openai/gpt-4o-mini

Aliases: 4o-mini, mini

$0.15

Input / 1M

$0.60

Output / 1M

128K

Context

145 t/s

Speed

Public benchmark scores

Sourced from each provider's published numbers. Verify before quoting.

Quality index

MMLU

GPQA

40.2

HumanEval

87.2

MATH

70.2

SWE-bench

—

Arena Elo

—

Sources: openai-research-page

Capabilities

toolsvisionjson_modestructured_outputstreaming

Input modalities: text, image, file

Use gpt-4o-mini via Relay

Configure the model alias in YAML, then call it from Python.

YAML

# models.yaml
version: 1
models:
  4o-mini:
    target: openai/gpt-4o-mini
    credential: $env.OPENAI_API_KEY

Python

from relay import Hub

async with Hub.from_yaml("models.yaml") as hub:
    resp = await hub.chat(
        "4o-mini",
        messages=[{"role": "user", "content": "Hello"}],
    )
    print(resp.text, resp.cost_usd)

pip install ai5labs-relay · full docs on GitHub

Compare with

vs anthropic/claude-haiku-4-5 vs mistral/mistral-large-latest vs groq/llama-3.3-70b-versatile vs anthropic/claude-3-5-sonnet-20241022