Atlas / Models / OpenAI / OpenAI: GPT-4o Audio

OpenAI: GPT-4o Audio✓ Catalog verified

openai/gpt-4o-audio-preview

The gpt-4o-audio-preview model adds support for audio inputs as prompts. This enhancement allows the model to detect nuances within audio recordings and add depth to generated user experiences. Audio outputs are currently not supported. Audio tokens are priced at $40 per million input and $80 per million output audio tokens.

Input price
$2.50 /1M
Output price
$10.00 /1M
Context
128K
Modalities
audiotext
Released
Aug 15, 2025
Tool calling
✓ Yes
Atlas signal
81/100
01

Overview

The gpt-4o-audio-preview model adds support for audio inputs as prompts. This enhancement allows the model to detect nuances within audio recordings and add depth to generated user experiences. Audio outputs are currently not supported. Audio tokens are priced at $40 per million input and $80 per million output audio tokens.

Access: available through the official OpenAI API. Context window: 128K.

Pricing and metadata from the ModelsAtlas catalog.Last refreshed Aug 5, 2026
02

Specifications

API identifieropenai/gpt-4o-audio-preview
ProviderOpenAI
Model typeMultimodal LLM
Context window128K catalog
Input modalitiesaudio · text
Output modalitiestext · audio
ReleasedAug 15, 2025
TokenizerGPT
ModeratedYes
Architecture modalitytext+audio->text+audio
Supported parameters
frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_logprobstop_p
Source: provider documentation + catalog feedMethodology →

API defaults

Default parameters
{
  "top_p": null,
  "temperature": null,
  "frequency_penalty": null
}
03

Pricing

Live pricing components for openai/gpt-4o-audio-preview as published in the catalog.

$2.50
Input /1M
$10.00
Output /1M
Per request
Per image
Pricing componentRaw unit priceNormalizedUnit
Prompt tokens$0.0000025$2.50 / 1MPer input token
Completion tokens$0.00001$10.00 / 1MPer output token
Request feeN/AN/APer request
Image feeN/AN/APer image unit
Web search feeN/AN/APer search request
Source: catalog pricing feedCompare all pricing →Cheapest models →
04

Cost calculator

Estimate monthly spend from your own token volumes.

Scale / Volume

Estimated Total Cost

$3.25Calculated from current list pricing in the ModelsAtlas catalog.
05

Capabilities

CapabilityStatusWhat it means
Visual UnderstandingNot advertisedImage and document analysis support
Audio Processing✓ SupportedSpeech and voice aligned flows
Tool Calling✓ SupportedSupports tools / function calling
Self-HostingNot advertisedDeploy outside managed APIs
Derived from catalog capability tags and supported parameters
06

Capability signals

Directional signals derived from model metadata and capability tags — not official benchmark submissions.

OpenAI: GPT-4o Audio
MMLU Signal (Reasoning)
79signal
Coding Signal (HumanEval proxy)
88signal
Math Signal (GSM8K proxy)
79signal
Science Signal (GPQA proxy)
79signal
Estimated from metadata — not an official benchmark runAll benchmarks →Methodology →
07

Quick start

Call OpenAI: GPT-4o Audio through an OpenAI-compatible client.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="openai/gpt-4o-audio-preview",
    messages=[{"role": "user", "content": "Explain quantum physics."}]
)

print(response.choices[0].message.content)
08

Alternatives

Closest models by context window from a different provider.

09

Sources & attribution

Pricing and metadata are maintained in the ModelsAtlas catalog.

Capability bars use metadata tags — directional estimates onlyHow we source and verify data →
10

Frequently asked questions

How much does OpenAI: GPT-4o Audio cost?

$2.50 per 1M input tokens and $10.00 per 1M output tokens on the official OpenAI API.

What is the context window of OpenAI: GPT-4o Audio?

OpenAI: GPT-4o Audio supports up to 128K tokens of context.

Does OpenAI: GPT-4o Audio support tool / function calling?

Yes, OpenAI: GPT-4o Audio supports tool / function calling — you can register tools and the model will emit structured tool calls.

How do I access OpenAI: GPT-4o Audio?

Use the official OpenAI API with the model id `openai/gpt-4o-audio-preview`. See the Quick start section above for code examples.