About GPT-5 mini
GPT-5 mini is the mid-size member of the GPT-5 family, offered by OpenAI for well-defined tasks that need solid reasoning without flagship cost — the role previously held by o4-mini, which OpenAI lists mini as succeeding. It handles text and image input with text output, and keeps the same reasoning-effort controls and tool integrations as its larger sibling.
The design intent is precision at a price: workloads with clear instructions and bounded scope — support automation, structured extraction, code review at scale — are its home ground, with the full family context window available when documents run long.
Mini's economics reward prompt discipline: its rates are a fraction of GPT-5's, and with cached input the recurring cost of a stable system prompt nearly vanishes. Output remains the dominant term, so tight response formats — JSON schemas, forced brevity — pay for themselves directly. It is the natural landing spot for traffic migrating off the retired o-series reasoning tiers, and the step down to nano is available when tasks turn out simpler than expected. Batch processing discounts asynchronous work further; the calculator on this page prices your exact token mix against both siblings.
Frequently asked questions
How much does the GPT-5 mini API cost?
GPT-5 mini costs $0.25 per million input tokens and $2 per million output tokens, with cached input at $0.025 per million (90% off).
How much does a typical chat message cost with GPT-5 mini?
A short chat message (about 500 input and 250 output tokens) costs roughly $0.0006 with GPT-5 mini. At 1,000 such requests a day, that is about $18.75 per month.
Is GPT-5 mini cheap compared to similar models?
GPT-5 mini has the #6 cheapest input rate of the 29 models we track. On a mixed workload (10K input / 2K output), it costs $0.0065 per request and $0.0070 for DeepSeek V4 Flash.
What does GPT-5 mini cost per 1,000 tokens?
Per 1,000 tokens, GPT-5 mini costs $0.00025 for input and $0.0020 for output, or $0.00003 for cached input. Providers quote rates per million tokens ($0.25/M in, $2/M out here), so divide by a thousand for the per-1K figure older pricing pages used.
How large a prompt can GPT-5 mini take?
GPT-5 mini accepts up to 391K tokens of input context and can generate up to 125K tokens of output per request. At its input rate, filling the entire 391K-token window costs about $0.100 per request before any output.
Related
Compare all models at once ·Count tokens in your prompt · GPT-5 mini vs Gemini 2.5 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 nano · GPT-4o · GPT-4o mini · o3 · o4-mini
Last updated 2026-09-03. Prices verified against OpenAI's official pricing page; see the methodology.