About Google
Artificial intelligence could be one of humanity’s most useful inventions. We research and build safe artificial intelligence systems. We're committed to solving intelligence, to advance science and benefit humanity.
We live in an exciting time when AI research and technology are delivering extraordinary advances.
In the coming years, AI — and ultimately artificial general intelligence (AGI) — has the potential to drive one of the greatest transformations in history.
We’re a team of scientists, engineers, ethicists and more, working to build the next generation of AI systems safely and responsibly.
Website ↗GitHub ↗
Source ↗ · 2026-11-12T02:17:01.624288184ZazureFoundry/HuggingFace/google-madlad400-10b-mt@2
`google/madlad400-10b-mt` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/google/madlad400-10b-mt) - [Text Generation Inference Documentation](ht
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/google-madlad400-7b-mt@1
`google/madlad400-7b-mt` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/google/madlad400-7b-mt) - [Text Generation Inference Documentation](http
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/google-madlad400-7b-mt-bt@1
`google/madlad400-7b-mt-bt` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/google/madlad400-7b-mt-bt) - [Text Generation Inference Documentation
- Input modalities
- text
- Output modalities
- text
huggingface/google/medgemma-4b-it
- Capabilities
- multimodal, visionInput
azureFoundry/HuggingFace/google-mobilenet-v2-1.0-224@1
`google/mobilenet_v2_1.0_224` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/google/mobilenet_v2_1.0_224) - [`image-classification` Task on Hugging Face](https://huggingface.co/tasks/image-classification) ### Send Request You can use c
azureFoundry/HuggingFace/google-mt5-base@10
`google/mt5-base` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `text2text-generation` task in the `transformers` library. If you want to learn more about the model's architecture, hyperparameters, limitations, and biases, y
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v2: 3.716%
azureFoundry/HuggingFace/google-mt5-large@7
`google/mt5-large` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `text2text-generation` task in the `transformers` library. If you want to learn more about the model's architecture, hyperparameters, limitations, and biases,
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/google-mt5-small@9
`google/mt5-small` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `text2text-generation` task in the `transformers` library. If you want to learn more about the model's architecture, hyperparameters, limitations, and biases,
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v2: 4.256%
azureFoundry/HuggingFace/google-mt5-xl@5
`google/mt5-xl` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `text2text-generation` task in the `transformers` library. If you want to learn more about the model's architecture, hyperparameters, limitations, and biases, you
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v2: 5.191%
huggingface/google/mt5-xxl
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v2: 5.103%
azureFoundry/HuggingFace/google-muril-base-cased@5
`google/muril-base-cased` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `fill-mask` task in the `transformers` library. If you want to learn more about the model's architecture, hyperparameters, limitations, and biases, you
azureFoundry/HuggingFace/google-muril-large-cased@1
`google/muril-large-cased` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/google/muril-large-cased) - [`feature-extraction` Task on Hugging Face](https://huggingface.co/tasks/feature-extraction) ### Send Request You can use cURL or any
- Input modalities
- text
- Output modalities
- embeddings
- Capabilities
- embeddings
cloudflareWorkersAI/google/nano-banana
Google's fast image generation model producing high-quality images from text prompts.
- Input modalities
- text
- Output modalities
- image
- Capabilities
- imageOutput
Inference prices
cloudflareWorkersAI/google/nano-banana-2
Google's second-generation image generation model with improved quality and speed.
- Input modalities
- text
- Output modalities
- image
- Capabilities
- imageOutput
Inference prices
cloudflareWorkersAI/google/nano-banana-2.1
Google's Nano Banana 2.1 image generation and editing model, optimized for a balance of quality and performance.
- Context window
- 131,072
- Input modalities
- text
- Output modalities
- image
- Capabilities
- imageOutput
Inference prices
google/gemini-nano-banana-2.1-20261006
Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization, mask- and ink-based editing, and factual accuracy, and renders photorealistic skin ton
- Context window
- 65,536
- Input modalities
- image, text
- Output modalities
- image, text
- Capabilities
- imageOutput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Benchmarks
- LMArena: 1,327.684
- OpenRouter Benchmarks: 63.194%
Inference prices
- Published price : $1.50 / input_tokens_per_million · openRouter ↗
- Published price : $7.50 / output_tokens_per_million · openRouter ↗
google/gemini-3.1-flash-image-20260528
Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced contextual understanding with fast, cost-efficient inference, making complex image gene
- Context window
- 131,072
- Input modalities
- image, text
- Output modalities
- image, text
- Capabilities
- batch, imageOutput, multimodal, promptCaching, reasoning, structuredOutputs, visionInput, webSearch
Inference prices
- Published price : $0.50 / input_tokens_per_million · openRouter ↗
- Published price : $3.00 / output_tokens_per_million · openRouter ↗
google/gemini-3.1-flash-image-preview-20260226
Gemini 3.1 Flash Image Preview, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced contextual understanding with fast, cost-efficient inference, making complex im
- Context window
- 65,536
- Input modalities
- image, text
- Output modalities
- image, text
- Capabilities
- imageOutput, multimodal, reasoning, structuredOutputs, visionInput
Inference prices
- Published price : $0.50 / input_tokens_per_million · openRouter ↗
- Published price : $3.00 / output_tokens_per_million · openRouter ↗