Vibe Coding

Creates a model response. Provide text or image inputs to generate text or JSON outputs. Supports tool calling and conversation state.

Authorization

bearerAuth

AuthorizationBearer <token>

In: header

Request Body

application/json

TypeScript Definitions

Use the request body type in TypeScript.

model?string

glm-5 (vibe coding), gpt-5.1-codex, gpt-5.1-codex-max or gpt-5.2-codex.

input?|array<>

Text, image, file, or chat-style inputs. The Responses API accepts a string or an array of input items/messages.

instructions?string

A system (or developer) message inserted into the model's context.

background?boolean

Whether to run the model response in the background.

Defaultfalse

store?boolean

Whether to store the generated model response for later retrieval via API.

Defaulttrue

previous_response_id?string

The unique ID of the previous response to the model. Cannot be used with 'conversation'.

conversation?|

Conversation that this response belongs to. Items are prepended to the request. Cannot be used with 'previous_response_id'.

include?array<>

Additional output data to include in the response.

max_output_tokens?integer

Upper bound for generated tokens (includes visible output tokens and reasoning tokens).

Range1 <= value

max_tool_calls?integer

Maximum total built-in tool calls processed in a response.

Range0 <= value

parallel_tool_calls?boolean

Whether to allow tool calls in parallel.

Defaulttrue

tools?array<>

Tools the model may call (built-in tools, MCP tools, or developer-defined function tools).

tool_choice?|

How the model should select which tool(s) to use.

text?

Configuration options for a text response from the model (plain text or structured JSON).

reasoning?

Reasoning configuration (gpt-5 and o-series models).

temperature?number

Default1

Range0 <= value <= 2

top_p?number

Default1

Range0 <= value <= 1

top_logprobs?integer

Number of most likely tokens to return per position with logprobs.

Range0 <= value <= 20

truncation?string

Truncation strategy when input exceeds the model context window.

Default"disabled"

Value in"auto" | "disabled"

stream?boolean

If true, stream the response via server-sent events.

Defaultfalse

stream_options?

Options for streaming responses (only when stream=true).

Defaultnull

metadata?

Up to 16 key/value pairs for storing structured metadata.

prompt?

Reference to a prompt template and its variables.

prompt_cache_key?string

Cache key used to help optimize prompt caching.

prompt_cache_retention?string

Retention policy for prompt cache (e.g. '24h').

safety_identifier?string

Stable identifier for abuse detection (recommended to hash username/email).

service_tier?string

Processing tier (e.g., auto/default/flex/priority).

Default"auto"

user_id?string

Hashed user indentify for improved monitoring and abuse detection.

Response Body

`application/json`

curl -X POST "https://api.vivgrid.com/v1/responses" \  -H "Content-Type: application/json" \  -d '{    "model": "glm-5",    "input": "Create a amazon-like web app."  }'

{
  "id": "string",
  "object": "string",
  "created_at": 0,
  "model": "string",
  "status": "string",
  "output": [
    {}
  ],
  "usage": {},
  "service_tier": "string"
}

{
  "error": {
    "message": "string",
    "type": "string",
    "param": "string",
    "code": "string"
  }
}

Vibe Coding

Authorization

Request Body

Response Body

200application/json

defaultapplication/json

`application/json`

`application/json`