impulse

Whisper Medium

Frontier labTranscription
API id whisper-medium
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
-
tokens
Max output
-
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Where to run it

1 host serve Whisper Medium. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
whisper-medium
-

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text

Similar models

This model has no listed price, so these are current models with similar capabilities.

Smaller OpenAI models

Other frontier labs

Open-weight picks

Call it

Using Deepgram's API.

Python
from litellm import completion

response = completion(
    model="deepgram/whisper-medium",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

Which APIs offer Whisper Medium?

Whisper Medium runs on 1 API: Deepgram.

Is Whisper Medium being retired?

No retirement date is scheduled for it on any API we track.

What is Whisper Medium's API model id?

Use whisper-medium with Deepgram.

Sources

Raw catalog entry for whisper-medium on Deepgram
{
  "input_cost_per_second": 0.0001,
  "litellm_provider": "deepgram",
  "metadata": {
    "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models"
  },
  "mode": "audio_transcription",
  "output_cost_per_second": 0,
  "source": "https://deepgram.com/pricing",
  "supported_endpoints": [
    "/v1/audio/transcriptions"
  ]
}