impulse

GPT-4o Mini TTS

Frontier labSpeechRetiring 6 Jan 2027
API id gpt-4o-mini-ttsReleased 20 Mar 2025 (Mar 2025)
OpenAI retires it on 6 Jan 2027 (in 48 days). 1 host keeps serving it.
Input / 1M
$0.60
at OpenAI
Output / 1M
$10.00
at OpenAI
Context window
-
tokens
Max output
-
tokens per reply
Hosts
2
4 listings
Released
Mar 2025
20 Mar 2025

Pricing

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

TierInput / 1MOutput / 1M
Standard$0.60$10.00

What it costs a month

At OpenAI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$930
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$648
  • Coding agent1,000 requests a day, 40K in / 2K out$1,320
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$3,840
Use your own numbers

Where to run it

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

HostIn / out per 1M
OpenAILab API
gpt-4o-mini-tts
$0.60 / $10.00
Retires 6 Jan 2027
gpt-4o-mini-tts
$0.60 / $10.00
Retires 15 Jun 2027
Show 2 more listings: regions, snapshots and variants
OpenAI
2025-03-20
gpt-4o-mini-tts-2025-03-20
$0.60 / $10.00
Retires 6 Jan 2027
2025-12-15
gpt-4o-mini-tts-2025-12-15
$0.60 / $10.00
Retires 6 Jan 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
AudioText
Produces
Audio

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

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-tts", input="Hello")
print(response.output_text)

Quick answers

How much does GPT-4o Mini TTS cost?

On OpenAI, GPT-4o Mini TTS costs $0.60 per million input tokens and $10.00 per million output tokens.

Which APIs offer GPT-4o Mini TTS?

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

Is GPT-4o Mini TTS being retired?

OpenAI retires it on 6 Jan 2027; Azure OpenAI on 15 Jun 2027. No API serves it after that.

What are cheaper alternatives to GPT-4o Mini TTS?

Models that cost less and keep most of what it can do: Gemini 3.8 Flash TTS on Google AI Studio (11% less), Gemini 3.8 Flash Lite TTS on Google AI Studio (36% less) and Qwen Audio 3.1 TTS Flash on Alibaba DashScope (78% less). Savings are on a mix of 3 input tokens to 1 output token.

When was GPT-4o Mini TTS released?

OpenAI released it on 20 Mar 2025.

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

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

Sources

Raw catalog entry for gpt-4o-mini-tts on OpenAI
{
  "deprecation_date": "2027-01-06",
  "deprecation_source": "https://developers.openai.com/api/docs/deprecations",
  "successor_model": "gpt-realtime-2.1-mini",
  "input_cost_per_token": 6e-7,
  "litellm_provider": "openai",
  "mode": "audio_speech",
  "output_cost_per_audio_token": 0.000012,
  "output_cost_per_second": 0.00025,
  "output_cost_per_token": 0.00001,
  "source": "https://developers.openai.com/api/docs/pricing",
  "supported_endpoints": [
    "/v1/audio/speech"
  ],
  "supported_modalities": [
    "text",
    "audio"
  ],
  "supported_output_modalities": [
    "audio"
  ]
}