Back to the index
OpenAI · GPT
No. 10

GPT-5.4 mini

Affordable OpenAI workhorse for standard production routing.

FastClosed weightsText, Image, Pdf
Field notes
Context window
400Ktokens
Max output
128Ktokens
Input price
$0.75/ 1M tokens
Output price
$4.50/ 1M tokens
Cached input
$0.07/ 1M tokens
Modalities
Text, Image, Pdf
Knowledge cutoff
Oct 2025
Released
Mar 2026
Approx. speed
—
Overview

What this model is

GPT-5.4 mini is OpenAI's affordable production workhorse, handling the bulk of standard routed traffic at a fraction of flagship cost. It delivers solid reasoning and coding for everyday tasks with a 400K context and full multimodal input, and is a strong default for cost-conscious applications that escalate to GPT-5.5 for the hardest jobs.

Strengths

  • Strong value for standard production work
  • Good coding and reasoning for the price
  • 400K-token context and multimodal input
  • Fast and cheap enough for high volume
  • Steep prompt-cache discount

Trade-offs

  • Not frontier-reliable for long-horizon agentic coding
  • Below flagship on hard reasoning
  • Smaller context than the 5.4/5.5 flagships

Best for

  • Standard production routing
  • Cost-sensitive coding assistants
  • Chat and support backends
  • RAG and summarization at scale
  • Lightweight agents

Not ideal for

  • Hard autonomous coding runs
  • Frontier research-grade reasoning
Capabilities

Capability profile

Normalized 0–100 scores, comparable across the whole catalog.

Reasoning84Coding82Math85Writing85Knowledge84Speed85Agentic80Vision82Multilingual86Long Context85
Reasoning
84
Coding
82
Math
85
Writing
85
Knowledge
84
Speed
85
Agentic
80
Vision
82
Multilingual
86
Long Context
85
Benchmarks

How it scores

Public benchmark results, with independent third-party results where available. Bars normalize percentages to 100 and Elo ratings to a 1500 ceiling.

Independent index
Artificial Analysis Intelligence Index
Composite of ~9–10 independent evals · Artificial Analysis
40/ 100
BenchmarkResult
Artificial Analysis Intelligence Indexindependent
GeneralArtificial Analysis
40%
SWE-bench Verifiedindependent
CodingSWE-bench
58.4%
MMLU-Pro
KnowledgeVendor-reported
55.3%
DeepSWEindependent
CodingDatacurve
24%
Alternatives

Comparable models

Models in a roughly similar class — worth weighing against this one.

GPT-5.4 nanoOpenAI

OpenAI's cheapest small model for high-volume simple work.

Gemini 3.5 FlashGoogle DeepMind

Fast, cheap multimodal workhorse with near-Pro quality.

Claude Haiku 4.5Anthropic

Fastest, cheapest Claude — snappy everyday tasks at scale.