Veo 3, Imagen 4, Nano Banana, and Gemini — Google's full stack from video generation to multimodal reasoning.
Google offers frontier models spanning video (Veo 3 with synchronized audio), image (Imagen 4, Nano Banana), and language (Gemini multimodal LLMs). Through RunAPI, the entire Google AI stack shares a single key.
- Single API key shared across providers
- Model skills carry docs and schemas into your workspace
- Per-call billing, no commitment
- Failed generations are not charged
What stands out
All models from Google
Gemini API access for Google's multimodal LLM across chat, code generation, reasoning, and long-context tasks.
Gemini Omni API access for voice, character, and multimodal video resources in agent media workflows.
Imagen 4 API access for photorealistic text-to-image, precise typography, broad styles, and up to 2K resolution.
Nano Banana API access for fast text-to-image with accurate in-image text and multi-character consistency.
Veo 3.1 API access for high-fidelity video generation up to 4K with synthesized dialogue, sound effects, and ambience.
Install a Google model skill.
Pick a model and add its skill so your coding tool has docs, schemas, pricing notes, and setup steps.
# Base URL
https://runapi.ai
# Endpoints
POST /v1/chat/completions
POST /v1beta/models/*:streamGenerateContent
curl https://runapi.ai/v1/chat/completions \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.5-flash",
"messages": [
{
"role": "user",
"content": "Analyze this codebase and suggest three performance improvements with before/after examples."
}
]
}'from openai import OpenAI
client = OpenAI(
base_url="https://runapi.ai/v1",
api_key="your-runapi-key"
)
response = client.chat.completions.create(
model="gemini-3.5-flash",
messages=[{"role": "user", "content": "Analyze this codebase and suggest three performance improvements with before/after examples."}]
)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://runapi.ai/v1",
apiKey: "your-runapi-key"
});
const response = await client.chat.completions.create({
model: "gemini-3.5-flash",
messages: [{ role: "user", content: "Analyze this codebase and suggest three performance improvements with before/after examples." }]
});Every variant from Google
| Model | Variant | Billing | From | |
|---|---|---|---|---|
|
Gemini
|
gemini-2.5-flash | 1K tokens | $0.020 | View → |
| gemini-2.5-pro | 1K tokens | $0.050 | View → | |
| gemini-3-flash-preview | 1K tokens | $0.020 | View → | |
| gemini-3-pro-preview | 1K tokens | $0.060 | View → | |
| gemini-3.1-pro-preview | 1K tokens | $0.060 | View → | |
| gemini-3.5-flash | 1K tokens | $0.050 | View → | |
|
Gemini Omni
|
gemini-omni-audio | call | $0.0000 | View → |
| gemini-omni-character | call | $0.0000 | View → | |
| gemini-omni-text-to-video | call | $3.60 | View → | |
|
Imagen 4
|
imagen-4 | call | $0.080 | View → |
| imagen-4-fast | call | $0.040 | View → | |
| imagen-4-pro-remix-image | call | $0.180 | View → | |
| imagen-4-ultra | call | $0.120 | View → | |
|
Nano Banana
|
nano-banana | call | $0.040 | View → |
| nano-banana-2 | call | $0.080 | View → | |
| nano-banana-edit | call | $0.040 | View → | |
| nano-banana-pro | call | $0.180 | View → | |
|
Veo 3.1
|
veo-3.1 | call | $2.50 | View → |
| veo-3.1-fast | call | $0.600 | View → |
Frequently asked questions about Google
Is this an official Google integration?
RunAPI exposes a managed API surface with transparent pricing, capability, and error behavior.
Do I need a Google account?
No — your RunAPI key is enough for managed access.
What's the latency overhead from proxying?
Typically under 20 ms. RunAPI keeps the proxy layer close to model execution regions.
Are images / videos cached?
Generated outputs are stored and retrievable by task ID. Inputs are not cached.
Can I bring my own key?
Not currently — calls use RunAPI-managed access.
