← Models

GPT-4o mini

OpenAI · GPT-4o

Lower-cost GPT-4o API tier for high-volume text-plus-image assistant and automation workloads.

Part of GPT family · Other versions: 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 mini , GPT-5 , GPT-5 nano , GPT-4.1 , GPT-4o mini Transcribe , GPT-4o mini TTS , GPT-4o Transcribe , GPT-4o
Type
multimodal
Context
128K tokens
Max Output
16K tokens
Status
current
Input
$0.15/1M tok
Output
$0.6/1M tok
API Access
Yes
License
proprietary
multimodal cost-efficient assistant automation production
Released July 2024 · Updated May 16, 2026

Overview

Freshness note: Model capabilities, limits, and pricing can change quickly. This profile is a point-in-time snapshot last verified on May 16, 2026.

GPT-4o mini is OpenAI’s cost-efficient GPT-4o API tier for production workloads where volume and latency matter. OpenAI’s current model card still presents it as a fast, affordable small model that accepts text and image inputs, produces text outputs, and remains useful for fine-tuning and distillation-style workflows even as product defaults have moved forward to newer GPT-5 routes.

Capabilities

The model performs well on concise reasoning, extraction, summarization, classification, and common workflow automation tasks. It supports multimodal patterns at materially lower operating cost than higher-end tiers, which keeps it relevant for cost-sensitive API systems and high-volume product features.

Technical Details

OpenAI’s current model docs still list GPT-4o mini at a 128K context window with 16,384 max output tokens. The model is positioned as a focused-task small model rather than a frontier route, but it remains practical when prompts are structured, outputs are validated, and the workload does not need the stronger reasoning behavior of newer GPT-5-family models.

Pricing & Access

OpenAI’s current pricing docs still list GPT-4o mini at 0.15per1Minputtokens,0.15 per 1M input tokens, 0.075 cached input, and $0.60 per 1M output tokens. It remains available through OpenAI API model endpoints and is still one of the cheaper multimodal OpenAI routes for text-plus-image input.

Best Use Cases

Strong fit for high-throughput support assistants, operations automations, content normalization, extraction pipelines, and product features requiring reliable but cost-sensitive inference.

Comparisons

Compared with GPT-4o, GPT-4o mini trades quality headroom for significantly lower cost. Compared with GPT-5 mini or newer GPT-5.5-era routes, GPT-4o mini remains useful for compatibility and cheap text-plus-image workloads but is no longer the strongest current GPT-family default. Compared with Gemini 2.5 Flash-Lite, both target efficient scale with different ecosystem and modality tradeoffs.