GPT-5.5 Text to Text API
openai/gpt-5.5GPT-5.5 turns text instructions and conversation history into code, analysis, and detailed answers across a 1M-token context. Supply source files, task constraints, and acceptance criteria to guide multi-step reasoning and agent workflows.
GPT-5.5
OpenAI · chat-completions
Quick start
Send a POST request to /v1/chat/completions with openai/gpt-5.5. Choose JSON or SSE with stream, and receive generated content and usage.
- Endpoint
- POST /v1/chat/completions
- Model ID
- openai/gpt-5.5
- Protocol
- Chat Completions
Request fields
| Field | Requirement | Description |
|---|---|---|
| model | Required | openai/gpt-5.5 |
| messages | Required | A non-empty array of conversation messages. |
| max_tokens | Optional | A positive integer setting the output limit; the model API maximum is 128,000 tokens, and the playground offers 256–8,192. |
| temperature | Optional | Sampling temperature; the playground allows 0–2. |
| top_p | Optional | Nucleus sampling probability; the playground allows 0–1. |
| stream | Optional | Returns an SSE event stream when true. |
Response and usage
Successful responses include generated content and usage. Billing settles from actual input, output, and cache tokens.
Streaming
Set stream: true to read SSE. Finalize usage accounting from the terminal usage event.
curl --request POST \
--url https://api.vidgo.ai/v1/chat/completions \
--header "Authorization: Bearer $VIDGO_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "openai/gpt-5.5",
"messages": [
{
"role": "user",
"content": "Explain why deterministic retries matter in distributed systems."
}
],
"max_tokens": 1024,
"temperature": 1,
"top_p": 1,
"stream": false
}'Keep API keys on the server. Never expose them in browser code or public repositories.
Continue with
Related Models
GPT-5.5 API frequently asked questions
What is the GPT-5.5 API?
GPT-5.5 is an OpenAI text model for coding, long-context analysis, and agent planning. It generates code, explanations, and detailed answers from text instructions and conversation history. Its 1M-token context connects related source material, while Responses reasoning controls let you set an effort level for closer analysis. You can call it programmatically or try it in the playground above.
How much context can GPT-5.5 examine?
GPT-5.5 has a 1M-token context window. Include the specifications, source files, and conversation turns that bear on the question, with labels that identify each source.
What output length can GPT-5.5 produce?
The model API maximum is 128K output tokens. Set max_tokens in Chat Completions or max_output_tokens in Responses; the on-page Playground offers 256–8,192 tokens for interactive use.
How can GPT-5.5 help with code across files?
Provide relevant files, target behavior, and acceptance criteria together. GPT-5.5 can connect dependencies across those files and draft an implementation or review for you to check against the source.
How do I set GPT-5.5 reasoning effort?
In a Responses request, set reasoning.effort to a value such as medium. State the task constraints and review the answer against the evidence you supplied.
Which GPT-5.5 protocol fits a conversation workflow?
Use Chat Completions with an ordered messages array for a conversation. Use Responses with input and optional reasoning.effort for structured input and reasoning controls.
How should GPT-5.5 analyze long documents?
Give each document a title and mark the relevant sections. Ask a specific comparison question so GPT-5.5 can relate findings to the supplied passages.