About GPT-4o mini
GPT-4o mini was OpenAI's workhorse small model of the omni generation — the default budget choice for API developers through the period when GPT-4o led the lineup. It shares the omni design: text and image input, text output, and a context window that was generous for its class at release.
OpenAI maintains it for the many production systems tuned to its exact behaviour, where even small model swaps force re-validation. Its role in new architectures has passed to the GPT-5 family's mini and nano tiers, which offer more context and deeper cache discounts at comparable or lower list prices.
The list price is friendly but the surrounding economics have moved on: GPT-5 nano sits below GPT-4o mini on both input and output while carrying a far larger context window, so cost alone no longer argues for staying. What does argue for staying is inertia of the good kind — validated prompts, measured failure modes, known latency. Cached input halves rather than nearly disappearing, a meaningful difference for services that resend a large system prompt with every call. Price a representative day of traffic on both models with the calculator on this page; the answer is usually decisive.
Frequently asked questions
How much does the GPT-4o mini API cost?
GPT-4o mini costs $0.15 per million input tokens and $0.6 per million output tokens, with cached input at $0.075 per million (50% off).
How much does a typical chat message cost with GPT-4o mini?
A short chat message (about 500 input and 250 output tokens) costs roughly $0.0002 with GPT-4o mini. At 1,000 such requests a day, that is about $6.75 per month.
Is GPT-4o mini cheap compared to similar models?
GPT-4o mini has the #3 cheapest input rate of the 29 models we track. On a mixed workload (10K input / 2K output), it costs $0.0027 per request, versus $0.0018 for Gemini 2.5 Flash-Lite and $0.0070 for DeepSeek V4 Flash.
What does GPT-4o mini cost per 1,000 tokens?
Per 1,000 tokens, GPT-4o mini costs $0.00015 for input and $0.00060 for output, or $0.00007 for cached input. Providers quote rates per million tokens ($0.15/M in, $0.6/M out here), so divide by a thousand for the per-1K figure older pricing pages used.
How large a prompt can GPT-4o mini take?
GPT-4o mini accepts up to 125K tokens of input context and can generate up to 16K tokens of output per request. At its input rate, filling the entire 125K-token window costs about $0.019 per request before any output.
Related
Compare all models at once ·Count tokens in your prompt · GPT-4o mini vs DeepSeek V4 Flash head-to-head
All OpenAI model costs: GPT-5.6 Sol · GPT-5.6 Terra · GPT-5.6 Luna · GPT-5.4 · GPT-5 · GPT-5 mini · GPT-5 nano · GPT-4o · o3 · o4-mini
Last updated 2026-09-03. Prices verified against OpenAI's official pricing page; see the methodology.