Citation and evidence

GPT-4o mini

10 min full readUpdated 21 references

This article's verification

Report a problem with this article

Edit article
More

Use this article

Raw MarkdownExplore connections

Improve this page

Revision historyDiscuss this article

Topics

Multimodal AIOpenAISmall Language Models

Cite this article

GPT-4o mini is a small, low-cost multimodal large language model developed by OpenAI and released on July 18, 2024, as the company's most cost-efficient model at the time. Priced at $0.15 per million input tokens and $0.60 per million output tokens, more than 60% cheaper than GPT-3.5 Turbo, it replaced GPT-3.5 Turbo as the default lightweight model in OpenAI's API and as the free-tier model in ChatGPT. GPT-4o mini accepts text and image inputs, has a 128,000-token context window, scores 82.0% on MMLU, and was roughly an order of magnitude cheaper than the frontier models of its era, making it the cost-efficient workhorse model of the pre-GPT-5 period. OpenAI described it as "our most cost-efficient small model," positioned to "expand the range of applications built with AI by making intelligence much more affordable." [1][2]

Compare, price, and deploy GPT-4o mini

These sourced facts are shared with the comparison and planning tools. Each field retains its own review date.

GPT-4o mini

Article updated after the pricing / specification review. Inspect the sources before relying on these fields; a newer edit does not necessarily change the model facts.

Provider API lifecycle
DeprecatedSource · checked 2026-10-25
Context tokens
128KSource · checked 2026-10-25
Input / output per 1M tokens
$0.15 / $0.6Source · checked 2026-10-25

OpenAI's Batch table lists no cached-input rate for this model. Rates as listed on October 25, 2026; the provider does not say when they took effect.

Fine-tuned versions follow the same January 14, 2027 shutdown as the base model.

OpenAI logo
OpenAI logo. Source: Wikimedia Commons, Public domain.

Overview

GPT-4o mini belongs to the GPT-4o ("omni") family but is a smaller, distinct model from the full GPT-4o. OpenAI introduced it as a way to expand the range of applications that could be built affordably with AI, citing low-cost use cases such as chaining or parallelizing multiple model calls, passing large volumes of context to a model, and powering fast, real-time text interactions like customer support chatbots. [1]

OpenAI did not disclose the model's parameter count, but described it as occupying roughly the same capability tier as small models such as Gemini 1.5 Flash and Claude 3 Haiku. The company noted that the cost per token of GPT-4o mini had dropped by 99% since text-davinci-003, a less capable model released in 2022, illustrating the rapid decline in inference costs. [1][2]

At launch GPT-4o mini supported text and vision (image) inputs through the API, with OpenAI stating that support for text, image, video, and audio inputs and outputs was planned for the future. [1][4]

What can GPT-4o mini do?

GPT-4o mini is a general-purpose model handling natural language understanding, reasoning, math, coding, and multimodal (text-and-vision) tasks. OpenAI highlighted its strong performance in function calling, which lets developers build applications that fetch data or take actions with external systems, as well as improved long-context performance relative to GPT-3.5 Turbo. [1]

The model uses the same tokenizer as GPT-4o, which is more efficient at handling non-English text than the tokenizer used by GPT-3.5 Turbo. [1] Its 128,000-token context window is large enough to hold roughly a book's worth of text in a single request, and it can generate up to 16,384 output tokens per request. The training data has a knowledge cutoff of October 2023. [4][5]

SpecificationValue
Context window128,000 tokens
Maximum output16,384 tokens
Knowledge cutoffOctober 2023
Input modalitiesText, image (vision)
Output modalitiesText
ReleasedJuly 18, 2024

Expanded article table

On safety, OpenAI stated that GPT-4o mini was the first model to apply its "instruction hierarchy" method, a technique designed to improve the model's ability to resist jailbreaks, prompt injections, and system-prompt extractions. The approach helps the model prioritize developer-supplied system instructions over conflicting user instructions, reducing the effectiveness of attacks such as telling the model to "ignore all previous instructions." [17] OpenAI said this should make the model more reliable for developers deploying it at scale. [1]

How does GPT-4o mini perform on benchmarks?

