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.
Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification.
Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation.
from openai import OpenAI
client = OpenAI(
base_url="https://api.aigateway.sh/v1",
api_key="sk-aig-...",
)
# Whisper
client.chat.completions.create(
model="openai/whisper",
messages=[{"role":"user","content":"hello"}],
)
# Whisper-Large-V3-Turbo
client.chat.completions.create(
model="openai/whisper-large-v3-turbo",
messages=[{"role":"user","content":"hello"}],
)