OpenAI
Every OpenAI model on Synthorai: one endpoint, live prices.
28 models · chat / code / tools / reasoning · from $0.2/M input
Why OpenAI via Synthorai
- Bring your own key. Bring your own OpenAI key: zero markup, free.
- Zero prompt retention. Zero prompt retention at the gateway by default; OpenAI's own API data policies apply upstream. Details →
- Prompt caching. Automatic prefix caching once a prompt passes the minimum length, with no code changes; cached reads are discounted (up to 90% on current models) and there is no write fee. Cache reads from $0.06/M.
Where OpenAI 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.
OpenAI models & pricing
Chat 12 models
| Model | Input /M | Output /M | Cache read /M | Context |
|---|---|---|---|---|
| GPT-5.2 | $1.75 | $14 | $0.875 | 400K |
| GPT-5.3 Codex | $1.75 | $14 | $0.875 | 400K |
| GPT-5.4 | $2.5 | $15 | $1.25 | 922K |
| GPT-5.4 Mini | $0.75 | $4.5 | $0.375 | 400K |
| GPT-5.4 Nano | $0.2 | $1.25 | $0.1 | 400K |
| GPT-5.4 Pro | $30 | $180 | $15 | 922K |
| GPT-5.5 | $5 | $30 | $0.5 | 1.1M |
| GPT-5.5 Pro | $30 | $180 | - | 1.1M |
| GPT-5.6 | $5 | $30 | $0.5 | 1.1M |
| GPT-5.6 Luna | $1 | $6 | $0.1 | 1.1M |
| GPT-5.6 Sol | $5 | $30 | $0.5 | 1.1M |
| GPT-5.6 Terra | $2.5 | $15 | $0.25 | 1.1M |
Image 4 models
| Model | Per image |
|---|---|
| GPT Image 1 | $5 |
| GPT Image 1 Mini | $2 |
| GPT Image 2 | $5 |
| gpt-image-1.5 | $5 |
Audio 4 models
| Model | Price |
|---|---|
| GPT-4o Mini Transcribe | $1.25/M tokens |
| GPT-4o Transcribe | $2.5/M tokens |
| GPT-4o Transcribe Diarize | $2.5/M tokens |
| Whisper v1 | $0.006/min |
Realtime 2 models
| Model | Input /M | Output /M | Cache read /M |
|---|---|---|---|
| GPT Realtime 2.1invited beta | $4 | $24 | $0.4 |
| GPT Realtime 2.1 Miniinvited beta | $0.6 | $2.4 | $0.06 |
Superseded models (4)
Chat1 model
| Model | Input /M | Output /M | Cache read /M | Context |
|---|---|---|---|---|
| GPT-5.2 Codex | $1.75 | $14 | $0.875 | 400K |
Video2 models
| Model | Per second |
|---|---|
| Sora 2 | $0.1/s |
| Sora 2 Pro | $0.3-$0.5/s |
Realtime1 model
| Model | Input /M | Output /M | Cache read /M |
|---|---|---|---|
| GPT Realtimeinvited beta | $4 | $16 | $0.4 |
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 OpenAI 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="gpt-5.4-pro",
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: "gpt-5.4-pro",
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": "gpt-5.4-pro",
"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: "gpt-5.4-pro",
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("gpt-5.4-pro")
.addUserMessage("Summarize this diff")
.reasoningEffort(ReasoningEffort.MEDIUM)
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));About OpenAI
OpenAI's API spans the GPT chat family, o-series reasoning models, image generation and speech-to-text. On Synthorai every OpenAI model sits behind the same endpoint and SDK you already use (swap the base_url, keep your code) with live pay-as-you-go pricing and prompt-cache reads billed at provider rates.
FAQ
How do I get an OpenAI API key without a subscription?
You don't need an OpenAI account: sign up on Synthorai, create one API key, and every OpenAI 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 OpenAI API cost?
Token-billed models start at $0.2/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 OpenAI key (BYOK)?
Yes. Bring your own OpenAI key: zero markup, free. Your key stays in an encrypted vault and requests using it bill at provider list price.
What is OpenAI's data-retention policy via API?
Zero prompt retention at the gateway by default; OpenAI's own API data policies apply upstream.
Other providers