OpenAI reported that GPT-4o mini outperformed GPT-3.5 Turbo and other small models on academic benchmarks spanning reasoning, math, and coding. On textual reasoning and intelligence as measured by MMLU (Massive Multitask Language Understanding), it scored 82.0%, ahead of Gemini 1.5 Flash at 77.9% and Claude 3 Haiku at 73.8%. On the MGSM benchmark for mathematical reasoning, it scored 87.0%, compared with 75.5% for Gemini 1.5 Flash and 71.7% for Claude 3 Haiku. On HumanEval, which measures coding, it scored 87.2%, ahead of Gemini 1.5 Flash at 71.5% and Claude 3 Haiku at 75.9%. [1][6]

In multimodal reasoning measured by MMMU (Massive Multi-discipline Multimodal Understanding), GPT-4o mini scored 59.4%, compared with 56.1% for Gemini 1.5 Flash and 50.2% for Claude 3 Haiku. OpenAI also reported scores of 70.2% on the MATH benchmark and 79.7% on DROP, a reading-comprehension and reasoning benchmark. [7][15] For comparison, OpenAI's simple-evals table lists Gemini 1.5 Flash at 40.9 on MATH and 78.4 on DROP, and Anthropic reported Claude 3 Haiku at 38.9% on MATH and 78.4 on DROP. [15][16]

BenchmarkGPT-4o miniGemini 1.5 FlashClaude 3 Haiku
MMLU (reasoning)82.0%77.9%73.8%
MGSM (math)87.0%75.5%71.7%
HumanEval (coding)87.2%71.5%75.9%
MMMU (multimodal)59.4%56.1%50.2%
MATH70.2%40.9%38.9%
DROP79.7%78.4 (F1)78.4 (F1)

Expanded article table

OpenAI further noted that, at the time of launch, an earlier version of GPT-4o mini ranked above GPT-4 Turbo (the 01-25 snapshot) on user chat preferences in the LMSYS Chatbot Arena leaderboard. [1][6]

How much does GPT-4o mini cost?

GPT-4o mini launched at $0.15 per million input tokens and $0.60 per million output tokens (15 cents and 60 cents, respectively). OpenAI described this as more than 60% cheaper than GPT-3.5 Turbo, whose pricing had been $0.50 per million input tokens and $1.50 per million output tokens. [1][18]

ModelInput (per 1M tokens)Output (per 1M tokens)
GPT-4o mini$0.15$0.60
GPT-3.5 Turbo$0.50$1.50

Expanded article table

The dramatically lower price was central to OpenAI's positioning of the model, enabling cost-sensitive workloads that would have been impractical with larger or older models. [1][3]

When was GPT-4o mini released and where was it available?

GPT-4o mini became available on July 18, 2024 through the OpenAI API (Assistants API, Chat Completions API, and Batch API) and immediately replaced GPT-3.5 Turbo in ChatGPT for Free, Plus, and Team users. As OpenAI put it, "Free, Plus and Team users will be able to access GPT-4o mini starting today, in place of GPT-3.5." Enterprise users gained access the following week. [1][2]

On July 23, 2024, OpenAI made fine-tuning available for GPT-4o mini, initially to developers on usage tiers 4 and 5, saying it planned to expand access to all tiers. That expansion happened within a month: when OpenAI opened fine-tuning for the full-size GPT-4o on August 20, 2024, it stated that GPT-4o mini fine-tuning was available to all developers on all paid usage tiers. [14] As a limited-time offer, the company provided the first 2 million training tokens per day for free through September 23, 2024. On May 8, 2026, OpenAI said it was winding down its fine-tuning platform, closing it to new users while keeping existing fine-tuned models available until their base models are deprecated. [14] This announcement came shortly after Meta released its open-source Llama 3.1 models, amid intense competition in the small-model market. [8][9]

GPT-4o mini was also offered through Microsoft's Azure OpenAI Service. Although GPT-4o mini replaced GPT-3.5 Turbo as OpenAI's recommended small model, GPT-3.5 Turbo remained available through the API for existing applications. [4]

What replaced GPT-4o mini?

