Pricing, context window, capabilities, and release date — pulled from each provider's public docs. Both are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.
Both models stream in parallel through your own AIgateway key. Tokens, latency, and cost update as they arrive.
| GPT-4o Transcribe openai/gpt-4o-transcribe | GPT-4.1 openai/gpt-4.1 | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Family | GPT-4 | GPT-4 |
| Modality | audio-stt | text |
| Context window | — | 1,047,576 tok |
| Max output | — | 32,768 tok |
| Released | 2026-05-22 | 2026-05-22 |
| Input price | $0.0060 /min | $2.00 /1M |
| Output price | — | $8.00 /1M |
| Cache read | — | — |
| Tools | — | yes |
| Streaming | — | yes |
| Vision | — | — |
| JSON mode | — | yes |
| Reasoning | — | — |
| Prompt caching | — | — |
A speech-to-text model that uses GPT-4o to transcribe audio with improved word error rate and better language recognition compared to original Whisper models.
OpenAI's flagship GPT model for complex tasks with a million-token context window.
# pip install aigateway-py openai
# aigateway-py: sub-accounts, evals, replays, jobs, webhook verify.
# openai SDK: chat/embeddings/images/audio — drop-in compat per our SDK's own guidance.
from openai import OpenAI
client = OpenAI(
base_url="https://api.aigateway.sh/v1",
api_key="sk-aig-...",
)
# Try GPT-4o Transcribe
client.chat.completions.create(
model="openai/gpt-4o-transcribe",
messages=[{"role":"user","content":"hello"}],
)
# Try GPT-4.1 — same client, same key
client.chat.completions.create(
model="openai/gpt-4.1",
messages=[{"role":"user","content":"hello"}],
)