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 /M | Output /M | Cache read /M | Context |
|---|---|---|---|---|
| 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 |
Image 5 models
| Model | Per image |
|---|---|
| Gemini 3 Pro Image (Preview) | $2 |
| Gemini 3.1 Flash Image | $0.5 |
| gemini-2.5-flash-image | $0.3 |
| gemini-3.1-flash-image | $0.5 |
| gemini-3.1-flash-lite-image | $0.25 |
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 |
Text to speech 3 models
| Model | Per M chars |
|---|---|
| Google TTS Chirp 3 HD | $30 |
| Google TTS Neural2 | $16 |
| Google TTS Standard | $4 |
Realtime 2 models
| Model | Input /M | Output /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Superseded models (3)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
| Model | Input /M | Output /M | Context |
|---|---|---|---|
| Gemini 3.1 Flash-Lite | $0.25 | $1.5 | 1M |
Embeddings2 models
| Model | Input /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)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://synthorai.io/v1",
apiKey: "sk-syn-...",
});
const resp = await client.chat.completions.create({
model: "gemini-3.1-pro-preview",
messages: [{ role: "user", content: "Summarize this diff" }],
reasoning_effort: "medium",
});
console.log(resp.choices[0].message.content);curl https://synthorai.io/v1/chat/completions \
-H "Authorization: Bearer sk-syn-..." \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-pro-preview",
"messages": [{"role": "user", "content": "Hello"}],
"reasoning_effort": "medium"
}'package main
import (
"context"
"fmt"
"github.com/openai/openai-go/v3"
"github.com/openai/openai-go/v3/option"
)
func main() {
client := openai.NewClient(
option.WithBaseURL("https://synthorai.io/v1"),
option.WithAPIKey("sk-syn-..."),
)
resp, _ := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
Model: "gemini-3.1-pro-preview",
Messages: []openai.ChatCompletionMessageParamUnion{
openai.UserMessage("Summarize this diff"),
},
ReasoningEffort: openai.ReasoningEffortMedium,
})
fmt.Println(resp.Choices[0].Message.Content)
}import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.*;
import com.openai.models.ReasoningEffort;
OpenAIClient client = OpenAIOkHttpClient.builder()
.baseUrl("https://synthorai.io/v1")
.apiKey("sk-syn-...")
.build();
ChatCompletion resp = client.chat().completions().create(
ChatCompletionCreateParams.builder()
.model("gemini-3.1-pro-preview")
.addUserMessage("Summarize this diff")
.reasoningEffort(ReasoningEffort.MEDIUM)
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));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