Learn about supported models

For mobile and web apps, the Vertex AI in Firebase 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.

Here's a brief overview of supported models for Vertex AI in Firebase and their latest stable versions. The sections later on this page provide more detailed comparisons and information.

Model	Input	Output	Optimized for
Gemini models
Gemini 2.0 Flash gemini-2.0-flash-001	text, code, PDFs, images, video, audio	text, code, JSON (images & audio coming soon!)	Next generation features, speed, and multimodal generation for a diverse variety of tasks
Gemini 1.5 Pro gemini-1.5-pro-002	text, code, PDFs, images, video, audio	text, code, JSON	Complex reasoning tasks requiring more intelligence
Gemini 1.5 Flash gemini-1.5-flash-002	text, code, PDFs, images, video, audio	text, code, JSON	Fast and versatile performance across a diverse variety of tasks

Does Vertex AI in Firebase support older models, like Gemini 1.0 models?

Yes, Vertex AI in Firebase supports all Gemini models, including older models.

Important: We strongly recommend using a newer model with our SDKs. These older Gemini models are approaching their discontinuation date and don't offer all the capabilities of the newer models.

Model	Input	Output	Optimized for
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

At the bottom of this page, you can view detailed information about older models. Review our FAQ about all the models that Vertex AI in Firebase supports and does not support.

The remainder of this page provides detailed information about the models supported by Vertex AI in Firebase:

• 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, and preview 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 Vertex AI in Firebase. Each model might have additional capabilities that aren't available when using our SDKs.

You can learn more about each of the Gemini models in the Google Cloud documentation.

Supported input and output

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

	Gemini 2.0 Flash	Gemini 1.5 Pro	Gemini 1.5 Flash
Input types
Text
Code
Documents (PDFs or plain-text)
Images, Video, and Audio
Audio (streaming)	coming soon!
Output types
Text
Structured output (like JSON)
Code
Images	coming soon!
Audio	coming soon!
Audio (streaming)	coming soon!

To learn about supported file types, see Supported input files and requirements for the Vertex AI Gemini API.

Supported capabilities and features

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

		Gemini 2.0 Flash	Gemini 1.5 Pro	Gemini 1.5 Flash
Generate text from text or multimodal inputs
Generate images		coming soon!
Generate audio		coming soon!
Generate structured output (like JSON)
Analyze images and video (vision)
Analyze audio
Analyze documents (PDFs or plain-text)
Multi-turn chat
Function calling (tools)
	Basic function calling
	Parallel function calling
	Function calling mode
Count tokens and billable characters
System instructions
Multimodal Live API (bidirectional streaming)		coming soon!

Note: Context caching, Search as a tool, grounding with Google Search, code execution, fine tuning a model, embeddings generation, and semantic retrieval are supported by various models or the Vertex AI Gemini API, but they are not available when using Vertex AI in Firebase.

Specifications and limitations

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

Property	Gemini 2.0 Flash	Gemini 1.5 Pro	Gemini 1.5 Flash
Context window * Total token limit (combined input+output)	1,048,576 tokens	2,097,152 tokens	1,048,576 tokens
Output token limit *	8,192 tokens	8,192 tokens	8,192 tokens
Knowledge cutoff date	June 2024	May 2024	May 2024
Images (per request)
Max number of input images	3,000 images	3,000 images	3,000 images
Max number of output images	coming soon!	---	---
Max size per input base64-encoded image	7 MB	7 MB	7 MB
PDFs (per request)
Max number of input PDF 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
Max size per input PDF file	50 MB	50 MB	50 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	coming soon!	---	---
Max length of all input audio	~8.4 hours	~8.4 hours	~8.4 hours
Max length of all output audio	coming soon!	---	---

^{* For all 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 for the Vertex AI Gemini API.

Important: For Vertex AI in Firebase SDKs, the maximum request size is 20 MB. You get an HTTP 413 error if a request is too large.

If an input file's size will make the total request size exceed 20 MB, then you'll need to provide the file using a URL (for example, by using a Cloud Storage for Firebase URL). However, if a file is small, you can often pass it directly as inline data (note though, that a file provided as inline data is encoded to base64 in transit, which increases the size of the request).

---

Model versioning and naming patterns

Models are offered in stable, auto-updated, and preview versions.

• Stable versions are considered Generally Available.

  • Stable versions have model names appended with a specific three-digit version number, for example gemini-2.0-flash-001 .

• Auto-updated versions always point to the latest stable version of that model; if a new stable version is released, the auto-updated version automatically starts pointing to that new stable version.

  • Auto-updated versions have model names with no appendage, for example gemini-2.0-flash.

• Preview versions have new capabilities and are considered not stable. Note that 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.

  • Preview versions have model names appended with -preview along with the model's initial release date (-MMDD), for example gemini-1.5-pro-preview-0409 (released on April 9, 2024).

Learn more about the available model versions and their lifecycle (Gemini) in the Google Cloud documentation.

Important: For production use cases, we recommend using the most recent stable version. Even though an auto-updated version points to a stable version, the actual model version it points to will automatically change whenever a new stable version is released, which could mean unexpected behavior or responses. Also, preview versions are only recommended during prototyping.

You can use Firebase Remote Config to dynamically change the model and version in your app without releasing a new version of your app.

---

Available model names

Model names are the explicit values that you include in your code during initialization of the generative model (which is a required step to call the Gemini API).

