Pricing
- Input Tokens: $0.02 /M tokens
- Output Tokens: $0.02 /M tokens
Input Modalities
Frequently asked questions
How much does Text Embedding 004 cost?
How do I call Text Embedding 004 via API?
Who created Text Embedding 004?
More models from Google
See all Google models →- Input: $ 3 /M
- Output: $ 15 /M
- Web Search: $0.014/request
- Input Audio: $3/M tokens
- Input Video: $3/M tokens
Gemini 4 Neon is the latest model in Google’s Gemini 4 series. It features frontier-level intelligence and can rapidly handle complex software engineering, knowledge work, and scientific research tasks. It has a unified 1-million-token context window, with a maximum single-generation length of up to 1 million tokens.
- Input: $ 1.5 /M
- Output: $ 9 /M
- Input Image: $1.5/M tokens
- Input Audio: $1.5/M tokens
- Input Video: $1.5/M tokens
Genie 4 is Google’s latest real-time interactive world generation model. Through the Interactions API, it can stream controllable video at 24 frames per second in a 16:9 aspect ratio, while simultaneously outputting 48 kHz stereo audio.
- Input: $ 1.5 /M
- Output: $ 7.5 /M
- Web Search: $0.014/request
- Input Audio: $1.5/M tokens
- Input Video: $1.5/M tokens
Gemini 4 Hydrogen is a Google Gemini 4 model focused on speed and efficiency. Potential use cases include everyday conversations, text processing, and interactive applications where fast responses matter.
Gemini Decision 1 is designed for judgment and decision-making tasks, helping developers build automated processes and agent workflows that require clear choices.
Audio input $3.00/M, audio output $12/M. Text input $0.75/M, text output $4.5/M.
Gemini 3.8 Live is a multimodal AI model from Google that delivers a low-latency, audio-to-audio voice interaction experience, enabling real-time conversations without inference delays. It supports interleaved reasoning, asynchronous and synchronous function calling, and built-in proactive audio processing capabilities.
Audio input $3.00/M, audio output $12/M.
Gemini 2.5 Flash Live is Google's multimodal AI model for real-time interactions, supporting low-latency voice conversations and able to understand user input by combining text, images, or video.