Google models, pricing, and protocols

Gemini 3.5 Flash is Google's multimodal model. It accepts text, images, video, audio, and PDF input and produces text output.

Gemini 3.1 Pro is Google's flagship multimodal model for complex reasoning, code, and long-form generation, with 1M context and 64K output.

Gemini 3 Flash is the Gemini 3 model for low latency, high throughput, and cost-efficient multimodal work.

gemini-4-argon is a Google model available through MoleAPI with gemini, openai access. It fits OpenAI compatible, Gemini compatible, Vision, Prompt cache workflows, with pricing synced from the MoleAPI console.

gemini-3.8-flash · Language model for conversation, writing and summarization.

gemini-3.8-flash-high is a Google model available through MoleAPI with gemini, openai access. It fits OpenAI compatible, Gemini compatible, Vision workflows, with pricing synced from the MoleAPI console.

gemini-3.7-flash · Language model for conversation, writing and summarization.

gemini-3.6-flash · Language model for conversation, writing and summarization.

gemini-3.5-flash-lite · Language model for conversation, writing and summarization.

gemini-3.1-flash-image · Generates images from text and edits reference images.

Image image model by Google for image generation, editing, visual creation, and creative production.

gemini-3.1-flash-image-preview-t · Generates images from text and edits reference images.

gemini-3.1-flash-lite · Language model for conversation, writing and summarization.

gemini-3.1-flash-lite-image · Generates images from text and edits reference images.

Gemini model by Google for general chat, writing, coding assistance, and tool-assisted workflows.

gemini-3.1-flash-tts-preview · Speech generation model for converting text into spoken audio.

Gemini 3.1 Pro is Google's flagship multimodal model for complex reasoning, code, and long-form generation, with 1M context and 64K output.

gemini-3.1-pro-preview-high · Language model for conversation, writing and summarization.

gemini-3.1-pro-preview-low · Language model for conversation, writing and summarization.

Gemini 3 Flash is the Gemini 3 model for low latency, high throughput, and cost-efficient multimodal work.

gemini-3-pro-image · Generates images from text and edits reference images.

Image image model by Google for image generation, editing, visual creation, and creative production.

Gemini model by Google for general chat, writing, coding assistance, and tool-assisted workflows.

Gemini 2.5 Flash is Google's mature model for speed, cost, and scaled multimodal processing, retaining 1M context and controllable thinking.

Image image model by Google for image generation, editing, visual creation, and creative production.

Image image model by Google for image generation, editing, visual creation, and creative production.

Gemini model by Google for general chat, writing, coding assistance, and tool-assisted workflows.

gemini-2.5-flash-nothinking · Reasoning model for analysis and solving complex questions.

Gemini 2.5 Pro is Google's mature long-context multimodal reasoning model for complex code, research, and media understanding that benefits from a stable version.

gemini-2.5-pro-thinking-128 · Reasoning model for analysis and solving complex questions.

Gemini 2.5 Pro is Google's mature long-context multimodal reasoning model for complex code, research, and media understanding that benefits from a stable version.

gemini-embedding-001 · Converts text into embeddings for semantic search and retrieval.

gemini-flash-latest · Language model for conversation, writing and summarization.

gemini-flash-lite-latest · Language model for conversation, writing and summarization.

Gemma model by Google for general chat, writing, coding assistance, and tool-assisted workflows.

Gemma model by Google for general chat, writing, coding assistance, and tool-assisted workflows.