AnyoneLearnAI
LevelEasyStart

Reference · API

OpenAI Chat Completions API

Send multi-turn messages; get assistant replies. Use **server-side** only.

Send multi-turn messages; get assistant replies. Use **server-side** only.

Endpoint

POST https://api.openai.com/v1/chat/completions

Core request fields

| Field | Purpose |

|-------|---------|

| `model` | e.g. `gpt-4o-mini`, `gpt-4o` |

| `messages` | `{role, content}` array — system, user, assistant |

| `temperature` | 0–2 creativity |

| `max_tokens` | Cap output length |

| `stream` | `true` for token streaming |

Minimal Python

from openai import OpenAI
client = OpenAI()
resp = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "system", "content": "You are concise."},
        {"role": "user", "content": "Explain RAG in one sentence."},
    ],
)
print(resp.choices[0].message.content)

Messages shape

[
  {"role": "system", "content": "Rules and persona"},
  {"role": "user", "content": "Question"},
  {"role": "assistant", "content": "Prior reply"},
  {"role": "user", "content": "Follow-up"}
]

Related

Try the interactive lesson →
← All API docs