Create a chat completion

curl --request POST \
  --url https://api.altrum.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "openai/gpt-4o-mini",
  "messages": [
    {
      "role": "user",
      "content": "Say hello."
    }
  ]
}
'

import requests

url = "https://api.altrum.ai/v1/chat/completions"

payload = {
    "model": "openai/gpt-4o-mini",
    "messages": [
        {
            "role": "user",
            "content": "Say hello."
        }
    ]
}
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-4o-mini', messages: [{role: 'user', content: 'Say hello.'}]})
};

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

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 2,
    "total_tokens": 11
  }
}

{
  "type": "budget_exceeded",
  "is_gateway_error": true,
  "status_code": 402,
  "error": {
    "type": "budget_exceeded",
    "code": "budget_exceeded",
    "message": "Budget exceeded: ..."
  },
  "request_id": "4f9c..."
}

{
  "type": "budget_exceeded",
  "is_gateway_error": true,
  "status_code": 402,
  "error": {
    "type": "budget_exceeded",
    "code": "budget_exceeded",
    "message": "Budget exceeded: ..."
  },
  "request_id": "4f9c..."
}

{
  "type": "budget_exceeded",
  "is_gateway_error": true,
  "status_code": 402,
  "error": {
    "type": "budget_exceeded",
    "code": "budget_exceeded",
    "message": "Budget exceeded: ..."
  },
  "request_id": "4f9c..."
}

{
  "type": "budget_exceeded",
  "is_gateway_error": true,
  "status_code": 402,
  "error": {
    "type": "budget_exceeded",
    "code": "budget_exceeded",
    "message": "Budget exceeded: ..."
  },
  "request_id": "4f9c..."
}

{
  "type": "budget_exceeded",
  "is_gateway_error": true,
  "status_code": 402,
  "error": {
    "type": "budget_exceeded",
    "code": "budget_exceeded",
    "message": "Budget exceeded: ..."
  },
  "request_id": "4f9c..."
}

{
  "type": "budget_exceeded",
  "is_gateway_error": true,
  "status_code": 402,
  "error": {
    "type": "budget_exceeded",
    "code": "budget_exceeded",
    "message": "Budget exceeded: ..."
  },
  "request_id": "4f9c..."
}

{
  "type": "budget_exceeded",
  "is_gateway_error": true,
  "status_code": 402,
  "error": {
    "type": "budget_exceeded",
    "code": "budget_exceeded",
    "message": "Budget exceeded: ..."
  },
  "request_id": "4f9c..."
}

{
  "type": "budget_exceeded",
  "is_gateway_error": true,
  "status_code": 402,
  "error": {
    "type": "budget_exceeded",
    "code": "budget_exceeded",
    "message": "Budget exceeded: ..."
  },
  "request_id": "4f9c..."
}

{
  "type": "budget_exceeded",
  "is_gateway_error": true,
  "status_code": 402,
  "error": {
    "type": "budget_exceeded",
    "code": "budget_exceeded",
    "message": "Budget exceeded: ..."
  },
  "request_id": "4f9c..."
}

POST

chat

completions

Create a chat completion

curl --request POST \
  --url https://api.altrum.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "openai/gpt-4o-mini",
  "messages": [
    {
      "role": "user",
      "content": "Say hello."
    }
  ]
}
'

import requests

url = "https://api.altrum.ai/v1/chat/completions"

payload = {
    "model": "openai/gpt-4o-mini",
    "messages": [
        {
            "role": "user",
            "content": "Say hello."
        }
    ]
}
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-4o-mini', messages: [{role: 'user', content: 'Say hello.'}]})
};

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

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 2,
    "total_tokens": 11
  }
}

{
  "type": "budget_exceeded",
  "is_gateway_error": true,
  "status_code": 402,
  "error": {
    "type": "budget_exceeded",
    "code": "budget_exceeded",
    "message": "Budget exceeded: ..."
  },
  "request_id": "4f9c..."
}

