GPT-5 mini

Overview

GPT-5 mini is a reasoning model from OpenAI that offers strong intelligence for cost-sensitive, low-latency, high-volume workloads. It accepts text and image input, returns text, and supports tool calling and structured output. Its context window is 400,000 tokens. It is aimed at workloads where price and response time matter as much as answer quality.

GPT-5 mini has a context window of 400,000 tokens and can generate up to 128,000 output tokens. It accepts text and image input and returns text output. Its knowledge cutoff is May 31, 2024, and it was released on August 7, 2025.

Capabilities

GPT-5 mini supports reasoning, tool calling, structured output and image input, and it returns text. It can generate up to 128,000 output tokens per request, which covers both reasoning and the visible answer.

Its knowledge cutoff is May 31, 2024, and cached input reads have a separate, lower price.

Pricing

GPT-5 mini is billed per token: $0.25 per 1M input tokens and $2.00 per 1M output tokens. Cached input reads cost $0.025 per 1M tokens. GPT-5 mini is available through RealRelay's OpenAI-compatible API.

Use cases

Use GPT-5 mini for high-volume assistants and agents that need some reasoning at a modest price, such as support chat, order lookups through tool calls, or checking a screenshot against a policy.

Its structured output suits pipelines that turn long text or images into fixed fields, with the 400,000-token window holding the full source.