Models / Google
Model vendorGoogle
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
Popular models
Gemini 3.5 FlashnewGemini 3.5 Flash is Google's high-efficiency multimodal model, released 2026-05, designed for near-Pro coding and reasoning at Flash-tier cost and speed.$0.18 / $1.06in / out · 1M−88%Gemini 3 Flash PreviewGemini 3 Flash Preview is Google's fast, lower-latency thinking model, released 2025-12, designed for agentic workflows, multi-turn chat, and coding assistance.$0.07 / $0.41in / out · 1M−86%Gemini 2.5 FlashGemini 2.5 Flash is Google's fast multimodal model, released 2025-06, built for advanced reasoning, coding, math, and scientific tasks.$0.09 / $0.67in / out · 1M−73%
Google models on MirAPI
ModelTypeContextInputOutputCache r / wOff listChannels
Defaultstable$0.18 / $1.06in / out · 1M−88%vs list price
Defaultstable$0.07 / $0.41in / out · 1M−86%vs list price
Defaultstable$0.09 / $0.67in / out · 1M−73%vs list price
Defaultstable$0.43 / $1.71in / out · 1M−39%vs list price
Defaultstable$0.26 / $2.14in / out · 1M−15%vs list price
Defaultstable$1.71 / $10.26in / out · 1M−15%vs list price
Defaultstable$0.21 / $1.28in / out · 1M−15%vs list price
Defaultstable$0.09 / $0.34in / out · 1M−15%vs list price
Defaultstable$0.71 / $3.56in / out · 1M−5%vs list price
Defaultstable$0.95 / $19.00in / out · 1M−5%vs list price
Defaultstable$0.09 / $0.34in / out · 1M—vs list price
Defaultstable$0.47 / $9.50in / out · 1M—vs list price
Defaultstable$0.95 / $19.00in / out · 1M—vs list price
Defaultstable$0.24 / $1.42in / out · 1M—vs list price
Defaultstable$71.25 / $285.00in / out · 1M—vs list price
Defaultstable$71.25 / $285.00in / out · 1M—vs list price
Defaultstable$1.42 / $16.63in / out · 1M—vs list price
Defaultstable$0.57 / $2.85in / out · 1M+52%vs list price
Defaultstable$1.90 / $114.00in / out · 1M+728%vs list price
Defaultstable$0.28 / $28.50in / out · 1M+928%vs list price
Defaultstable$0.24 / $28.50in / out · 1M+1542%vs list price
Defaultstable$0.47 / $57.00in / out · 1M+1542%vs list price
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 embeddingsimport 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"}], )
import OpenAI from "openai"; const client = new OpenAI({ baseURL: "https://api.mirapi.ai/v1", // changed apiKey: process.env.MIRAPI_API_KEY, // changed }); const res = await client.chat.completions.create({ model: "google/gemini-3.5-flash", messages: [{ role: "user", content: "Hello" }], });
curl https://api.mirapi.ai/v1/chat/completions \ -H "Authorization: Bearer $MIRAPI_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "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.