sora-2-proSora 2 Pro is the higher-quality version of OpenAI's Sora 2 text-to-video and audio generation model, designed to produce more realistic, controllable, and detailed AI-generated videos with synchronized audio and advanced world simulation capabilities. It builds on Sora 2's breakthrough in video realism and physics-aware generation, offering enhanced visual fidelity and extended features for creative and professional use. Early access has been available to ChatGPT Pro subscribers via sora.com, with wider availability expected after the invite/beta rollout.
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="sora-2-pro", 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="sora-2-pro",# messages=[{"role": "user", "content": "Hello!"}],# extra_body={"compression": {"enabled": True, "model": "gpt-4.1-mini"}}# )modelmessagesmax_tokenstemperaturetop_pstreamtoolsreasoning_effortstream_optionsthinkingextra_bodyUse 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-5.6 Luna Pro uses the same underlying model as GPT-5.6 Luna, but runs with reasoning.mode set to pro to deliver higher-quality responses on complex tasks. It is optimized for deeper reasoning, advanced coding, and multi-step agentic workflows, offering improved accuracy and solution quality while retaining the efficiency and scalability of the Luna tier.
GPT-5.6 Luna is the fast, cost-efficient model in OpenAI's GPT-5.6 series, optimized for high-volume, latency-sensitive workloads. It delivers capable reasoning at an affordable price point, making it ideal for chat applications, classification, and lightweight agentic workflows. Designed for scalable production deployments, GPT-5.6 Luna balances speed, cost, and reliability, providing efficient performance for real-time applications and large-scale automation tasks.
GPT-5.6 Terra Pro uses the same underlying model as GPT-5.6 Terra, but runs with reasoning.mode set to pro to deliver higher-quality responses on complex tasks. Optimized for deeper reasoning and greater reliability, it is well suited for advanced coding, multi-step reasoning, and agentic workflows where improved accuracy and solution quality are more important than maximizing speed or minimizing cost.
GPT-5.6 Terra is the balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is designed for everyday coding, reasoning, and agentic workflows, delivering strong performance while balancing capability and cost. Offering near-flagship quality at approximately half the cost of Sol, GPT-5.6 Terra is well suited for production applications that require reliable reasoning, software development, and scalable agent execution.
See how this model compares to others from the same provider.
Codex Mini is a fine-tuned o4-mini model made for the Codex CLI. For most direct API usage, it’s better to use gpt-4.1 instead.
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.
text-embedding-ada-002 is OpenAI's older, legacy text embedding model.
Whisper (whisper-1) is OpenAI's open-source automatic speech recognition (ASR) model, designed for audio transcription and translation. It supports 50+ languages and processes audio files up to 25 MB, accepting formats such as mp3, mp4, wav, and webm. Optimized for reliable speech-to-text conversion across diverse audio inputs, Whisper is priced per minute of audio, billed to the nearest second, making it well suited for transcription, localization, and voice-driven applications.
Initialized observational baseline with no recorded failures