gpt-4o-audio-preview-2025-06-03gpt-4o-audio-preview adds support for audio inputs, allowing the model to understand nuances in audio recordings and enrich responses. It currently does not generate audio outputs, and audio input is billed per million audio tokens.
Select an endpoint and copy a working example for this model.
from openai import OpenAI client = OpenAI( api_key="YOUR_API_KEY", base_url="https://api.apertis.ai/v1") response = client.chat.completions.create( model="gpt-4o-audio-preview-2025-06-03", messages=[ {"role": "user", "content": "Hello!"} ], max_tokens=1024, temperature=0.7) print(response.choices[0].message.content) # Optional: Enable context compression to reduce token usage# response = client.chat.completions.create(# model="gpt-4o-audio-preview-2025-06-03",# messages=[{"role": "user", "content": "Hello!"}],# extra_body={"compression": {"enabled": True, "model": "gpt-4.1-mini"}}# )modelinputvoiceresponse_formatspeedinstructionsstream_formatUse these namespaced identifiers in Cursor IDE to avoid conflicts with built-in models.
See how this model compares to others from the same provider.
GPT-4o Mini TTS is OpenAI's cost-efficient text-to-speech model, designed to convert text into natural-sounding audio output. It supports a variety of voices and tones, enabling flexible and expressive speech generation. Optimized for scalability and low cost, it is well suited for real-time voice applications, content narration, and high-volume audio generation workflows.
GPT-4o Mini Transcribe is a smaller, cost-efficient speech-to-text model built on GPT-4o Mini's audio capabilities. It is designed for high-volume transcription workloads, delivering reliable performance with lower cost and latency. Priced per token (input and output), it provides transparent, fine-grained billing, making it well suited for scalable transcription pipelines, real-time applications, and cost-sensitive deployments.
GPT-4o Transcribe is OpenAI's high-quality speech-to-text model built on GPT-4o's audio capabilities. It delivers accurate transcription with strong language understanding, making it suitable for a wide range of audio processing tasks. Priced per token (input and output), it offers transparent, fine-grained billing, making it well suited for workflows that require scalable transcription, integration with LLM pipelines, and cost-aware processing.
Whisper Large V3 Turbo is an optimized version of OpenAI's Whisper Large V3 speech recognition model, designed for high-speed and cost-efficient transcription. It supports 99+ languages and accepts common audio formats including mp3, mp4, wav, webm, flac, and ogg. With a ~12% word error rate and real-time speed factors up to 216×, it delivers fast, scalable performance for latency-sensitive and high-throughput transcription workloads, making it ideal for real-time and large-scale speech processing applications.
See how this model compares to others from the same provider.
gpt-image-1 is OpenAI's image generation model designed to create, edit, and enhance images from natural language prompts. It supports tasks like producing detailed visuals, modifying existing images, generating variations, and upscaling — making it useful for design, illustration, marketing assets, and creative exploration.
GPT-5.3 Chat is an updated version of ChatGPT's most widely used conversational model, designed to make everyday interactions smoother, more accurate, and more helpful. It improves contextual understanding and response quality while reducing unnecessary refusals, excessive caveats, and overly cautious phrasing that can disrupt conversational flow. Optimized for general-purpose dialogue, GPT-5.3 Chat delivers more natural, reliable responses across a wide range of everyday tasks and discussions.
gpt-oss-20b is an open-weight, 21B-parameter OpenAI model released under Apache 2.0. It uses a Mixture-of-Experts design so only ~3.6B parameters run each step, enabling faster, lower-cost inference on consumer or single-GPU hardware. Trained in the Harmony format, it supports configurable reasoning depth, fine-tuning, function calling, tool use, and structured outputs.
GPT-5 Codex (High) is a coding-focused version of GPT-5 built for both interactive development and long autonomous engineering tasks. It can create projects, add features, debug, refactor, and review code, producing cleaner and more controllable outputs than GPT-5. It integrates with developer tools (CLI, IDEs, GitHub, cloud), supports adjustable reasoning effort, handles multimodal inputs, and uses tools for search and environment setup — making it purpose-built for agentic coding workflows.
Initialized observational baseline with no recorded failures