impulse

GPT-4o Mini Transcribe

Frontier labTranscriptionRetiring 26 Feb 2027
API id gpt-4o-mini-transcribeReleased 20 Mar 2025 (Mar 2025)
OpenAI (2025-03-20 only) retires it on 20 Jan 2027 (in 63 days); OpenAI on 26 Feb 2027. 2 hosts keep serving it.
Input / 1M
$1.25
at OpenAI
Output / 1M
$5.00
at OpenAI
Context window
16K
tokens
Max output
2K
tokens per reply
Hosts
3
5 listings
Released
Mar 2025
20 Mar 2025

Pricing

List prices at OpenAI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$1.25$5.00

What it costs a month

At OpenAI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$750
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$780
  • Coding agent1,000 requests a day, 40K in / 2K out$1,800
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$4,200
Use your own numbers

Where to run it

3 hosts serve GPT-4o Mini Transcribe. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
OpenAILab API
gpt-4o-mini-transcribe
$1.25 / $5.00
Retires 26 Feb 2027
gpt-4o-mini-transcribe
$1.25 / $5.00
Retires 15 Jun 2027
ReplicateInference
gpt-4o-mini-transcribe
$3.00 / $5.00
+60% vs headline
Show 2 more listings: regions, snapshots and variants
OpenAI
2025-03-20
gpt-4o-mini-transcribe-2025-03-20
$1.25 / $5.00
Retires 20 Jan 2027
2025-12-15
gpt-4o-mini-transcribe-2025-12-15
$1.25 / $5.00
Retires 26 Feb 2027

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

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than OpenAI.

Smaller OpenAI models

No cheaper OpenAI model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

No cheaper open-weight match.

Call it

Using OpenAI's API.

Python
from openai import OpenAI

client = OpenAI()  # reads OPENAI_API_KEY

response = client.responses.create(model="gpt-4o-mini-transcribe", input="Hello")
print(response.output_text)

Quick answers

How much does GPT-4o Mini Transcribe cost?

On OpenAI, GPT-4o Mini Transcribe costs $1.25 per million input tokens and $5.00 per million output tokens.

Which APIs offer GPT-4o Mini Transcribe?

GPT-4o Mini Transcribe runs on 3 APIs: OpenAI, Azure OpenAI and Replicate.

What is GPT-4o Mini Transcribe's context window?

16K tokens, with up to 2K tokens in one reply.

Is GPT-4o Mini Transcribe being retired?

OpenAI (2025-03-20 only) retires it on 20 Jan 2027; OpenAI on 26 Feb 2027; Azure OpenAI on 15 Jun 2027. 1 host keeps serving it.

When was GPT-4o Mini Transcribe released?

OpenAI released it on 20 Mar 2025.

What is GPT-4o Mini Transcribe's API model id?

Use gpt-4o-mini-transcribe with OpenAI.

Sources

Raw catalog entry for gpt-4o-mini-transcribe on OpenAI
{
  "input_cost_per_audio_token": 0.000003,
  "input_cost_per_token": 0.00000125,
  "litellm_provider": "openai",
  "max_input_tokens": 16000,
  "max_output_tokens": 2000,
  "mode": "audio_transcription",
  "output_cost_per_token": 0.000005,
  "supported_endpoints": [
    "/v1/audio/transcriptions"
  ],
  "deprecation_date": "2027-02-26",
  "deprecation_source": "https://developers.openai.com/api/docs/deprecations",
  "successor_model": "gpt-live-transcribe",
  "input_cost_per_second": 0.00005,
  "source": "https://developers.openai.com/api/docs/pricing"
}