

FAST AND INTELLIGENT

gemini-3.5-flash

Frontier-class performance rivaling larger models at a fraction of the cost. (billing not required)

ULTRA FAST

gemini-3.1-flash-lite

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

Gemini 2.5 general-use models

  • Gemini 2.5 Pro (gemini-2.5-pro): The most advanced model for complex tasks of the Gemini 2.5 series, featuring deep reasoning and coding capabilities. (billing not required)

  • Gemini 2.5 Flash (gemini-2.5-flash): The best price-performance model of the Gemini 2.5 series, especially for low-latency, high-volume tasks that require reasoning. (billing not required)

  • Gemini 2.5 Flash (gemini-2.5-flash-lite): The fastest and most budget-friendly multimodal model of the Gemini 2.5 series. (billing not required)

Image-generating models

Go to tables with model details

Gemini 3.x image-generating models

gemini-3-pro-image

State-of-the-art image generation and editing models for highly contextual native image creation. (billing required)

gemini-3.1-flash-image

Powerful, high-efficiency image generation and editing, optimized for speed and high-volume use cases. (billing required)

gemini-3.1-flash-lite-image

Ultra-low latency and cost-effective image generation and editing, designed for high-volume interactive use cases. (billing required)

Gemini 2.5 image-generating models

  • Gemini 2.5 Flash Image (gemini-2.5-flash-image, aka "Nano Banana"): Designed for speed and efficiency, optimized for high-volume, low-latency tasks. (billing required)

Audio-generating models

You can generate streamed audio with models that support the Gemini Live API.

Go to page with model details

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

Vertex AI 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)


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 previous generation models.

For details about the Gemini Live API models (like gemini-live-2.5-flash-native-audio), see Limits and specifications of the Live API.


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 or Vertex AI Gemini API.

For details about the Gemini Live API models (like gemini-live-2.5-flash-native-audio), see Limits and specifications of the Live API.

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.

Gemini 3.x
Pro, Flash, Flash‑Lite 		Gemini 3.x
Pro
Image 		Gemini 3.x
Flash
Image 		Gemini 3.x
Flash‑Lite
Image
Input types
Text
Code
Documents
(PDFs or plain-text)
Images
Video
Audio
Output types
Text
Text (streaming)
Code
Structured output
(like JSON)
Images
Audio

Supported capabilities and features

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

Gemini 3.x
Pro, Flash, Flash‑Lite 		Gemini 3.x
Pro
Image 		Gemini 3.x
Flash
Image 		Gemini 3.x
Flash‑Lite
Image
Thinking
Generate text from text-only or multimodal inputs interleaved or as part of image interleaved or as part of image interleaved or as part of image
Generate images
Edit images
Generate audio
Generate structured output
(like JSON)
Analyze documents
(PDFs or plain-text)
(text-output | image-output)
Analyze images
(text-output | image-output)
Analyze video
(text-output | image-output)
Analyze audio
Multi-turn chat
Bidirectional multimodal streaming
Supported tools
Function calling
Code execution
URL context
Grounding with Google Search
Grounding with Google Maps

Specifications and limitations

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

Property Gemini 3.x
Pro, Flash, Flash‑Lite 		Gemini 3.x
Pro
Image 		Gemini 3.x
Flash
Image 		Gemini 3.x
Flash‑Lite
Image
Input token limit * 1,048,576 tokens 65,536 tokens 131,072 tokens 65,536 tokens
Output token limit * 65,536 tokens 32,768 tokens 32,768 tokens 4,096 tokens
Knowledge cutoff date January 2025 January 2025 January 2025 January 2025
PDFs (per request)
Max number
of input PDF files **		 900 files 14 files 14 files 14 files
Max number
of pages
per input PDF file **		 900 pages 14 pages 14 pages 14 pages
Max size
per input PDF file		 50 MB 50 MB 50 MB 50 MB
Images (per request)
Max number
of input images		 1,000 images 14 images 14 images 14 images
Max size
per input base64-encoded image		 7 MB 7 MB 7 MB 7 MB
Max number
of output images		 --- Up to output token limit Up to output token limit Up to output token limit
Video (per request)
Max number
of input video files		 10 files --- Up to input token limit Up to input token limit
Max length
of all input video
(frames only)		 ~60 minutes --- ~25 minutes ~12 minutes
Max length
of all input video
(frames+audio)		 ~45 minutes --- --- ---
Audio (per request)
Max number
of input audio files		 1 file --- --- ---
Max length
of all input audio		 ~8.4 hours --- --- ---

* 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


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.
Gemini 2.5 and later models
Model names of stable versions have no suffix

Example: gemini-3.5-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 shutdown (retired) within a few weeks or months after their associated stable version is released.
  • For the Vertex AI Gemini API, preview models usually require you to set the location where you access the model to global.

Model names of preview versions are appended with -preview and often the model's release date (-MM-DD for older models or -MM-YYYY for newer models)

Examples:
gemini-2.5-flash-preview-04-17
(released on April 17, 2025)
or
gemini-2.5-flash-preview-09-2025
(released in September 2025)
or
gemini-3-pro-preview
(released in November 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.
  • These models are shutdown (retired) within a few weeks or months after their associated stable version is released.
  • For the Vertex AI Gemini API, experimental models require you to set the location where you access the model to global.

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.

---


Available model names

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

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

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

Programmatically list all available models

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

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

General-use models

Gemini 3.x Pro model names

Requires the pay-as-you-go Blaze pricing plan regardless of your Gemini API provider.

Model name Description Release stage Release date Shutdown date
gemini-3.1-pro-preview Latest preview version of Gemini 3.x Pro Preview 2026-02-19 To be determined

Gemini 3.x Flash model names

Does not require the pay-as-you-go Blaze pricing plan if you're using the Gemini Developer API.

