impulse

GPT-4o Mini Realtime Preview

Frontier labRealtimePreviewRetiring 20 Jan 2027
API id gpt-4o-mini-realtime-preview-2024-12-17Released 17 Dec 2024 (Dec 2024)
OpenAI retires it on 20 Jan 2027 (in 63 days). 1 host keeps serving it.
Input / 1M
$0.60
at OpenAI
Output / 1M
$2.40
at OpenAI
Context window
128K
tokens
Max output
4K
tokens per reply
Hosts
2
4 listings
Released
Dec 2024
17 Dec 2024

Pricing

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

TierInput / 1MOutput / 1M
Standard$0.60$2.40
Cached input
50% off input
$0.30

What it costs a month

At OpenAI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$333
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$302
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$612
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$2,016
Use your own numbers

Where to run it

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

HostIn / out per 1M
OpenAILab API
2024-12-17
gpt-4o-mini-realtime-preview-2024-12-17
$0.60 / $2.40
Retires 20 Jan 2027
2024-12-17
gpt-4o-mini-realtime-preview-2024-12-17
$0.60 / $2.40
Show 2 more listings: regions, snapshots and variants
Azure OpenAI
eu · 2024-12-17
gpt-4o-mini-realtime-preview-2024-12-17
$0.66 / $2.64
+10% vs headline
us · 2024-12-17
gpt-4o-mini-realtime-preview-2024-12-17
$0.66 / $2.64
+10% vs headline

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
TextAudio
Produces
TextAudio
Features
Audio inputAudio outputParallel tool calls

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

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-realtime-preview-2024-12-17", input="Hello")
print(response.output_text)

Quick answers

How much does GPT-4o Mini Realtime Preview cost?

On OpenAI, GPT-4o Mini Realtime Preview costs $0.60 per million input tokens and $2.40 per million output tokens. Cached input costs $0.30 per million tokens.

Which APIs offer GPT-4o Mini Realtime Preview?

GPT-4o Mini Realtime Preview runs on 2 APIs: OpenAI and Azure OpenAI.

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

128K tokens, with up to 4K tokens in one reply.

Is GPT-4o Mini Realtime Preview being retired?

OpenAI retires it on 20 Jan 2027. 1 host keeps serving it.

What are cheaper alternatives to GPT-4o Mini Realtime Preview?

Models that cost less and keep most of what it can do: Gemini Live 2.5 Flash Native Audio on Vertex AI (17% less). Savings are on a mix of 3 input tokens to 1 output token.

When was GPT-4o Mini Realtime Preview released?

OpenAI released it on 17 Dec 2024.

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

Use gpt-4o-mini-realtime-preview-2024-12-17 with OpenAI.

Sources

Raw catalog entry for gpt-4o-mini-realtime-preview-2024-12-17 on OpenAI
{
  "cache_creation_input_audio_token_cost": 3e-7,
  "cache_read_input_token_cost": 3e-7,
  "deprecation_date": "2027-01-20",
  "deprecation_source": "https://developers.openai.com/api/docs/deprecations",
  "input_cost_per_audio_token": 0.00001,
  "input_cost_per_token": 6e-7,
  "litellm_provider": "openai",
  "max_input_tokens": 128000,
  "max_output_tokens": 4096,
  "mode": "realtime",
  "output_cost_per_audio_token": 0.00002,
  "output_cost_per_token": 0.0000024,
  "successor_model": "gpt-realtime-2.1-mini",
  "supports_audio_input": true,
  "supports_audio_output": true,
  "supports_function_calling": true,
  "supports_parallel_function_calling": true,
  "supports_system_messages": true,
  "supports_tool_choice": true
}