{
  "type": "budget_exceeded",
  "is_gateway_error": true,
  "status_code": 402,
  "error": {
    "type": "budget_exceeded",
    "code": "budget_exceeded",
    "message": "Budget exceeded: ..."
  },
  "request_id": "4f9c..."
}

{
  "type": "budget_exceeded",
  "is_gateway_error": true,
  "status_code": 402,
  "error": {
    "type": "budget_exceeded",
    "code": "budget_exceeded",
    "message": "Budget exceeded: ..."
  },
  "request_id": "4f9c..."
}

{
  "type": "budget_exceeded",
  "is_gateway_error": true,
  "status_code": 402,
  "error": {
    "type": "budget_exceeded",
    "code": "budget_exceeded",
    "message": "Budget exceeded: ..."
  },
  "request_id": "4f9c..."
}

{
  "type": "budget_exceeded",
  "is_gateway_error": true,
  "status_code": 402,
  "error": {
    "type": "budget_exceeded",
    "code": "budget_exceeded",
    "message": "Budget exceeded: ..."
  },
  "request_id": "4f9c..."
}

{
  "type": "budget_exceeded",
  "is_gateway_error": true,
  "status_code": 402,
  "error": {
    "type": "budget_exceeded",
    "code": "budget_exceeded",
    "message": "Budget exceeded: ..."
  },
  "request_id": "4f9c..."
}

{
  "type": "budget_exceeded",
  "is_gateway_error": true,
  "status_code": 402,
  "error": {
    "type": "budget_exceeded",
    "code": "budget_exceeded",
    "message": "Budget exceeded: ..."
  },
  "request_id": "4f9c..."
}

{
  "type": "budget_exceeded",
  "is_gateway_error": true,
  "status_code": 402,
  "error": {
    "type": "budget_exceeded",
    "code": "budget_exceeded",
    "message": "Budget exceeded: ..."
  },
  "request_id": "4f9c..."
}

{
  "type": "budget_exceeded",
  "is_gateway_error": true,
  "status_code": 402,
  "error": {
    "type": "budget_exceeded",
    "code": "budget_exceeded",
    "message": "Budget exceeded: ..."
  },
  "request_id": "4f9c..."
}

Authorizations

Authorization

string

header

required

Your virtual key, sk-alt-.... What every OpenAI and Anthropic SDK sends.

Headers

x-request-id

string

Your own reference for the request. Altrum uses it instead of making one, and returns it.

x-alt-prompt-id

string

Use a prompt saved in your AI Gateway prompts. Its messages go before yours.

x-alt-prompt-version

integer

The prompt version to use, such as 2. Without it, the latest version.

x-alt-cache-key

string

Keeps this request's cached answers apart from others, for example per customer.

x-alt-cache-ttl

string

Keeps the answer for less time than your setting: 30s, 5m, 1h or a number of seconds.

x-alt-cache-threshold

number

Asks for a closer match than your setting, from 0 to 1.

x-alt-cache-type

enum<string>

direct matches word for word only, semantic by meaning only.

Available options:

direct,

semantic

x-alt-cache-no-store

enum<string>

true serves from the cache when it can, but does not store this answer.

Available options:

true

x-alt-disable-content-logging

enum<string>

true keeps this request's prompt and reply out of the request log, even when your organization keeps content.

Available options:

true

x-alt-direct-key

enum<string>

true sends your own provider key in Authorization, x-api-key or x-goog-api-key, with your virtual key in x-alt-vk. Only when your organization allows it.

Available options:

true

Body

application/json

An OpenAI chat completion request. Every other field the OpenAI API accepts is passed to the model.

model

string

required

The provider and the model, such as openai/gpt-4o-mini. A name without a provider is matched to one your organization can serve.

Example:

"openai/gpt-4o-mini"

messages

object[]

required

The conversation, in the OpenAI chat format.

stream

boolean

Stream the answer as server-sent events.

fallbacks

string[]

Models to try in order when an attempt fails. Altrum's addition to the request body.

Response

The completion.

An OpenAI chat completion.

Overview

OpenAI format

Anthropic format

Gemini format

MCP

Create a chat completion

Authorizations

Headers

Body

Response