/ Models

Language models

OpenAI: GPT-4o-mini (2024-07-18)

GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...

Maker
Openai
Context window
128K
Max output
16K
Input / 1M
$0.15
Output / 1M
$0.6
1M in + 1M out
$0.75

Everything else

Max output16K
Input / 1M$0.15
Output / 1M$0.6
Cache read / 1M$0.075
Cache write / 1M
1M in + 1M out$0.75
Takestext, image, file
Returnstext
Toolsyes
Reasoningno
Open weightsno
Released2024-07-18
Knowledge cutoff2023-10-31
Retires
Catalog idopenai/gpt-4o-mini-2024-07-18

Benchmarks

sourceepoch
gpqa0.377
gpqaStderr0.0241
mathLevel50.526
mathLevel5Stderr0.0113
aime0.069
aimeStderr0.0274

Benchmark scores by Epoch AI, CC BY 4.0.

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models