Whisper Large V3: Pricing, Performance & Examples
Whisper Large V3 is a speech-to-text model from OpenAI, released in November 2024, with a 100M-token context window, and pricing from $0.970 per 1M input tokens.
State-of-the-art multilingual transcription with high accuracy. 10.3% WER, 189x real-time speed. Served by Groq.
Whisper Large V3 pricing
Providers
Whisper Large V3 starts at $0.970 per million input tokens via Groq.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 Groq | $0.970 | — | — | 100.0M/— | — | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Whisper Large V3 context window
Input and output token limits for Whisper Large V3, plus how it ranks on long-context understanding.
Whisper Large V3 API
Any audio format up to 25 MB.
Run a request to see the response
Use it in your code
OpenAI-compatible endpoint through the LLM Stats gateway.
import requests
with open("audio.mp3", "rb") as f:
response = requests.post(
"https://gateway.llm-stats.com/v1/stt/transcribe",
headers={"Authorization": "Bearer YOUR_API_KEY"},
files={"file": f},
data={"model_id": "whisper-large-v3"},
)
print(response.json()["text"])Need an API key? Create one above in the playground, or read the API documentation.
Whisper Large V3 latency
Whisper Large V3 time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Whisper Large V3 license
Whisper Large V3 is released under the Apache 2.0 license, which permits commercial use.
- License
- Apache 2.0
- Commercial use allowed
Apache License 2.0 - allows commercial use
FAQ
Common questions about Whisper Large V3.