GPT-5.4 Mini vs GPT-5.4 Nano: same limits, different token prices
Within the GPT-5.4 family, the documented token ceilings match for Mini and Nano. Their text prices differ, giving you a cost comparison before any task-specific quality evaluation.
The documented limits are the same
Both entries list 400,000 shared context tokens, a 272,000 input-token limit and 128,000 maximum output. Show differences only removes those identical facts while leaving their API IDs and prices visible. Equal ceilings describe request capacity, not equal task behavior.
Scale a realistic mix of input and output
Mini lists $0.75 input and $4.50 output per million tokens; Nano lists $0.20 and $1.25. Cached input reads use a separate rate. A thousand short requests and a few long answers can lead to different budgets even with the same total number of user actions.
Keep the decision measurable
Both use the OpenAI Responses API and have verified structured-output and function-calling support in this catalogue. Preserve an acceptance set when evaluating either model. This page does not assume that a family name, size label or lower price establishes comparative accuracy.
Documented specifications and standard direct API rates, manually checked 2026-10-09. Evaluation suggestions are editorial guidance; no measured comparative quality or speed is claimed.
Unknown fields are not evidence of equal capabilities. Specifications describe support, not comparative answer quality.
BENCHMARK EVIDENCE
No reliable data available
Comparable results with confirmed reuse permission have not been published here yet.
A published result must include the exact model version, benchmark version, original value and unit, test date, conditions and source. No scores or overall rankings are inferred.
Text tokens only. Billable output includes reasoning tokens where applicable. Excludes cache creation, tools, media and regional or processing-tier uplifts.
Text tokens only. Billable output includes reasoning tokens where applicable. Excludes cache creation, tools, media and regional or processing-tier uplifts.
KNOW YOUR API COST
A small prompt. A clearer budget.
Same token counts for both models. Standard paid text rates in USD. Output must include all billable reasoning tokens.
Cached input is included in total input. No cache creation/storage, tools, media, taxes or regional/priority/Batch fees. Tokenizers differ; equal token counts do not imply equal text length.
4 estimated credits / comparison4,000 credits across 1,000 comparisons.Reference estimate only. Playground uses verified OpenRouter charges; 1,000 credits = $1. A + B round up together once for each comparison.
See how your prompt behaves.
Choose an enabled official model pair in the Playground. Your maximum reservation is shown before running; confirmed usage determines the final charge.