openai/o3-deep-research

$10.00

Input / 1M

$40.00

Output / 1M

200K

Context

—

Speed

Capabilities

json_modetoolsvision

Input modalities: image, text, file

Use o3-deep-research via Relay

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

YAML

# models.yaml
version: 1
models:
  o3:
    target: openai/o3-deep-research
    credential: $env.OPENAI_API_KEY

Python

from relay import Hub

async with Hub.from_yaml("models.yaml") as hub:
    resp = await hub.chat(
        "o3",
        messages=[{"role": "user", "content": "Hello"}],
    )
    print(resp.text, resp.cost_usd)

pip install ai5labs-relay · full docs on GitHub

Compare with

vs groq/llama-3.3-70b-versatile vs anthropic/claude-haiku-4-5 vs mistral/mistral-large-latest vs openai/gpt-4o-mini