gemini-3.1-flash-lite-previewgemini-flash-lite
Legacy model retained for compatibility with older integrations
1,048,576 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-3.5-flash-litegemini-flash-lite
Fast Gemini model balancing multimodal reasoning, tool use, and cost
1,048,576 tokens→gemini-flash-lite-latestgemini-flash-lite
Fast Gemini model balancing multimodal reasoning, tool use, and cost
1,048,576 tokens→deep-research-max-preview-04-2026gemini-pro
Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports
131,072 tokens→deep-research-preview-04-2026gemini-pro
Agentic model for autonomous multi-step research, synthesis, and cited reports
131,072 tokens→gemini-2.5-computer-use-preview-10-2025gemini-pro
Specialized Gemini 2.5 model for browser-control agents that automate UI tasks
128,000 tokens→gemini-2.5-progemini-pro
Google's proven reasoning model for coding, math, and multimodal analysis
1,048,576 tokens→gemini-3.1-pro-previewgemini-pro
Reasoning-first Gemini preview for agentic coding and complex problem solving
1,048,576 tokens→gemini-3.1-pro-preview-customtoolsgemini-pro
Advanced Gemini model for complex reasoning, coding, and multimodal analysis
1,048,576 tokens→gemini-3.5-live-translate-previewgemini-pro
Low-latency audio-to-audio model for real-time speech translation across 70+ languages
16,384 tokens→gemini-3-pro-imagegemini-pro
Nano Banana Pro for higher-fidelity image generation and design-heavy edits
65,536 tokens→gemini-3-pro-image-previewgemini-pro
Nano Banana Pro for higher-fidelity image generation and design-heavy edits
131,072 tokens→gemini-pro-latestgemini-pro
Reasoning-first Gemini preview for agentic coding and complex problem solving
1,048,576 tokens→gemma-4-26b-a4b-itgemma
Open Gemma instruction model for efficient chat and self-hosted deployments
262,144 tokens→gemma-4-31b-itgemma
Largest Gemma 4 instruction model for open, self-hosted chat and reasoning
262,144 tokens→lyria-3-clip-previewlyria
Music generation model for short 30-second clips, loops, and previews from text or image prompts
1,048,576 tokens→lyria-3-pro-previewlyria
Music generation model for full-length songs from text or images with vocals and structure
1,048,576 tokens→Video model for prompt-guided generation, editing, and motion workflows
480 tokens→Video model for prompt-guided generation, editing, and motion workflows
480 tokens→Video model for prompt-guided generation, editing, and motion workflows
480 tokens→