GPT-5.3 Chat

GPT-5.3 Chat is a chat-tuned GPT model from OpenAI for conversational assistance, writing, and tool workflows. It is part of the gpt line, released on 2026-03-03, succeeding GPT-5.1. It has a context window of 128000 tokens and a maximum output of 16384 tokens. It accepts image and text inputs and returns text. It supports tool calling but not reasoning mode. The weights are not open. Pricing starts at $1.75 per million input tokens and $14.00 per million output tokens, with cached input at $0.175 per million tokens.

Against GPT-5.1: window 400K to 128K, input $1.00 to $1.75, output $8.00 to $14.00, cached input $0.104 to $0.175.

• ·Tool calling for workflows
• ·Accepts image and text inputs
• ·128k token context window
• ·16k token max output
• ·Knowledge cutoff August 2025

• Reach for it for conversational assistance
• Reach for it for writing tasks
• Reach for it for tool workflows
• Reach for it for image and text inputs

6 hosts serve this model at the price above · the maker's documentation

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

What is the context window?

The context window is 128000 tokens, and the maximum output is 16384 tokens.

Does it support tool calling?

Yes, it supports tool calling. It does not support reasoning mode.

What is the price?

Input costs from $1.75 per million tokens, output from $14.00 per million tokens. Cached input is $0.175 per million tokens.