GPT-4o mini served as OpenAI's default budget model for roughly ten months before being superseded. On April 14, 2025, OpenAI released the GPT-4.1 family, including GPT-4.1 mini and GPT-4.1 nano; GPT-4.1 mini replaced GPT-4o mini as the fallback model for all ChatGPT users beginning May 14, 2025. For reasoning-heavy workloads, OpenAI's o-series small model o4-mini (released April 2025) provided a chain-of-thought alternative in the same low-cost tier. GPT-4o mini's lineage continued with GPT-5 mini, released August 7, 2025 alongside GPT-5, which became the resource-efficient fallback for free ChatGPT users. [12][19][20]

ModelReleasedRole
GPT-3.5 Turbo2023Prior default budget model
GPT-4o miniJuly 18, 2024Cost-efficient multimodal workhorse
GPT-4.1 miniApril 14, 2025Replaced GPT-4o mini in ChatGPT (May 14, 2025)
o4-miniApril 2025Small reasoning (o-series) model
GPT-5 miniAugust 7, 2025GPT-5-era budget fallback

Expanded article table

On February 13, 2026, OpenAI retired GPT-4o, GPT-4.1, GPT-4.1 mini, and o4-mini from the ChatGPT consumer interface, consolidating around the GPT-5 family, though API deprecation schedules for individual models run separately. [13] On October 14, 2026, OpenAI notified developers that GPT-4o mini (gpt-4o-mini-2024-07-18), along with GPT-4o, GPT-4.1, and GPT-4.1 mini, would be removed from the API on January 14, 2027, naming GPT-6 Luna as the recommended replacement. [21]

Reception

GPT-4o mini was widely covered as a significant move to lower the cost of capable AI. TechCrunch described it as a "smaller and cheaper" model that powered ChatGPT and replaced GPT-3.5 Turbo as OpenAI's smallest offering, quoting Artificial Analysis's measurement of a median output speed of 202 tokens per second, more than twice as fast as GPT-4o and GPT-3.5 Turbo. [2] VentureBeat characterized it as a "smaller, much cheaper multimodal AI model" and emphasized its competitive benchmark results against rival small models. [4]

Commentators framed the launch as part of an escalating price and capability race among providers of small, fast models, including Google's Gemini 1.5 Flash and Anthropic's Claude 3 Haiku, with OpenAI's free fine-tuning offer interpreted as a direct response to Meta's Llama 3.1 release. [8][9] Outlets such as TechRadar covered the launch under the framing of bidding "goodbye" to GPT-3.5, reflecting the model's role in superseding the older default. [11]

What are GPT-4o mini's limitations?

GPT-4o mini is a small model and is less capable than larger frontier models, including the full GPT-4o, on the most demanding reasoning, knowledge, and multimodal tasks; OpenAI positioned it for cost-efficient and high-volume workloads rather than maximum capability. Its knowledge is fixed at an October 2023 cutoff, so it lacks awareness of events after that date unless supplemented with external context. [4][5]

At launch the model's multimodal support was limited to text and image inputs and text outputs; the audio and video capabilities that OpenAI said were planned were not available at release. [1][4] As with other large language models, GPT-4o mini can produce inaccurate or fabricated information ("hallucinations"), and OpenAI's instruction-hierarchy safety method reduces but does not entirely eliminate the risk of jailbreaks and prompt-injection attacks. [1]

