---
id: "openai/gpt-5"
also: ["openai/gpt-5-2025-08-07", "requesty/openai/gpt-5", "vercel/openai/gpt-5"]
card_usd_per_m: "1.25 in, 10.0 out, at openai/default"
cheapest_list_usd_per_m: "1.25 in, 10.0 out, at azure on openrouter"
cheapest_effective_usd_per_m: "0.5883 in, 10.0 out, at openai on requesty"
context: 400000
max_output: 128000
input: ["text", "image", "file"]
output: ["text"]
released: "2025-08-07"
reasoning: ["high", "medium", "low", "minimal"]
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", "tool_choice", "tools", "verbosity"]
endpoints: 14
gateways: "requesty (9), openrouter (3), vercel (2)"
no_training: 14
trains: 0
retains_prompts: 3
coding: 37.8000
---
# OpenAI: GPT-5

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like "think hard about this." Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.