# GPT-4o mini

> OpenAI's cheap, fast small model that replaced GPT-3.5 Turbo as the everyday workhorse.

- Maker: OpenAI
- Line: GPT Mini
- Canonical page: https://ai-tldr.dev/models/gpt-4o-mini/
- Updated: 2026-06-18

## In short

GPT-4o mini is OpenAI's small, low-cost model introduced on July 18, 2024 as the successor to GPT-3.5 Turbo. It has a 128K-token context window and costs $0.15 per million input tokens and $0.60 per million output tokens. You can use it through OpenAI and OpenAI (dated snapshot).

## Facts

| Fact | Value | Source |
| --- | --- | --- |
| Context window | 128K tokens (max output 16,384 tokens) | [1] |
| Input price | $0.15 per 1M tokens | [2] |
| Output price | $0.60 per 1M tokens | [2] |
| Licence | Proprietary (OpenAI commercial terms; available via API and ChatGPT) · API only | [1] |
| Released | 18 July 2024 | [3] |
| Parameters | Not disclosed by OpenAI | [1] |
| Knowledge cutoff | October 2023 | [1] |

## Sources

1. [GPT-4o mini model docs (OpenAI)](https://developers.openai.com/api/docs/models/gpt-4o-mini)
2. [GPT-4o mini announcement (OpenAI)](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/)
3. [OpenAI unveils GPT-4o mini (TechCrunch)](https://techcrunch.com/2024/07/18/openai-unveils-gpt-4o-mini-a-small-ai-model-powering-chatgpt/)

## Overview

GPT-4o mini is OpenAI's small, low-cost model introduced on July 18, 2024 as the successor to GPT-3.5 Turbo. It launched at $0.15 per million input tokens and $0.60 per million output tokens — which OpenAI said made it more than 60% cheaper than GPT-3.5 Turbo — and immediately became the default model for free-tier ChatGPT users while also being available in the API.

Despite the low price, GPT-4o mini posted strong scores for its tier: OpenAI reported 82.0% on MMLU, 87.0% on the MGSM math benchmark, and 87.2% on HumanEval coding, beating rival small models of the era such as Google's Gemini 1.5 Flash and Anthropic's Claude 3 Haiku on those tests. It carries a 128K-token context window, returns up to 16,384 output tokens per request, and has an October 2023 knowledge cutoff.

At launch GPT-4o mini supported text and vision (image) inputs with text output; OpenAI said video and audio support could come later via the API. For two years it was OpenAI's go-to model for high-volume, latency-sensitive, and cost-sensitive tasks like classification, extraction, summarization, and chat assistants. It remains available through the OpenAI API even after the older 4o-class models were retired from the ChatGPT interface during OpenAI's 2026 legacy-model cleanup.

## Benchmarks

- MMLU (5-shot): 82% ([source](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/))
- MGSM (math, 0-shot CoT): 87% ([source](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/))
- HumanEval (coding): 87.2% ([source](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/))
- MMMU (multimodal reasoning): 59.4% ([source](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/))
- MATH: 70.2% ([source](https://llm-stats.com/models/gpt-4o-mini-2024-07-18))
- GPQA: 40.2% ([source](https://llm-stats.com/models/gpt-4o-mini-2024-07-18))
- DROP (F1): 79.7% ([source](https://llm-stats.com/models/gpt-4o-mini-2024-07-18))

## Pricing

- Input: $0.15 per 1M tokens per 1M tokens
- Output: $0.60 per 1M tokens per 1M tokens

Launch pricing as announced by OpenAI on July 18, 2024; OpenAI stated this was more than 60% cheaper than GPT-3.5 Turbo. Batch API and cached-input discounts apply separately.

Source: https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/

## Strengths

- Very low price — $0.15 input / $0.60 output per million tokens, far cheaper than GPT-4o and a steep cut from GPT-3.5 Turbo
- Fast, low-latency responses suited to high-throughput and real-time workloads
- Strong reasoning and coding for its size class (MMLU 82%, HumanEval 87.2%) — outscored Gemini 1.5 Flash and Claude 3 Haiku at launch
- 128K-token context window — long enough to process large documents and long conversations
- Native vision: accepts image inputs alongside text
- Supports function/tool calling, structured outputs, and fine-tuning

## Best for

- High-volume text classification, tagging, and content moderation where cost per call matters
- Information extraction and structured-data parsing from documents and emails
- Summarization of long documents, transcripts, and chat logs within the 128K window
- Customer-facing chatbots and assistants needing fast, cheap responses
- Drafting, rewriting, and routine coding help where frontier-model quality isn't required
- Function/tool-calling agents and pipelines that fan out many small LLM calls

## How to access

- [OpenAI](https://developers.openai.com/api/docs/models/gpt-4o-mini) — model id `gpt-4o-mini`
- [OpenAI (dated snapshot)](https://developers.openai.com/api/docs/models/gpt-4o-mini) — model id `gpt-4o-mini-2024-07-18`

## GPT Mini versions

- [GPT-5.4 mini](https://ai-tldr.dev/models/gpt-5-4-mini/) (17 March 2026)
- [GPT-5 mini](https://ai-tldr.dev/models/gpt-5-mini/) (7 August 2025)
- GPT-4o mini (18 July 2024) — this page

## FAQ

### How much does GPT-4o mini cost?

At launch (July 18, 2024) OpenAI priced GPT-4o mini at $0.15 per million input tokens and $0.60 per million output tokens — which OpenAI said made it more than 60% cheaper than GPT-3.5 Turbo. Discounts apply for cached inputs and the Batch API.

### What is GPT-4o mini's context window?

GPT-4o mini has a 128K-token context window and can return up to 16,384 tokens of output per request. Its training knowledge runs through October 2023.

### Is GPT-4o mini multimodal?

Yes, for input: it accepts both text and images (vision) and produces text output. At launch OpenAI said audio and video support could be added later via the API.

### Is GPT-4o mini still available?

Yes. It remains a supported model in the OpenAI API with no announced sunset date. The older 4o-class models were removed from the ChatGPT model picker during OpenAI's 2026 legacy-model phase-out, but gpt-4o-mini continues to be offered through the API.

## Links

- [GPT-4o mini announcement (OpenAI)](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/)
- [GPT-4o mini model docs (OpenAI)](https://developers.openai.com/api/docs/models/gpt-4o-mini)
- [OpenAI API pricing](https://openai.com/api/pricing/)
- [OpenAI unveils GPT-4o mini (TechCrunch)](https://techcrunch.com/2024/07/18/openai-unveils-gpt-4o-mini-a-small-ai-model-powering-chatgpt/)
- [GPT-4o mini specs & benchmarks (LLM-Stats)](https://llm-stats.com/models/gpt-4o-mini-2024-07-18)

Source: AI/TLDR LLM registry, https://ai-tldr.dev/models/gpt-4o-mini/