gemini-embedding-001gemini
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
2,048 tokens→MODEL PRICE INDEX
模型比价
先确定模型版本，再查看各服务商的渠道、输入输出价格和核验状态。
gemini-embedding-2gemini
Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space
8,192 tokens→Video generation and editing model for fast, conversational text- and image-to-video workflows
131,072 tokens→gemini-2.5-flashgemini-flash
Fast Gemini workhorse for multimodal apps where latency and price matter
1,048,576 tokens→gemini-2.5-flash-imagegemini-flash
Nano Banana image model for fast generation, edits, and character-consistent assets
32,768 tokens→gemini-2.5-flash-preview-ttsgemini-flash
Speech generation model for controllable voice, narration, and audio delivery
8,192 tokens→gemini-2.5-pro-preview-ttsgemini-flash
Speech generation model for controllable voice, narration, and audio delivery
8,192 tokens→gemini-3.1-flash-imagegemini-flash
Image model for prompt-driven generation, editing, and visual design workflows
131,072 tokens→gemini-3.1-flash-image-previewgemini-flash
Image model for prompt-driven generation, editing, and visual design workflows
65,536 tokens→gemini-3.1-flash-live-previewgemini-flash
High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications
131,072 tokens→gemini-3.1-flash-tts-previewgemini-flash
Low-latency speech generation with steerable prompts and expressive audio tags
8,192 tokens→gemini-3.5-flashgemini-flash
Fast Gemini model balancing multimodal reasoning, tool use, and cost
1,048,576 tokens→gemini-3.6-flashgemini-flash
Fast Gemini model balancing multimodal reasoning, tool use, and cost
1,048,576 tokens→gemini-3.7-flashgemini-flash
High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning
1,048,576 tokens→gemini-3.8-flashgemini-flash
Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows
1,048,576 tokens→gemini-3-flash-previewgemini-flash
New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs
1,048,576 tokens→gemini-flash-latestgemini-flash
High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning
1,048,576 tokens→gemini-2.5-flash-litegemini-flash-lite
Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents
1,048,576 tokens→gemini-3.1-flash-litegemini-flash-lite
Low-latency Gemini model for high-volume multimodal and agent workloads
1,048,576 tokens→gemini-3.1-flash-lite-imagegemini-flash-lite
Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing
65,536 tokens→