You can use the publishers.models.list endpoint to list all available model names. Note that this returned list will include all models that Vertex AI supports, but Vertex AI in Firebase only supports the Gemini models described on this page. Also note that auto-updated versions (for example, gemini-2.0-flash) aren't listed because they're a convenience alias for the base stable model.

Gemini model names

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

Gemini 2.0 Flash model names

Model name	Description	Release stage	Initial release date	Discontinuation date
Stable versions
gemini-2.0-flash-001	Latest stable version of Gemini 2.0 Flash	General Availability	2025-02-05	To be determined
Auto-updated version
gemini-2.0-flash	Points to the latest stable version of 2.0 Flash (currently gemini-2.0-flash-001)	General Availability	2025-02-10	---

Gemini 1.5 Pro model names

Model name	Description	Release stage	Initial release date	Discontinuation date
Stable versions
gemini-1.5-pro-002	Latest stable version of Gemini 1.5 Pro	General Availability	2024-09-24	No earlier than 2025-09-24
gemini-1.5-pro-001	Initial stable version of Gemini 1.5 Pro	General Availability	2024-05-24	No earlier than 2025-05-24
Auto-updated version
gemini-1.5-pro	Points to the latest stable version of 1.5 Pro (currently gemini-1.5-pro-002)	General Availability	2024-09-24	---

Gemini 1.5 Flash model names

Model name	Description	Release stage	Initial release date	Discontinuation date
Stable versions
gemini-1.5-flash-002	Latest stable version of Gemini 1.5 Flash	General Availability	2024-09-24	No earlier than 2025-09-24
gemini-1.5-flash-001	Initial stable version of Gemini 1.5 Flash	General Availability	2024-05-24	No earlier than 2025-05-24
Auto-updated version
gemini-1.5-flash	Points to the latest stable version of 1.5 Flash (currently gemini-1.5-flash-002)	General Availability	2024-09-24	---

---

Supported languages

Note: These languages are not the locations supported by the Vertex AI service and the models; these are the languages that the models can understand and (for Gemini) respond in (like the text input and output). If needed, learn more about supported locations.

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 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 older models

Vertex AI in Firebase supports all Gemini models, including older models like Gemini 1.0 Pro and Gemini 1.0 Pro Vision. However, we strongly recommend using a newer model with our SDKs. These older Gemini models are approaching their discontinuation date and don't offer all the capabilities of the newer models.

View supported input and output of older models

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

	Gemini 1.0 Pro Vision	Gemini 1.0 Pro
Input types
Text
Code
Image
Documents (PDFs or plain text)
Video (frames only)
Video (frames+audio)
Audio
Output types
Text
Code
Images, Video, and Audio

Supported capabilities and features of older models

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

		Gemini 1.0 Pro Vision	Gemini 1.0 Pro
Generate text from text-only input
Generate text from multimodal input
Generate images, video, or audio
Generate structured output (like JSON) using response schema
Multi-turn chat
Function calling (tools)
	Basic function calling
	Parallel function calling
	Function calling mode
Count tokens and billable characters
System instructions

Specifications and limitations of older models

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

Property	Gemini 1.0 Pro Vision	Gemini 1.0 Pro
Context window * Total token limit (combined input+output)	16,384 tokens	32,760 tokens
Output token limit *	2,048 tokens	8,192 tokens
Knowledge cutoff date	February 2023	February 2023
Images (per request)
Max number of input images	16 images	---
Max size per base64-encoded input image	7 MB	---
PDFs (per request)
Max number of input PDF files **	16 files	---
Max number of pages per input PDF file **	16 pages	---
Max size per input PDF file	50 MB	---
Video (per request)
Max number of input video files	1 file	---
Max length of all input video (frames only)	2 minutes	---
Max length of all input video (frames+audio)	---	---
Audio (per request)
Max number of input audio files	---	---
Max length of all input audio	---	---

^{* For all 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.}

Available model names of older models

Gemini 1.0 Pro Vision model names

Model name	Description	Release stage	Initial release date	Discontinuation date
Stable versions
gemini-1.0-pro-vision-001	Latest stable version of Gemini 1.0 Pro Vision	General Availability	2024-02-15	No earlier than 2025-02-15
Auto-updated version
gemini-1.0-pro-vision	Points to the latest stable version of 1.5 Pro Vision (currently gemini-1.5-pro-vision-001)	General Availability	2024-01-04	---

Gemini 1.0 Pro model names

Model name	Description	Release stage	Initial release date	Discontinuation date
Stable versions
gemini-1.0-pro-002	Latest stable version of Gemini 1.0 Pro	General Availability	2024-04-09	No earlier than 2025-04-09
gemini-1.0-pro-001	Stable version of Gemini 1.0 Pro	General Availability	2024-02-15	No earlier than 2025-02-15
Auto-updated version
gemini-1.0-pro	Points to the latest stable version of 1.0 Pro (currently gemini-1.0-pro-002)	General Availability	2024-02-15	---

---

Next steps

Try out the capabilities of the Gemini API

• Build multi-turn conversations (chat).
• Generate text from text-only prompts.
• Generate text from multimodal prompts (including text, images, PDFs, video, and audio).
• Generate structured output (like JSON) from both text and multimodal prompts.
• Use function calling to connect generative models to external systems and information.