GPT-4o Transcribe
gpt-4o-transcribePricing
List prices at OpenAI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $2.50 | $10.00 |
What it costs a month
At OpenAI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$1,500
- RAG over documents2,000 requests a day, 8K in / 0.6K out$1,560
- Coding agent1,000 requests a day, 40K in / 2K out$3,600
- Overnight batch20,000 requests a day, 4K in / 0.4K out$8,400
Where to run it
3 hosts serve GPT-4o Transcribe. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
OpenAILab API gpt-4o-transcribe | $2.50 / $10.00 Retires 26 Feb 2027 | gpt-4o-transcribe | Retires 26 Feb 2027 |
Azure OpenAICloud gpt-4o-transcribe | $2.50 / $10.00 | gpt-4o-transcribe | |
ReplicateInference gpt-4o-transcribe | $6.00 / $10.00 +60% vs headline | gpt-4o-transcribe |
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
- 50% less
Other frontier labs
- 31% less
Open-weight picks
No cheaper open-weight match.
Call it
Using OpenAI's API.
from openai import OpenAI
client = OpenAI() # reads OPENAI_API_KEY
response = client.responses.create(model="gpt-4o-transcribe", input="Hello")
print(response.output_text)curl https://api.openai.com/v1/responses \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-4o-transcribe", "input": "Hello"}'from litellm import completion
response = completion(
model="openai/gpt-4o-transcribe",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does GPT-4o Transcribe cost?
On OpenAI, GPT-4o Transcribe costs $2.50 per million input tokens and $10.00 per million output tokens.
Which APIs offer GPT-4o Transcribe?
GPT-4o Transcribe runs on 3 APIs: OpenAI, Azure OpenAI and Replicate.
What is GPT-4o Transcribe's context window?
16K tokens, with up to 2K tokens in one reply.
Is GPT-4o Transcribe being retired?
OpenAI retires it on 26 Feb 2027. 2 hosts keep serving it.
What are cheaper alternatives to GPT-4o Transcribe?
Models that cost less and keep most of what it can do: GPT-4o Mini Transcribe on OpenAI (50% less) and Gemini 3.5 Transcribe on Vertex AI (31% less). Savings are on a mix of 3 input tokens to 1 output token.
What is GPT-4o Transcribe's API model id?
Use gpt-4o-transcribe with OpenAI.
Sources
Raw catalog entry for gpt-4o-transcribe on OpenAI
{
"input_cost_per_audio_token": 0.000006,
"input_cost_per_token": 0.0000025,
"litellm_provider": "openai",
"max_input_tokens": 16000,
"max_output_tokens": 2000,
"mode": "audio_transcription",
"output_cost_per_token": 0.00001,
"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": 0.0001,
"source": "https://developers.openai.com/api/docs/pricing"
}