← All models
O

GPT-5 Mini

OpenAI

Affordable GPT-5 intelligence — brings GPT-5 capability to cost-sensitive workloads

Input price$0.60 / 1M tokens
Output price$2.40 / 1M tokens
Context window512k tokens
Last updated2026-05-20

Quick calculator

tokens
tokens
req/day
Per request
$0.001800
Daily
$18.00
Monthly
$540.00
per month · 30-day estimate
Yearly
$6,570.00

Tips to reduce cost

  • Use prompt caching to reuse repeated system prompts
  • Trim whitespace and reduce verbose instructions
  • Use a smaller model for classification or routing tasks
  • Batch async requests to get 50% discount (OpenAI/Anthropic)
  • Cache identical requests at the application layer

Similar models from OpenAI

Compared at your current token settings

About GPT-5 Mini

GPT-5 Mini is a mid-range large language model from openai, priced at $0.6/1M input tokens and $2.4/1M output tokens. It is 77% cheaper than the market average and best suited for cost-efficient frontier tasks. The 512k context window makes it suitable for very long documents, large codebases, and book-length inputs.

For most production workloads, the cost breakdown is dominated by input tokens (system prompts, context, retrieved documents) rather than output. At this price point, GPT-5 Mini is a solid choice when balancing quality and cost at scale.

GPT-5 Mini supports prompt caching at $0.3/1M — a 50% discount on repeated input tokens. For applications with a fixed system prompt or repeated document context (RAG, chatbots, agents), enabling caching is the single highest-leverage cost optimization available.

Frequently Asked Questions

How much does GPT-5 Mini cost per 1,000 tokens?
GPT-5 Mini costs $0.0006 per 1,000 input tokens and $0.0024 per 1,000 output tokens.
What is GPT-5 Mini's context window?
GPT-5 Mini supports a context window of 512k tokens, which is suitable for very long documents, large codebases, and extended multi-turn conversations.
How does GPT-5 Mini compare to GPT-4o on price?
GPT-5 Mini is 77% cheaper than the market average on input tokens. At $0.6/1M input vs $2.50/1M for GPT-4o, the cost difference becomes significant at scale — 10,000 requests/day with 1,000 input tokens each costs $180/month with GPT-5 Mini vs $750/month with GPT-4o.
Does GPT-5 Mini support prompt caching?
Yes. GPT-5 Mini supports prompt caching at $0.3/1M tokens — a 50% discount on repeated input. This is especially effective for RAG pipelines and chatbots with large system prompts that repeat across requests.

Compare GPT-5 Mini with other models

GPT-5 Mini vs DeepSeek R1GPT-5 Mini vs Gemini 3 FlashGPT-5 Mini vs Mistral Large 3GPT-5 Mini vs Llama 4 MaverickGPT-5 Mini vs Mistral Medium 3GPT-5 Mini vs Claude 3.5 Haiku