---
id: "openai/gpt-5.4"
also: ["openai/gpt-5.4-20260305", "requesty/openai/gpt-5.4", "vercel/openai/gpt-5.4"]
card_usd_per_m: "2.5 in, 15.0 out, at openai"
cheapest_list_usd_per_m: "1.25 in, 7.5 out, at openai/flex on openrouter"
cheapest_effective_usd_per_m: "0.9128 in, 15.0058 out, at openai on openrouter"
context: 1050000
max_output: 128000
input: ["text", "image", "file"]
output: ["text"]
released: "2026-03-05"
reasoning: ["xhigh", "high", "medium", "low", "none"]
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "reasoning_effort", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "verbosity"]
endpoints: 21
gateways: "requesty (11), openrouter (8), vercel (2)"
no_training: 20
trains: 0
retains_prompts: 6
coding: 71.1000
---
# OpenAI: GPT-5.4

GPT 5.4 is OpenAI's frontier model designed for complex professional workloads, with strong reasoning, high reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large scale reasoning, coding, and multimodal workflows within a single system.