Models / Google

Model vendor

Google

Google DeepMind ships the Gemini multimodal family, Imagen and Veo — long-context models with native image and video.

45Models routed
+193%Average vs list price
1Channels serving Google

Google models on MirAPI

ModelTypeContextInputOutputCache r / wOff listChannels
Chirp 3newTranscription$16000.00 / soon
Gemini Embedding 2newEmbeddings8K$0.20 / soon
Gemini Embedding 2 PreviewEmbeddings8K$0.20 / soon
Gemma 4 26B A4B Text262K$0.07$0.34 / soon
Gemma 4 31BText262K$0.10$0.34 / soon
Veo 3.1 FastVideo / soon
Veo 3.1 LiteVideo / soon
Gemini 3.1 Flash Lite PreviewText1.049M$0.25$1.50 / soon
Lyria 3 Clip PreviewAudio1.049M / soon
Lyria 3 Pro PreviewAudio1.049M / soon
Veo 3.1Video / soon
Gemini 3.1 Pro PreviewText1.049M$2.00$12.00 / soon
Gemini 3.1 Pro Preview Custom ToolsText1.049M$2.00$12.00 / soon
Gemini Embedding 001Embeddings20K$0.15 / soon
Gemini 2.5 ProText1.049M$1.25$10.00 / soon
Gemini 2.5 Pro Preview 06-05Text1.049M$1.25$10.00 / soon
Gemini 2.5 Pro Preview 05-06Text1.049M$1.25$10.00 / soon
Gemma 3n 4BText33K$0.06$0.12 / soon
Gemma 3 12BText131K$0.05$0.15 / soon
Gemma 3 27BText262K$0.08$0.45 / soon
Gemma 3 4BText131K$0.05$0.10 / soon
Gemma 2 27BText8K$0.65$0.65 / soon
Browse the full catalogue
Migration

Gemini through the OpenAI-compatible API

Call Gemini, Imagen and Veo through the same OpenAI-compatible endpoint as every other model — no Google Cloud project, no service accounts. Just the catalogue model ID: gemini-3.5-flash becomes google/gemini-3.5-flash.

Endpoints
/v1/chat/completionsChat & tool calls
/v1/embeddingsText embeddings
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.mirapi.ai/v1",   # changed
    api_key=os.environ["MIRAPI_API_KEY"],   # changed
)

resp = client.chat.completions.create(
    model="google/gemini-3.5-flash",
    messages=[{"role": "user", "content": "Hello"}],
)

One key covers Google and 10 more vendors.

1M free tokens to start. No card required.