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

GPT-4o-mini (2024-07-18)Deprecated

OpenAI
VisionTool usePrompt cachingStructured output
Context
128K
Max output
16K
Serving providers
3
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: ARC Prize
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
ARC-AGI-20%default$0.010

Pricing by serving provider

last-known · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
OpenAI$0.15$0.601
OpenRouter$0.15$0.601
Azure$0.17$0.661

Price history

input + output $/1M since we started tracking
Input Output
$0.000$0.200$0.400$0.600Jul 18Dec 24Mar 13Jul 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
gpt-4o-mini-2024-07-18openai/gpt-4o-mini-2024-07-18azure/eu/gpt-4o-mini-2024-07-18

Frequently asked questions

GPT-4o-mini (2024-07-18) pricing, context and availability

Is GPT-4o-mini (2024-07-18) still available?

GPT-4o-mini (2024-07-18) 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 (2024-07-18) cost?

GPT-4o-mini (2024-07-18)'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 (2024-07-18)?

GPT-4o-mini (2024-07-18) had a 128K token context window and could return up to 16K output tokens.

What could GPT-4o-mini (2024-07-18) do?

GPT-4o-mini (2024-07-18) supported image input (vision), tool use, prompt caching and structured output.

Other OpenAI models

compare pricing across the OpenAI lineup
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