Pricing per million tokens, context window, capabilities — pulled from each provider's public docs. All 2 are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.
Google's most capable Gemini 4 reasoning model, built for complex software engineering, math and science problems, autonomous multi-step agents, and long outputs up to 1M tokens.
o3 is OpenAI’s general-purpose reasoning model, balancing strong analytical performance with reasonable latency and cost.
from openai import OpenAI
client = OpenAI(
base_url="https://api.aigateway.sh/v1",
api_key="sk-aig-...",
)
# Gemini 4 Carbon
client.chat.completions.create(
model="google/gemini-4-carbon",
messages=[{"role":"user","content":"hello"}],
)
# O3
client.chat.completions.create(
model="openai/o3",
messages=[{"role":"user","content":"hello"}],
)