---
title: "Text2Text Completions"
method: POST
path: "/text2text/chat/completions"
tags: ["Text2Text"]
---

# Text2Text Completions

`POST /text2text/chat/completions`

The *Text2Text Completion* service helps generate a text based on the text introduced as input by the user. It also takes the pain out of writing to give your social, marketing, and advertising copy a premium edge.

## Request body

- object
  - `messages` object[], required — The messages containing the original text and instructions.
    - `role` string — Each message object has a role (either system, user, or assistant) and content. The system message is optional and can be used to set the behavior of the assistant The user messages provide requests or comments for the assistant to respond to Assistant messages store previous assistant responses, but can also be written by you to give examples of desired behavior.
    - `content` string
  - `max_tokens` number
  - `temperature` number
  - `model` 'urn:air:openai:model:openai:gpt-5@1' | 'urn:air:openai:model:openai:gpt-5-search-api@1' | 'urn:air:openai:model:openai:gpt-5.1@1' | 'urn:air:openai:model:openai:gpt-5.1-chat@1' | 'urn:air:openai:model:openai:gpt-5.2@1' | 'urn:air:openai:model:openai:gpt-5-mini@1' | 'urn:air:openai:model:openai:gpt-5-nano@1' | 'urn:air:openai:model:openai:gpt-4o@1' | 'urn:air:openai:model:openai:gpt-4o-mini@1' | 'urn:air:openai:model:openai:gpt-4o-search-preview@1' | 'urn:air:openai:model:openai:gpt-4-turbo@1' | 'urn:air:openai:model:openai:gpt-4.1@1' | 'urn:air:openai:model:openai:gpt-4.1-mini@1' | 'urn:air:openai:model:openai:gpt-4.1-nano@1' | 'urn:air:openai:model:openai:gpt-3.5-turbo@1' | 'urn:air:anthropic:model:anthropic:claude-sonnet-4-5-latest@1' | 'urn:air:anthropic:model:anthropic:claude-sonnet-4-6@1' | 'urn:air:google:model:google:gemini-2.0-flash-001@1' | 'urn:air:google:model:google:gemini-2.0-flash-lite@1' | 'urn:air:google:model:google:gemini-2.5-pro@1' | 'urn:air:google:model:google:gemini-2.5-flash@1' | 'urn:air:google:model:google:gemini-3-pro-preview@1', nullable — Optionally choose a specific AI model to use for this request. If not specified, a default model will be applied. Please note that the default model may change over time as Picsart continues to improve performance and accuracy. Any change to the default will be made only after thorough testing and validation to ensure it delivers better results. If you require consistent behavior or wish to evaluate different models on your own, we recommend explicitly setting this parameter.

## Response `200`

Success.

- object
  - `status` string
  - `data` string — The response to the provided messages/instructions.

## Other responses

- `400` — Bad Request
- `401` — Unauthorized
- `402` — Payment Required
- `403` — Forbidden
- `404` — Not Found
- `405` — Method Not Allowed
- `413` — Request Entity Too Large
- `415` — Unsupported Media Type
- `429` — Too Many Requests
- `431` — Request Header Fields Too Large
- `500` — Internal Server Error
- `503` — Service Unavailable

---

[API](https://skmtc.net/picsart/apis/picsart-programmable-image-apis.md) · [All operations](https://skmtc.net/picsart/apis/picsart-programmable-image-apis/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/picsart/picsart-programmable-image-apis/revisions/726b2a637ae8/schema)