Get access
Three ways to access Serenity Edge
Choose the route that fits your case: a Serenity Star account, a contract or a third-party platform.
Serenity Star account
Self-service for teams and developers: API keys and credits from your account.
- Create your Serenity Star account.
- Generate an API key and buy credits.
- Point your client at the base URL and pick a model.
When you create a Serenity Star account you get a welcome credit to try the chat models.
The decision, embeddings, rerank and redaction routes need a Serenity Edge API key.How to get one
Contract with SLA
For high volumes, dedicated capacity, specific terms or a service level agreement.
- Tell us about your use case and your volume.
- We agree terms, capacity and SLA.
- You start with direct support from the team.
Third-party platforms
Use Serenity Edge as a provider from the platform you already use, with that platform’s account and billing.
Available on
- cortecs
Use Serenity Edge as a provider from your cortecs account; billed by cortecs.
- EUrouter
Use Serenity Edge as a provider from your EUrouter account; billed by EUrouter.
Upcoming platforms
- Kilo
- nexos.ai
- OpenRouter
- Opper
- ProviderBench
- Requesty
- Vercel
Platforms where we are onboarding Serenity Edge as a provider, at different stages. The names belong to their respective owners.
Your first request
Point your client at the base URL and use your API key. Model identifiers are on the models page.
- Base URL
https://api.serenityedge.ai/v1
Everything the API includes
Streaming responses/v1/chat/completions
Tool calling/v1/chat/completions- Structured outputs (JSON)
/v1/chat/completions - Image input and document OCR
/v1/chat/completionsTry it - Responses API, for Codex CLI
/v1/responses - Decisions (preview)
/v1/decisionsTry it - Embeddings
/v1/embeddingsTry it - Rerank
/v1/rerankTry it - Personal data redaction
/v1/redactTry it
The decision, embeddings, rerank and redaction routes need a Serenity Edge API key.How to get one
Questions about availability before you start?Check the service status
Request
from openai import OpenAI
client = OpenAI(
base_url="https://api.serenityedge.ai/v1",
api_key="YOUR_API_KEY",
)
prompt = "Summarise this email in three bullet points: …"
response = client.chat.completions.create(
model="orion-plus",
messages=[
{"role": "system", "content": "Reply in English, briefly and professionally."},
{"role": "user", "content": prompt},
],
max_tokens=200,
temperature=0.3,
)
print(response.choices[0].message.content)
print(response.usage)A real answer from orion-plus, recorded on 14 October 2026.See the full request
{
"model": "orion-plus",
"choices": [
{
"message": {
"content": "* **Issue:** Order 8812 arrived with two damaged boxes.\n* **Request:** Urgent replacement of the damaged items is required before Friday to meet a Saturday trade fair deadline.\n* **Alternative:** If replacements cannot be delivered by Friday, a refund for the two boxes is requested."
}
}
],
"usage": {
"completion_tokens": 66,
"prompt_tokens": 81,
"total_tokens": 147,
"completion_tokens_details": {
"reasoning_tokens": 0
}
}
}Response abridged to the fields the code prints, as the API returned them.

