Which Google models does this reference list?

23 Google models: 8 text, 5 image, 4 video and 6 audio. Each has its own page with Google's list rate and the providers that serve it.

Which providers serve Google models?

Google AI (Gemini), Google Vertex AI, OpenRouter, KIE, LaoZhang API, Together AI, fal.ai, Replicate and 1 more. You connect your own account with any of them; INFRO routes between the ones you connect.

What is the lowest Google input rate listed?

Gemini 3.1 Flash-Lite, at $0.25 per 1M input tokens and $1.50 per 1M output tokens, with cached input at $0.025 per 1M tokens on Google's list (checked 2026-10-05).

Does INFRO add a markup to Google model usage?

No. Your Google or provider account bills usage directly; INFRO charges a software subscription and takes 0% of model spend.

Model vendor

Google models: API pricing and providers

23 Google models with Google's published list rates and the providers that serve each one. You call them through INFRO on a provider account you connect; that account bills you, and INFRO adds 0% to model spend.

Rates checked 2026-10-05.

Model	Modality	List rate	Providers
Gemini 3.1 Pro google/gemini-3.1-pro Multimodal reasoning	Text	$2.00 per 1M input tokens and $12 per 1M output tokens, with cached input at $0.20 per 1M tokens	5
Gemini 3.8 Flash google/gemini-3.8-flash Fast agents & coding	Text	$0.75 per 1M input tokens and $3.75 per 1M output tokens, with cached input at $0.075 per 1M tokens	5
Gemini 3.7 Flash google/gemini-3.7-flash Fast agents & coding	Text	$0.75 per 1M input tokens and $3.75 per 1M output tokens, with cached input at $0.075 per 1M tokens	5
Gemini 3.6 Flash google/gemini-3.6-flash Previous-generation Flash	Text	$0.75 per 1M input tokens and $3.75 per 1M output tokens, with cached input at $0.075 per 1M tokens	3
Gemini 3.5 Flash google/gemini-3.5-flash Legacy Flash	Text	$1.50 per 1M input tokens and $9.00 per 1M output tokens, with cached input at $0.15 per 1M tokens	3
Gemini 3.5 Flash-Lite google/gemini-3.5-flash-lite Fastest low-cost 3.5 model	Text	$0.30 per 1M input tokens and $2.50 per 1M output tokens, with cached input at $0.03 per 1M tokens	3
Gemini 3.1 Flash-Lite google/gemini-3.1-flash-lite Low-cost high-volume model	Text	$0.25 per 1M input tokens and $1.50 per 1M output tokens, with cached input at $0.025 per 1M tokens	3
Gemini 3 Flash (Preview) google/gemini-3-flash Legacy Flash preview	Text	$0.50 per 1M input tokens and $3.00 per 1M output tokens, with cached input at $0.05 per 1M tokens	2
Nano Banana Pro google/nano-banana-pro 2K–4K image generation	Image	$0.134 per image	8
Nano Banana 2 google/nano-banana-2 Fast image generation	Image	$0.067 per image	8
Nano Banana 2 Lite google/nano-banana-2-lite Low-latency, low-cost image generation and editing	Image	$0.034 per image	7
Nano Banana google/nano-banana Image generation & editing	Image	$0.039 per image	7
Veo 3.1 google/veo-3.1 Cinematic video, native audio	Video	$0.40 per second of video	5
Veo 3.1 Fast google/veo-3.1-fast Fast video generation, native audio	Video	$0.10 per second of video	5
Veo 3.1 Lite google/veo-3.1-lite Low-cost video generation, native audio	Video	$0.05 per second of video	4
Gemini Omni Flash google/gemini-omni-flash Video generation and editing, native audio	Video	$0.101 per second of video	1
Gemini 3.1 Flash TTS google/gemini-3.1-flash-tts Controllable text to speech	Audio	$16 per 1M characters	2
Gemini 3.5 Transcribe google/gemini-3.5-transcribe Speech-to-text with diarization and timestamps	Audio	$0.30 per audio hour	2
Lyria 3.5 google/lyria-3.5 Full-length music generation	Audio	$0.08 per track	1
Lyria 3 Clip (Preview) google/lyria-3-clip 30-second music clips	Audio	$0.04 per track	2
Chirp 3 google/chirp-3 Speech-to-text	Audio	$0.96 per audio hour	1
Imagen Upscaler google/imagen-upscaler Image upscale, 2x or 4x	Image	$0.02 per image	2
Lyria 2 google/lyria-2 Instrumental music clips	Audio	$0.0020 per second of video	3

Google models: questions

Which Google models does this reference list?: 23 Google models: 8 text, 5 image, 4 video and 6 audio. Each has its own page with Google's list rate and the providers that serve it.
Which providers serve Google models?: Google AI (Gemini), Google Vertex AI, OpenRouter, KIE, LaoZhang API, Together AI, fal.ai, Replicate and 1 more. You connect your own account with any of them; INFRO routes between the ones you connect.
What is the lowest Google input rate listed?: Gemini 3.1 Flash-Lite, at $0.25 per 1M input tokens and $1.50 per 1M output tokens, with cached input at $0.025 per 1M tokens on Google's list (checked 2026-10-05).
Does INFRO add a markup to Google model usage?: No. Your Google or provider account bills usage directly; INFRO charges a software subscription and takes 0% of model spend.

Google models

Google models: questions

Other model vendors