OpenAI-compatible chat completion

curl --request POST \
  --url https://secureai.hiperai.ai/api/external/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "openai/gpt-5-nano",
  "messages": [
    {
      "content": "<string>"
    }
  ],
  "temperature": 123,
  "max_tokens": 123,
  "stream": true,
  "models": [
    "<string>"
  ],
  "fallback_models": [
    "<string>"
  ],
  "redundancy": {},
  "smltp_policy": "<string>",
  "prompt_shield": {}
}
'

import requests

url = "https://secureai.hiperai.ai/api/external/v1/chat/completions"

payload = {
    "model": "openai/gpt-5-nano",
    "messages": [{ "content": "<string>" }],
    "temperature": 123,
    "max_tokens": 123,
    "stream": True,
    "models": ["<string>"],
    "fallback_models": ["<string>"],
    "redundancy": {},
    "smltp_policy": "<string>",
    "prompt_shield": {}
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'openai/gpt-5-nano',
    messages: [{content: '<string>'}],
    temperature: 123,
    max_tokens: 123,
    stream: true,
    models: ['<string>'],
    fallback_models: ['<string>'],
    redundancy: {},
    smltp_policy: '<string>',
    prompt_shield: {}
  })
};

fetch('https://secureai.hiperai.ai/api/external/v1/chat/completions', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

POST

chat

completions

OpenAI-compatible chat completion

curl --request POST \
  --url https://secureai.hiperai.ai/api/external/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "openai/gpt-5-nano",
  "messages": [
    {
      "content": "<string>"
    }
  ],
  "temperature": 123,
  "max_tokens": 123,
  "stream": true,
  "models": [
    "<string>"
  ],
  "fallback_models": [
    "<string>"
  ],
  "redundancy": {},
  "smltp_policy": "<string>",
  "prompt_shield": {}
}
'

import requests

url = "https://secureai.hiperai.ai/api/external/v1/chat/completions"

payload = {
    "model": "openai/gpt-5-nano",
    "messages": [{ "content": "<string>" }],
    "temperature": 123,
    "max_tokens": 123,
    "stream": True,
    "models": ["<string>"],
    "fallback_models": ["<string>"],
    "redundancy": {},
    "smltp_policy": "<string>",
    "prompt_shield": {}
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'openai/gpt-5-nano',
    messages: [{content: '<string>'}],
    temperature: 123,
    max_tokens: 123,
    stream: true,
    models: ['<string>'],
    fallback_models: ['<string>'],
    redundancy: {},
    smltp_policy: '<string>',
    prompt_shield: {}
  })
};

fetch('https://secureai.hiperai.ai/api/external/v1/chat/completions', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

OpenAI-Compatible Endpoint

SecureAI exposes an OpenAI-compatible surface so you can integrate with any OpenAI SDK by changing only the base URL and API key — no code changes. The full SecureAI security stack (API-key auth, model/index allowlists, SMLTP policy enforcement + entitlements, Prompt Shield, PII/DLP, points billing, and the model redundancy engine) runs underneath.

Endpoint

POST /api/external/v1/chat/completions
GET  /api/external/v1/models

Point your OpenAI client’s base_url at:

https://{customer.name}.hiperai.ai/api/external/v1

Zero-Knowledge onlyThis surface does not support RAG / knowledge bases. Requests are pinned to Zero-Knowledge. If you need knowledge-base retrieval, use the classic Chat Completion endpoint.

Authentication

Authorization: Bearer sk-your-api-key-here

Using an OpenAI SDK

Python (`openai`)

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-api-key-here",
    base_url="https://{customer.name}.hiperai.ai/api/external/v1",
)

resp = client.chat.completions.create(
    model="openai/gpt-5-nano",
    messages=[{"role": "user", "content": "Hello!"}],
    # SecureAI extensions travel via extra_body
    extra_body={
        "smltp_policy": "internal",
        "fallback_models": ["anthropic/claude-sonnet-4"],
    },
)
print(resp.choices[0].message.content)
print(resp.model_extra["secureai"]["served_model"])

JavaScript (`openai`)

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-your-api-key-here',
  baseURL: 'https://{customer.name}.hiperai.ai/api/external/v1',
});

const resp = await client.chat.completions.create({
  model: 'openai/gpt-5-nano',
  messages: [{ role: 'user', content: 'Hello!' }],
  // @ts-expect-error — SecureAI extension fields
  smltp_policy: 'internal',
  fallback_models: ['anthropic/claude-sonnet-4'],
});
console.log(resp.choices[0].message.content);

Request Body

Standard OpenAI fields are supported. messages is required (there is no prompt on this surface). max_completion_tokens is accepted as an alias for max_tokens. The following OpenAI parameters are passed through to the provider as-is: tools, tool_choice, parallel_tool_calls, response_format, stop, top_p, frequency_penalty, presence_penalty, seed, logprobs, top_logprobs, user.

