New Sign up free, 10 calls on us. Up to $1, no card needed.

Google

Every Google model on Synthorai: one endpoint, live prices.

29 models · chat / vision / code / tools · from $0.025/M input

Why Google via Synthorai

  • Pay-as-you-go, no subscription. One key, every model; no Google account required.
  • Zero prompt retention. Zero prompt retention at the gateway by default; Google's own API data policies apply upstream. Details →
  • Prompt caching. Implicit caching is on by default for current Gemini models (discounted automatically on cache hits), plus an explicit CachedContent API with storage-based billing for guaranteed savings. The implicit floor is per model family: 4,096 tokens on Gemini 3.x, 2,048 on 2.5. The public docs state no default TTL and no separate write charge. Cache reads from $0.01/M.

Where Google sits · input price across 60 chat models

  • Alibaba $0.05 - $2.5
  • ByteDance $0.1 - $0.5
  • Google $0.1 - $2
  • DeepSeek $0.138 - $1.32
  • Tencent $0.14
  • OpenAI $0.2 - $30
  • MiniMax $0.22 - $0.3
  • Moonshot $0.574 - $3
  • Anthropic $1 - $10
  • Z.ai $1 - $1.4

Each bar spans a vendor’s cheapest to most expensive chat model, so you can see where this one sits against the rest of the catalogue.

Google models & pricing

Chat 9 models

Model Input /MOutput /MCache read /MContext
Gemini 2.5 Flash $0.3 $2.5 $0.03 1M
Gemini 2.5 Flash-Lite $0.1 $0.4 $0.01 1M
Gemini 2.5 Pro $1.25 $10 $0.125 1M
Gemini 3 Flash $0.5 $3 $0.05 1M
Gemini 3.1 Pro $2 $12 $0.2 1M
Gemini 3.5 Flash $1.5 $9 $0.15 1M
Gemini 3.5 Flash-Lite $0.3 $2.5 $0.03 1M
Gemini 3.6 Flash $1.5 $7.5 $0.15 1M
Gemini 3.7 Flash $0.75 $3.75 $0.075 1M

Video 5 models

Model Per second
Veo 2 $0.5/s
Veo 3 $0.75/s
Veo 3 Fast $0.15/s
Veo 3.1 $0.4/s
Veo 3.1 Fast $0.15/s

Audio 2 models

Model Per minute
Chirp 2 $0.016/min
Chirp 3 $0.016/min

Text to speech 3 models

Realtime 2 models

Model Input /MOutput /M
gemini-2.5-flash-native-audioinvited beta $0.5 $2
gemini-3.1-flash-liveinvited beta $0.75 $4.5
Superseded models (3)

Chat1 model

ModelInput /MOutput /MContext
Gemini 3.1 Flash-Lite $0.25$1.51M

Embeddings2 models

ModelInput /M
Gemini Embedding 001 $0.15
Text Embedding 004 $0.025

These carry a deprecation date from the vendor, or a newer model in this catalogue names them as its predecessor. They stay routable at their published prices, so a pinned model id keeps working.

Provider list prices: no platform markup. Prices refresh live on each model's page. These are official list prices. Logged-in customers may see effective prices including workspace discounts on /console/pricing.

Use Google models in 30 seconds

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.chat.completions.create(
    model="gemini-3.1-pro-preview",
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

About Google

Google's Gemini family covers fast, inexpensive Flash and Flash-Lite tiers up to Pro-grade reasoning, with million-token context windows, native multimodality and image generation. Synthorai exposes Gemini through the OpenAI-compatible API you already use (no Google Cloud project or SDK setup required) with per-model live pricing below.

FAQ

How do I get a Google API key without a subscription?

You don't need a Google account: sign up on Synthorai, create one API key, and every Google model on this page works through the OpenAI-compatible endpoint: pay-as-you-go, no subscription (models marked "invited beta" additionally need an approved application).

What does the Google API cost?

Token-billed models start at $0.025/M input tokens; every model's live per-unit price is in the table above. These are provider list prices with no platform markup.

Can I use my own Google key (BYOK)?

Gemini BYOK isn't available yet; requests run on Synthorai's managed channels at the listed pay-as-you-go rates.

What is Google's data-retention policy via API?

Zero prompt retention at the gateway by default; Google's own API data policies apply upstream.

Other providers

Get your API key Browse all models