Model name Description Release stage Release date Shutdown date
gemini-3.5-flash Stable version of Gemini 3.x Flash GA 2026-05-19 No earlier than
2027-05-19
gemini-3-flash-preview Preview version of Gemini 3.x Flash Preview 2025-12-17 To be determined

Gemini 3.x Flash‑Lite model names

Does not require the pay-as-you-go Blaze pricing plan if you're using the Gemini Developer API.

Model name Description Release stage Release date Shutdown date
gemini-3.1-flash-lite Stable version of Gemini 3.x Flash‑Lite GA 2026-05-07 No earlier than
2027-05-07

Gemini 2.5 Pro model names

Does not require the pay-as-you-go Blaze pricing plan if you're using the Gemini Developer API.

Model name Description Release stage Release date Shutdown date
gemini-2.5-pro Stable version of Gemini 2.5 Pro GA 2025-06-17 No earlier than
2026-06-17

Gemini 2.5 Flash model names

Does not require the pay-as-you-go Blaze pricing plan if you're using the Gemini Developer API.

Model name Description Release stage Release date Shutdown date
gemini-2.5-flash Stable version of Gemini 2.5 Flash GA 2025-06-17 No earlier than
2026-06-17

Gemini 2.5 Flash‑Lite model names

Does not require the pay-as-you-go Blaze pricing plan if you're using the Gemini Developer API.

Model name Description Release stage Release date Shutdown date
gemini-2.5-flash-lite Stable version of Gemini 2.5 Flash‑Lite GA 2025-07-22 No earlier than
2026-07-22

Image-generating models

Gemini 3.x Pro Image model names (aka "Nano Banana Pro")

Requires the pay-as-you-go Blaze pricing plan regardless of your Gemini API provider.

Model name Description Release stage Release date Shutdown date
gemini-3-pro-image Stable version of Gemini 3.x Pro Image
(aka "Nano Banana Pro")		 GA 2026-05-28 No earlier than
2027-05-28
gemini-3-pro-image-preview Preview version of Gemini 3.x Pro Image
(aka "Nano Banana Pro")		 Preview 2025-11-20 As early as
2026-06-25

Gemini 3.x Flash Image model names (aka "Nano Banana 2")

Requires the pay-as-you-go Blaze pricing plan regardless of your Gemini API provider.

Model name Description Release stage Release date Shutdown date
gemini-3.1-flash-image Stable version of Gemini 3.x Flash Image
(aka "Nano Banana 2")		 GA 2026-05-28 No earlier than
2027-05-28
gemini-3.1-flash-image-preview Preview version of Gemini 3.x Flash Image
(aka "Nano Banana 2")		 Preview 2026-02-26 As early as
2026-06-25

Gemini 3.x Flash‑Lite Image model names (aka "Nano Banana 2 Lite")

Requires the pay-as-you-go Blaze pricing plan regardless of your Gemini API provider.

Model name Description Release stage Release date Shutdown date
gemini-3.1-flash-lite-image Stable version of Gemini 3.x Flash‑Lite Image
(aka "Nano Banana 2 Lite")		 GA 2026-06-30 No earlier than
2027-06-30

Gemini 2.5 Flash Image model names (aka "Nano Banana")

Requires the pay-as-you-go Blaze pricing plan regardless of your Gemini API provider.

Model name Description Release stage Release date Shutdown date
gemini-2.5-flash-image Stable version for Gemini 2.5 Flash Image (aka "Nano Banana") GA 2025-10-02 No earlier than
2026-10-02

Audio-generating models

Gemini 2.5 Flash Live model names

Does not require the pay-as-you-go Blaze pricing plan if you're using the Gemini Developer API (usually preview models require a paid plan).

Gemini 2.5 Flash Live models are the native audio models that support the Gemini Live API. Even though the model has different model names depending on the Gemini API provider, the behavior and features of the model are the same.

Gemini Developer API
Model name		 Description Release stage Release date Shutdown date
gemini-2.5-flash-native-audio-preview-12-2025 1 Latest preview version for the Live API on the Gemini Developer API Preview 2025-12-12 To be determined
gemini-2.5-flash-native-audio-preview-09-2025 1 Initial preview version for the Live API on the Gemini Developer API Preview 2025-09-18 To be determined
Vertex AI Gemini API
Model name		 Description Release stage Release date Shutdown date
gemini-live-2.5-flash-native-audio 2 Stable version for the Live API on the Vertex AI Gemini API GA 2025-12-12 No earlier than
2026-12-12
gemini-live-2.5-flash-preview-native-audio-09-2025 2 Preview version for the Live API on the Vertex AI Gemini API Preview 2025-09-18 To be determined

1 Only supported by the Gemini Developer API. Also, even though these are preview models, they're available on the "free tier" of the Gemini Developer API.
2 Only supported by the Vertex AI Gemini API. Also, these models are not supported in the global location.


Supported languages

  • 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)


Information about previous models

The following are active, but previous generation models. We recommend using one of the latest models instead when possible.

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:

Older Gemini models

  • gemini-2.0-flash-001 (and its auto-updated alias gemini-2.0-flash)
  • gemini-2.0-flash-lite-001 (and its auto-updated alias gemini-2.0-flash-lite)

For information about older Gemini Live API models, see the Gemini API provider documentation:

Older Imagen models

  • imagen-4.0-ultra-generate-001
  • imagen-4.0-generate-001
  • imagen-4.0-fast-generate-001
  • imagen-3.0-capability-001
  • imagen-3.0-generate-002
  • imagen-3.0-generate-001
  • imagen-3.0-fast-generate-001

View details about about previous models


Next steps

Try out the capabilities of the Gemini API