SecureAI extension fields

Send these as extra body fields (via extra_body in the OpenAI SDKs):

Field	Description
`smltp_policy`	SMLTP security policy for this call.
`prompt_shield`	`{ enabled?, policy? }` — per-call Prompt Shield override.
`models` / `fallback_models`	Model redundancy chain.
`redundancy`	`{ timeout_ms, first_token_timeout_ms, on[] }`.
`user_id`	Bill to a different user (admin-gated).

Response

Standard OpenAI chat.completion shape, plus a secureai extension object.

{
  "id": "chatcmpl-1a2b3c...",
  "object": "chat.completion",
  "created": 1705312200,
  "model": "anthropic/claude-sonnet-4",
  "choices": [
    { "index": 0, "message": { "role": "assistant", "content": "Hello!" }, "finish_reason": "stop" }
  ],
  "usage": { "prompt_tokens": 9, "completion_tokens": 3, "total_tokens": 12 },
  "secureai": {
    "served_model": "anthropic/claude-sonnet-4",
    "requested_model": "openai/gpt-5-nano",
    "failover": { "occurred": true, "attempts": [ ... ] },
    "smltp_policy_used": "internal",
    "smltp_policy_source": "request",
    "smltp_policy_hash": "a1b2c3...",
    "prompt_shield_policy": null,
    "smltp_bundle_id": "bnd_..."
  }
}

secureai.smltp_bundle_id (when present) can be exchanged for a signed compliance receipt.

Streaming

Set stream: true. Frames are native OpenAI chat.completion.chunk objects terminated by data: [DONE]. The secureai extension is attached to the first chunk. choices (including tool_calls deltas and finish_reason) pass through untouched.

Errors

Errors from this handler use the OpenAI envelope:

{ "error": { "message": "you must provide a model parameter", "type": "invalid_request_error", "code": null } }

When a whole redundancy chain fails, the error uses code: "all_models_failed" and status 429 (all rate limits) or 502 (otherwise). Security-middleware rejections keep the SecureAI { "success": false, ... } shape; both always carry a message.

Chat Completion — the classic surface (adds RAG).
Redundancy & Failover
Prompt Shield API

Authorizations

Authorization

string

header

required

API key authentication using Bearer token format. Example: Authorization: Bearer sk-your-api-key-here

Body

application/json

model

string

required

Example:

"openai/gpt-5-nano"

messages

object[]

required

Show child attributes

temperature

number

max_tokens

integer

stream

boolean

models

string[]

fallback_models

string[]

redundancy

object

{ timeout_ms, first_token_timeout_ms, on[] }

smltp_policy

string

prompt_shield

object

{ enabled?, policy? } per-call Prompt Shield override

Response

OpenAI chat.completion object plus a secureai extension

Primeros Pasos & Setup

Modelos & Generación AI

Knowledge Base & RAG

Seguridad, Guardrails & Auditoría

Usuarios & Acceso (IAM)

Facturación, Cuotas & Webhooks

OpenAI-Compatible Endpoint

OpenAI-Compatible Endpoint

Endpoint

Authentication

Using an OpenAI SDK

Python (`openai`)

JavaScript (`openai`)

Request Body

SecureAI extension fields

Response

Streaming

Errors

Authorizations

Body

Response

​OpenAI-Compatible Endpoint

​Endpoint

​Authentication

​Using an OpenAI SDK

​Python (openai)

​JavaScript (openai)

​Request Body

​SecureAI extension fields

​Response

​Streaming

​Errors

​Related

Authorizations

Body

Response

OpenAI-Compatible Endpoint

Endpoint

Authentication

Using an OpenAI SDK

Python (`openai`)

JavaScript (`openai`)

Request Body

SecureAI extension fields

Response

Streaming

Errors

Related