distil-whisper-large-v3-en to whisper-large-v3-turbo
Some values not published Checked 2026-10-26.
Price per 1M tokens
| Field | Old | New | Change |
|---|---|---|---|
| Input | Not published | Not published | Not published |
| Output | Not published | Not published | Not published |
| Cached input | Not published | Not published | Not published |
| Example monthly cost | Not published | Not published | Example only |
Context and max output
| Limit | Old | New | Change |
|---|---|---|---|
| Context window | Not published | Not published | Not published |
| Max output | Not published | Not published | Not published |
Capabilities that differ
No differing capability values are published for both models.
Endpoint changes
- The Groq API reference says transcriptions are POST https://api.groq.com/openai/v1/audio/transcriptions. It names whisper-large-v3 and whisper-large-v3-turbo as the model ids currently available. The sample only changes the model field. Source
Code
python before
from groq import Groq
client = Groq()
transcription = client.audio.transcriptions.create(
file=("sample_audio.m4a", open("sample_audio.m4a", "rb").read()),
model="distil-whisper-large-v3-en",
)
python after
from groq import Groq
client = Groq()
transcription = client.audio.transcriptions.create(
file=("sample_audio.m4a", open("sample_audio.m4a", "rb").read()),
model="whisper-large-v3-turbo",
)
typescript before
import fs from "fs";
import Groq from "groq-sdk";
const groq = new Groq();
const transcription = await groq.audio.transcriptions.create({
file: fs.createReadStream("sample_audio.m4a"),
model: "distil-whisper-large-v3-en",
});
typescript after
import fs from "fs";
import Groq from "groq-sdk";
const groq = new Groq();
const transcription = await groq.audio.transcriptions.create({
file: fs.createReadStream("sample_audio.m4a"),
model: "whisper-large-v3-turbo",
});
curl before
curl https://api.groq.com/openai/v1/audio/transcriptions \
-F file="@./sample_audio.m4a" \
-F model="distil-whisper-large-v3-en"
curl after
curl https://api.groq.com/openai/v1/audio/transcriptions \
-F file="@./sample_audio.m4a" \
-F model="whisper-large-v3-turbo"
Checklist
- Read the shutdown date for distil-whisper-large-v3-en on the linked official page.
- Point your requests at whisper-large-v3-turbo.
- Re-check price, context, and parameters on the provider pages linked here.
- Ship the change before the published shutdown date.