gpt-4o-audio-preview-2024-12-17gpt-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-2024-12-17", 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-2024-12-17",# 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-5.2 Chat (Instant) is the fast, lightweight version of the 5.2 family, tuned for low-latency conversation while keeping strong general intelligence. It uses adaptive reasoning to think more on tough questions, boosting accuracy in math, coding, and multi-step tasks without slowing normal chats. It’s friendlier by default, follows instructions well, and is ideal for high-throughput interactive use where speed and consistency matter more than deep deliberation.
gpt-oss-120b is an open-weight 117B-parameter MoE model from OpenAI, built for advanced reasoning and production workloads. Only about 5.1B parameters are active per step, and it’s optimized to run on a single H100 using MXFP4 quantization. It supports adjustable reasoning depth, full chain-of-thought, and native agent features like tool use, function calling, browsing, and structured outputs.
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-5.1 Codex Max is OpenAI's advanced agentic coding model, built for long-running, high-context development work. Using an upgraded 5.1 reasoning stack and training on real engineering workflows, it delivers faster performance, stronger reasoning, and better token efficiency across the full software lifecycle.
Initialized observational baseline with no recorded failures