GPT-4o-mini

Provider: OpenAI US Official API price

Input price
$0.15
/ 1M tokens
Output price
$0.60
/ 1M tokens
Cache price
$0.075
/ 1M tokens (read)
Batch API
$0.075 / $0.30
input / output per 1M tokens
Context
128K tokens
Max output 16K tokens

Overview

GPT-4o-mini is OpenAI's cost-optimized model, designed for versatility within the broader GPT-4o family. It targets a wide range of developer-centric workloads requiring multi-modal input, large context, and structured output capabilities.

Strengths

  • Cost-effective pricing for both input ($0.15/1M tokens) and output ($0.6/1M tokens).
  • Supports vision capabilities for processing and understanding image-based inputs.
  • Robust function-calling and JSON mode for structured data interaction and API integration.
  • Features a substantial 128,000 token context window for extensive input processing.
  • Generous maximum output of 16,384 tokens suitable for detailed responses.

Best use cases

  • Developing applications that require multi-modal input processing, such as image analysis.
  • Automating complex workflows through structured function calls and JSON outputs.
  • Building intelligent chatbots or agents that require understanding long conversations or documents.
  • Generating detailed reports, summaries, or structured code with extensive context.
  • Cost-effectively powering applications where vision and precise, structured responses are critical.

Pricing position

GPT-4o-mini is positioned as a cost-optimized option within OpenAI's lineup, with input at $0.15/1M tokens and output at $0.6/1M tokens. This makes it more expensive than GPT-5 Nano and GPT-4.1 Nano, but significantly more affordable than GPT-5 Mini, GPT-4.1 Mini, and GPT-5.4 Nano. Its pricing directly matches Llama 4 Maverick and Mistral Small 4, though Ministral 3 8B 2512 offers much cheaper output at $0.15/M tokens.

Caveats

This model does not offer a free tier, meaning all usage incurs charges from the outset. For text-only tasks that do not require vision or a 128K token context, OpenAI's GPT-5 Nano and GPT-4.1 Nano provide lower input and output costs. Additionally, consider Ministral 3 8B 2512 for applications where minimizing output token cost is the primary concern, as it offers a significantly lower output price.

Notes drafted by an LLM from the figures on this page (2026-05-21) and rewritten when the price changes.

Key facts

Price basis
Official API price
Max output
16K tokens
Knowledge cutoff
2023-10-31
Listed on OpenRouter
2024-07-18
Tracked since
2026-05-08
Last updated
2026-11-10

Features

Image inputFunction callingJSON output

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.04
1M (small app) 1 0.5 $0.45
10M (mid scale) 10 5 $4.50
100M (large) 100 50 $45.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from OpenAI

Similar-priced models

Source: OpenRouter API (openai/gpt-4o-mini)