← Models

GPT-5 mini

OpenAI · GPT-5

Older cost-efficient GPT-5 variant now mainly useful for compatibility after GPT-5.4 mini became the recommended fresh-build route.

Part of GPT family · Other versions: GPT-5.6 Luna , GPT-5.6 Terra , GPT-5.6 Sol , GPT-5.5 Pro , GPT-5.5 , GPT-Rosalind , GPT-5.4 mini , GPT-5.4 nano , GPT-5.4 Pro , GPT-5.4 , GPT-5.3 , GPT-5.3-Codex , GPT-5.2-Codex , GPT-5.2 Pro , GPT-5.2 , GPT-5-Codex , GPT-5 nano , GPT-5 , GPT-4.1 , GPT-4o mini Transcribe , GPT-4o mini TTS , GPT-4o Transcribe , Computer Use Preview , GPT-4o mini , GPT-4o
Type
language
Context
400K tokens
Max Output
128K tokens
Status
legacy
Input
$0.25/1M tok
Output
$2/1M tok
API Access
Yes
License
proprietary
reasoning cost-efficient tool-use coding production
Released August 2025 · Updated June 8, 2026

Overview

Freshness note: Model capabilities, limits, and pricing can change quickly. This profile is a point-in-time snapshot last verified on June 8, 2026.

GPT-5 mini is designed as a lower-cost member of the GPT-5 family for teams that need strong baseline quality with tighter budget control. It still fits production scenarios where request volume matters more than absolute frontier depth, but OpenAI’s current model docs now recommend GPT-5.4 mini as the better starting point for most new low-latency, high-volume workloads.

Capabilities

The model is effective for structured summarization, extraction, routing logic, and general coding assistance in medium-complexity tasks. It typically performs well when prompts include clear constraints and output format requirements.

Technical Details

GPT-5 mini is positioned for production throughput with 400K context, 128K max output, image input support, and modern tool-use support. It is best treated as a generalist tier for scalable workflows that do not always require flagship-level reasoning depth, especially in systems already pinned to older GPT-5 behavior.

Pricing & Access

Access is available via OpenAI API surfaces. Published text-token pricing remains 0.25per1Minputtokens,0.25 per 1M input tokens, 0.025 per 1M cached input tokens, and $2.00 per 1M output tokens. Newer GPT-5.4 mini routing is now the recommended path for most fresh mini-tier builds.

Best Use Cases

Choose GPT-5 mini mainly for high-volume assistants, internal knowledge operations, triage workflows, and standardized document-processing pipelines that are already tuned to this older model. For a new OpenAI mini-tier build, start evaluation with GPT-5.4 mini.

Comparisons

Compared with GPT-5.4 mini, GPT-5 mini is cheaper but materially weaker on current coding, computer-use, and tool benchmarks. Compared with o4-mini, GPT-5 mini is still a stronger general-purpose GPT-5-era default for mixed workloads. Compared with Gemini 2.5 Flash, selection usually depends on ecosystem integration and workload characteristics.