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 ↗ · 2026-11-12T02:17:01.624288184ZcloudflareWorkersAI/google/nano-banana-2-lite
Google's fastest Gemini image generation model for rapid image creation and iteration.
- Context window
- 65,536
- Input modalities
- text
- Output modalities
- image
- Capabilities
- imageOutput
Inference prices
google/gemini-3.1-flash-lite-image-20260630
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation in roughly 4 seconds — about 2.7× faster than Gemini 3
- Context window
- 65,536
- Input modalities
- image, text
- Output modalities
- image, text
- Capabilities
- imageOutput, multimodal, promptCaching, reasoning, structuredOutputs, videoInput, visionInput, webSearch
Benchmarks
- OpenRouter Benchmarks: 11.616%
Inference prices
- Published price : $0.25 / input_tokens_per_million · openRouter ↗
- Published price : $1.50 / output_tokens_per_million · openRouter ↗
google/gemini-2.5-flash-image
Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation, edits, and multi-turn conversations. Aspect ratios can be controlled with the [image_config
- Context window
- 32,768
- Input modalities
- image, text
- Output modalities
- image, text
- Capabilities
- batch, imageOutput, multimodal, promptCaching, reasoning, structuredOutputs, visionInput, webSearch
Benchmarks
- Vercel AI Gateway: 3.788%
Inference prices
- Published price : $0.03 / cache_read_tokens_per_million · openRouter ↗
- Published price : $0.08 / cache_write_tokens_per_million · openRouter ↗
- Published price : $0.30 / input_tokens_per_million · openRouter ↗
- Published price : $2.50 / output_tokens_per_million · openRouter ↗
cloudflareWorkersAI/google/nano-banana-pro
Google's higher-quality image generation model with improved detail and prompt adherence.
- Input modalities
- text
- Output modalities
- image
- Capabilities
- imageOutput
Inference prices
google/gemini-3-pro-image-20260528
Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and high-fidelity visual synthesis. The model generates context-rich gr
- Context window
- 131,072
- Input modalities
- image, text
- Output modalities
- image, text
- Capabilities
- batch, imageOutput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Benchmarks
- Vercel AI Gateway: 11.882%
Inference prices
- Published price : $0.20 / cache_read_tokens_per_million · openRouter ↗
- Published price : $0.38 / cache_write_tokens_per_million · openRouter ↗
- Published price : $2.00 / input_tokens_per_million · openRouter ↗
- Published price : $12.00 / output_tokens_per_million · openRouter ↗
google/gemini-3-pro-image-preview-20251120
Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and high-fidelity visual synthesis. The model generates context-rich gr
- Context window
- 65,536
- Input modalities
- image, text
- Output modalities
- image, text
- Capabilities
- imageOutput, multimodal, promptCaching, reasoning, structuredOutputs, visionInput
Inference prices
- Published price : $0.20 / cache_read_tokens_per_million · openRouter ↗
- Published price : $0.38 / cache_write_tokens_per_million · openRouter ↗
- Published price : $2.00 / input_tokens_per_million · openRouter ↗
- Published price : $12.00 / output_tokens_per_million · openRouter ↗
huggingface/google/owlv2-base-patch16-ensemble
azureFoundry/HuggingFace/google-pegasus-cnn-dailymail@12
`google/pegasus-cnn_dailymail` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `summarization` task in the `transformers` library. If you want to learn more about the model's architecture, hyperparameters, limitations, and bia
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/google-pegasus-large@8
`google/pegasus-large` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `summarization` 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
azureFoundry/HuggingFace/google-pegasus-newsroom@5
`google/pegasus-newsroom` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `summarization` 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-pegasus-pubmed@5
`google/pegasus-pubmed` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `summarization` task in the `transformers` library. If you want to learn more about the model's architecture, hyperparameters, limitations, and biases, yo
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/google-pegasus-x-large@3
`google/pegasus-x-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 bi
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/google-pegasus-xsum@12
`google/pegasus-xsum` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `summarization` 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
huggingface/google/recurrentgemma-2b
- Input modalities
- text
- Output modalities
- text
Benchmarks
- LLM-Perf: 17,902,562.252
- Open LLM Leaderboard v1: 45.461%
- Open LLM Leaderboard v2: 7.015%
- Subquadratic LLM Leaderboard: 16.15%
huggingface/google/recurrentgemma-2b-it
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v1: 40.86%
- Open LLM Leaderboard v2: 7.996%
- Subquadratic LLM Leaderboard: 40.87%
huggingface/google/recurrentgemma-9b
- Input modalities
- text
- Output modalities
- text
Benchmarks
- LLM-Perf: 1,737.007
- Open LLM Leaderboard v2: 13.709%
huggingface/google/recurrentgemma-9b-it
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v2: 19.218%
azureFoundry/HuggingFace/google-roberta2roberta-l-24-cnn-daily-mail@4
`google/roberta2roberta_L-24_cnn_daily_mail` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `summarization` task in the `transformers` library. If you want to learn more about the model's architecture, hyperparameters, limita
- Input modalities
- text
- Output modalities
- text