API reference

Chat

POSThttps://api.oneover.com/functions/v1/api-v1-chatScope: chat

Stateless chat completions across every text model. Streaming and non-streaming. Prompts are not retained after the response.

Request body

Parameters

Name	Type	Required	Description
`model`	`string`	Yes	Text model ID from your catalog (GET api-v1-models?type=text).
`messages`	`array`	Yes	Conversation turns: { role: "system"\|"user"\|"assistant", content: string }.
`stream`	`boolean`	No	If true, returns Server-Sent Events instead of JSON.
`max_tokens`	`number`	No	Optional completion budget cap.

Examples

Request

curl -X POST "https://api.oneover.com/functions/v1/api-v1-chat" \
  -H "Authorization: Bearer oo_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.6-sol",
    "messages": [
      { "role": "user", "content": "Hello from OneOver" }
    ],
    "stream": false
  }'

Non-streaming response

200 OK

{
  "request_id": "uuid",
  "model": "gpt-5.6-sol",
  "message": { "role": "assistant", "content": "..." },
  "credits_charged": 4,
  "balance": { "subscription": 14996, "anytime": 5000 },
  "efficiency": {
    "original_message_count": 5,
    "compacted_message_count": 3,
    "original_estimated_tokens": 4200,
    "compacted_estimated_tokens": 2800,
    "tokens_saved": 1400,
    "actions": ["dropped_2_old_turns"]
  }
}

Streaming (SSE)

Content-Type: text/event-stream. Each line is data: {...}.

Event types

Name	Type	Required	Description
`connection_established`	`event`	No	Handshake with request_id.
`content`	`event`	No	Token chunk in content field.
`done`	`event`	No	Final event with credits_charged, balance, efficiency.
`error`	`event`	No	Failure during stream.

Try it in the Playground.