impulse

Whisper

Frontier labTranscription
API id whisper
Azure AI Foundry, Azure OpenAI retire it on 15 Dec 2026 (in 27 days). 2 hosts keep serving it.
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
-
tokens
Max output
-
tokens per reply
Hosts
4
4 listings
Released
-
date not published

Where to run it

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

HostIn / out per 1M
whisper
-
Retires 15 Dec 2026
whisper
-
Retires 15 Dec 2026
-
whisper
-

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 Azure OpenAI's API.

Python
from litellm import completion

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

Quick answers

Which APIs offer Whisper?

Whisper runs on 4 APIs: Azure OpenAI, Azure AI Foundry, Cloudflare Workers AI and Deepgram.

Is Whisper being retired?

Azure AI Foundry and Azure OpenAI retire it on 15 Dec 2026. 2 hosts keep serving it.

What is Whisper's API model id?

Use whisper with Azure OpenAI.

Sources

Raw catalog entry for whisper on Azure OpenAI
{
  "deprecation_date": "2026-12-15",
  "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule",
  "input_cost_per_second": 0.0001,
  "litellm_provider": "azure",
  "mode": "audio_transcription",
  "output_cost_per_second": 0.0001,
  "source": "https://management.azure.com/subscriptions/a88257a5-3323-4ef9-95bf-5681a46c9624/providers/Microsoft.CognitiveServices/locations/eastus/models?api-version=2024-10-01"
}