CtrlAltDebrief
This model was retired on 2027-04-14. The pricing below is the last-known rate, kept for migration reference.

GPT-4o-miniDeprecated

OpenAIReleasedJul 18, 2024KnowledgeSep 2023
VisionTool usePrompt cachingStructured output
Compare GPT-4o-mini
Context
131K
Max output
16K
Serving providers
6
Cheapest input
$0.15 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Speed & latency
Output speed
89 t/s
tokens / second
Time to first token
0.89s
latency
Headline indices
Intelligence Index
6.7
of 100
Coding Index
11.4
of 100
Agentic Index
1.0
of 100
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
GDPval237.9default—
GPQA Diamond43%default—
Humanity's Last Exam4%default—
IFBench31%default—
LiveCodeBench23%default—
Mlcr Overall0default—
MMLU-Pro65%default—
MMMU-Pro42%default—
SciCode23%default—
TerminalBench v2.16%default—
τ-bench Banking3%default—

Pricing by serving provider

last-known · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
Azure$0.15$0.601
Gmi$0.15$0.601
OpenAI$0.15$0.601
Vercel AI Gateway$0.15$0.601
Replicate$0.15$0.601
OpenRouter$0.15$0.601

Price history

input + output $/1M since we started tracking
Input Output
$0.000$0.200$0.400$0.600Jul 18Dec 24Jan 12Jul 19$0.600$0.150

Cost calculator

estimate your monthly spend on this model
$78
estimated / month

Model IDs

copy the exact identifier for your platform
azure/global-standard/gpt-4o-minigmi/openai/gpt-4o-minigpt-4o-minivercel_ai_gateway/openai/gpt-4o-minireplicate/openai/gpt-4o-miniopenai/gpt-4o-mini

Frequently asked questions

GPT-4o-mini pricing, context and availability

Is GPT-4o-mini still available?

GPT-4o-mini was retired on 2027-04-14. The pricing on this page is the last-known rate, kept for migration reference.

How much did GPT-4o-mini cost?

GPT-4o-mini's last-known pricing, before it was retired on 2027-04-14, was $0.15 per 1M input tokens and $0.60 per 1M output tokens.

What was the context window of GPT-4o-mini?

GPT-4o-mini had a 131K token context window and could return up to 16K output tokens.

What could GPT-4o-mini do?

GPT-4o-mini supported image input (vision), tool use, prompt caching and structured output.

Other OpenAI models

compare pricing across the OpenAI lineup
gpt-oss-120b$0.03/1M · 19 providersgpt-oss-20b$0.01/1M · 13 providersGPT-5$1.25/1M · 6 providersGPT-4o$2.50/1M · 6 providersGPT-5 Nano$0.05/1M · 5 providersGPT-4.1 Nano$0.10/1M · 5 providersGPT-5 Mini$0.25/1M · 5 providersGPT-4.1 Mini$0.40/1M · 5 providers

Popular comparisons

head-to-head pages featuring GPT-4o-mini
GPT-4o-mini vs GPT-5 Nanoside-by-side pricing & benchmarks GPT-4o-mini vs GPT-4oside-by-side pricing & benchmarks GPT-4o-mini vs GPT-5 Miniside-by-side pricing & benchmarks GPT-4o-mini vs GPT-4.1 Miniside-by-side pricing & benchmarks GPT-4o-mini vs GPT-4side-by-side pricing & benchmarks
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI