# GPT Audio 1.5

> OpenAI's audio model for the Chat Completions API. It accepts audio inputs and produces audio outputs.

Agent resources: the index of everything machine-readable is https://www.ohmygpt.com/llms.txt; the integration skill (endpoints, auth, SDK and coding-tool setup) is https://www.ohmygpt.com/skill.md.

- Model ID: `openai/gpt-audio-1.5`
- Status: available
- Released: 2026-02-23
- Context: 128K tokens
- Max output: 16K tokens
- Input: text, audio; output: text, audio
- Knowledge cutoff: 2024-09-30

## Prices (USD)

| Item | Price | Unit |
| --- | --- | --- |
| Input | $2.25 | per 1M tokens |
| Output | $9.00 | per 1M tokens |
| Audio input | $28.80 | per 1M tokens |
| Audio output | $57.60 | per 1M tokens |

## Providers

This model chooses its provider itself; a provider prefix is not accepted.

| Provider | Pinned model ID | Location | Input | Output | Trains on your data |
| --- | --- | --- | --- | --- | --- |
| OpenAI | — | United States | $2.25 | $9.00 | no |

## Endpoints

| API | Request | model |
| --- | --- | --- |
| OpenAI Chat | POST https://api.ohmygpt.com/v1/chat/completions | `openai/gpt-audio-1.5` |
| OpenAI Responses | POST https://api.ohmygpt.com/v1/responses | `openai/gpt-audio-1.5` |
| Anthropic Messages | POST https://api.ohmygpt.com/v1/messages | `openai/gpt-audio-1.5` |
| Google Gemini | POST https://api.ohmygpt.com/v1/models/openai/gpt-audio-1.5:generateContent | `openai/gpt-audio-1.5` |

## Example

```bash
curl https://api.ohmygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $OHMYGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-audio-1.5",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'
```

Web page: https://www.ohmygpt.com/models/openai/gpt-audio-1.5