Continue reading

More to read

Topics:Multimodal AIOpenAISmall Language Models

References

  1. ^1 ^2 ^3 ^4 ^5 ^6 ^7 ^8 ^9 ^10 ^11 ^12 ^13 ^14OpenAI. "GPT-4o mini: advancing cost-efficient intelligence." July 18, 2024. openai.com/...dvancing-cost-efficient-intelligence
  2. ^1 ^2 ^3 ^4Zeff, Maxwell. "OpenAI unveils GPT-4o mini, a smaller and cheaper AI model." TechCrunch, July 18, 2024. techcrunch.com/...-small-ai-model-powering-chatgpt
  3. ^Campus Technology. "OpenAI Launches Slimmer, Cheaper GPT-4o Mini." July 18, 2024. campustechnology.com/...limmer-cheaper-gpt-4o-mini
  4. ^1 ^2 ^3 ^4 ^5 ^6Franzen, Carl. "OpenAI unveils GPT-4o mini, a smaller and much cheaper multimodal AI model." VentureBeat, July 18, 2024. venturebeat.com/...uch-cheaper-multimodal-ai-model
  5. ^1 ^2DocsBot AI. "OpenAI's GPT-4o Mini - AI Model Details." docsbot.ai/...gpt-4o-mini
  6. ^1 ^2DataCamp. "What Is GPT-4o Mini? How It Works, Use Cases, API & More." datacamp.com/...gpt-4o-mini
  7. ^LLM Stats. "GPT-4o mini Benchmarks, Pricing & Context Window." llm-stats.com/...gpt-4o-mini-2024-07-18
  8. ^1 ^2OpenAI Developers (@OpenAIDevs). "Customize GPT-4o mini for your application with fine-tuning." X, July 23, 2024. x.com/...1815836887631946015
  9. ^1 ^2Nunez, Michael. "AI arms race escalates: OpenAI offers free GPT-4o Mini fine-tuning to counter Meta's Llama 3.1 release." VentureBeat, July 23, 2024. venturebeat.com/...counter-metas-llama-3-1-release
  10. Microsoft Azure. "OpenAI's fastest model, GPT-4o mini is now available on Azure AI." azure.microsoft.com/...s-now-available-on-azure-ai
  11. ^TechRadar. "Goodbye GPT-3.5, OpenAI's new GPT-4o mini AI model is all about compact power." July 19, 2024. techradar.com/...-model-is-all-about-compact-power
  12. ^OpenAI. "Introducing GPT-4.1 in the API." April 14, 2025. openai.com/...gpt-4-1
  13. ^OpenAI. "Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT." 2026. openai.com/...retiring-gpt-4o-and-older-models
  14. ^1 ^2OpenAI. "Fine-tuning now available for GPT-4o." August 20, 2024. openai.com/...gpt-4o-fine-tuning
  15. ^1 ^2OpenAI. "simple-evals" (benchmark results table). GitHub. github.com/...simple-evals
  16. ^Anthropic. "Introducing the next generation of Claude." March 4, 2024. anthropic.com/...claude-3-family
  17. ^Robison, Kylie. "OpenAI's latest model will block the 'ignore all previous instructions' loophole." The Verge, July 19, 2024. theverge.com/...pt-injection-instruction-hierarchy
  18. ^OpenAI. "New embedding models and API updates." January 25, 2024. openai.com/...new-embedding-models-and-api-updates
  19. ^Disotto, John-Anthony. "OpenAI just gave ChatGPT users a huge free upgrade, 4.1 mini is available today." TechRadar, May 15, 2025. techradar.com/...grade-4-1-mini-is-available-today
  20. ^OpenAI. "Introducing GPT-5." August 7, 2025. openai.com/...introducing-gpt-5
  21. ^OpenAI. "Deprecations." OpenAI API documentation. developers.openai.com/...deprecations

Improve this article

Add missing citations, update stale details, or write a clearer explanation. Anyone can edit: changes go live when you publish, and every edit is checked by an editor.

7 revisions · v7 · 2,056 words · full history

Fact-checks are independent of edits: a reviewer re-verifies the article against its sources and stamps the date. How we verify

Research and drafting on this wiki are AI-assisted, under named human editorial standards. How AI is used here

Reviewer note: Independent fact-check of the full article against its cited sources (72 claims, 23 sources fetched); 7 material + 9 minor fixed

Cite this page: AI Wiki. "GPT-4o mini." aiwiki.ai, updated 1 Nov 2026, fact-checked 2 Nov 2026. CC BY 4.0. https://aiwiki.ai/wiki/gpt_4o_mini

Edit article