Google's 14 models on ModelRunner span Image-to-Video, Text-to-Text, Image-to-Image and 4 more, from $0.4 per second of video upward.
14 public models — every one runnable in a free playground, through the REST API and JavaScript SDK, or from an AI assistant over MCP.
Google models & pricing
Gemini 3.1 Flash TTS
Turn text into expressive, directable speech in 30 voices — describe the delivery in plain language and get back a 24 kHz WAV.
Gemini 3.5 Flash-Lite
The cheapest Gemini text tier — built for high-volume agentic tasks, translation and simple data processing over an OpenAI-compatible endpoint.
Gemini 3.7 Flash
Reasoning-first flagship text model for coding and agentic work, with tunable thinking levels, tool calling and streaming over an OpenAI-compatible endpoint.
Gemini 3.5 Flash
Fast, general-purpose text model served over an OpenAI-compatible chat completions endpoint, with tool calling, JSON mode and streaming.
Lyria 3 Clip
Generate a 30-second song clip — vocals and lyrics included by default — from a single text prompt, as an MP3.
Nano Banana 2 Lite Text to Image
Generate 1K (roughly 1 megapixel) images from a text prompt at the lowest price in the Nano Banana family, with 14 aspect ratios from square to ultra-wide banner.
Nano Banana 2 Image Editing
Edit images with text prompts. Make targeted changes like adding or removing objects, changing styles, or modifying specific elements while preserving the rest of the image.
Nano Banana 2 Text to Image
Nano Banana 2 is a fast and versatile text-to-image model. It excels at creating high-quality images, from photorealistic scenes to complex infographics with accurate text, and can optionally use Google Search to generate content based on real-time information.
Veo 3.1 Extend Video
Extend existing Veo-generated videos by seamlessly adding 7 seconds of high-fidelity footage and synchronized audio using text prompts.
Veo 3.1 Reference to Video
Generate high-fidelity, cinematic videos with synchronized audio by using text prompts and up to three reference images to guide visual style and content.
Veo 3.1 First/Last Frame to Video
Generate seamless 8-second video transitions by interpolating between a first and last frame with high-fidelity visuals and native audio.
Veo 3.1 Image to Video
Turn static images into high-fidelity 720p or 1080p videos with synchronized native audio using text prompts to guide the animation.
Veo 3.1 Text to Video
Create cinematic 8-second videos with Veo 3.1, Google’s latest text-to-video model in the Gemini API — now with native audio, frame control, and reference image support.
Nano Banana
State of the art image editing model from Google Gemini 2.5.
What you can build with Google models
- Generate voice-over and narration with a specific tone, accent or pace Gemini 3.1 Flash TTS
- Produce audiobook and e-learning reads directed in plain language Gemini 3.1 Flash TTS
- Create character dialogue and IVR or assistant prompts from a script Gemini 3.1 Flash TTS
- Add expressive delivery — whisper, excited, calm — without re-recording Gemini 3.1 Flash TTS
- Synthesize speech in 30 distinct prebuilt voices Gemini 3.1 Flash TTS
- High-volume classification, tagging and routing at the lowest cost per token Gemini 3.5 Flash-Lite
- Bulk translation and text normalisation pipelines Gemini 3.5 Flash-Lite
- Cheap extraction of structured JSON from messy text Gemini 3.5 Flash-Lite
Browse by capability
Call a Google model in one request
Every endpoint shares the same lifecycle: submit to the queue, poll the status URL, fetch the result. Swap the endpoint to switch models — nothing else changes.
cURL
curl -X POST https://queue.modelrunner.run/google/gemini-3.1-flash-tts \
-H "Authorization: Key $MRUN_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "prompt": "..." }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }Use Google models from Claude & Cursor
Connect the ModelRunner MCP server once and your AI assistant can run every Google model on this page as a tool — authorized via OAuth, results returned as hosted URLs in the conversation.
Claude Code
claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcpFrequently asked questions
What Google models can I run on ModelRunner?
The catalog has 14 public Google models: Gemini 3.1 Flash TTS, Gemini 3.5 Flash-Lite, Gemini 3.7 Flash and 11 more. They cover image-to-video, text-to-text, image-to-image, text-to-image and 3 more. Each one has its own page with a free playground, the full input schema, and copy-paste code.
How much do Google models cost?
Pay-per-use, with no subscription: the 5 Google models billed per second of video start at $0.4, and every page publishes its own rate — some are tiered, so a lower resolution or a shorter clip costs less per run. You buy credits and pay only for what you generate.
How do I call a Google model from the API?
POST to https://queue.modelrunner.run/google/gemini-3.1-flash-tts with an Authorization: Key header and the input fields as the top-level JSON body (no wrapper object), then poll the returned status_url and fetch the result from response_url. The JavaScript SDK (@modelrunner/client) wraps that in a single subscribe() call, which is the one place an { input } object is used.
Can I run Google models from Claude or Cursor?
Yes. Connect the ModelRunner MCP server (https://mcp.modelrunner.run/mcp) once and all 14 Google models become tools your assistant can call with run_model — authorized over OAuth 2.1, so no API key goes into a config file. Results come back as hosted URLs in the conversation.
More on ModelRunner
Browse the full model catalog, compare live per-configuration rates on the pricing page, see curated sets on explore, or view every model creator.