OpenAI AI API models
OpenAI AI models on MuAPI
Explore OpenAI models for chat, code, image and video generation, including Gemini, Nano Banana and Veo-style workflows available through MuAPI.
All models
26 ModelsVideo Generation Models
$0.800 / second
openai-sora-2-image-to-video
Sora 2’s I2V lets you bring still images to life by animating them into short video clips with natural motion, audio, and visual effects. While realistic portraits of people aren’t allowed at launch, you can use objects, landscapes, stylized characters or scenes. Use detailed prompts for camera movement, atmosphere, and pacing to get the best results.
$0.800 / second
openai-sora-2-text-to-video
Sora 2 T2V converts text prompts into short, dynamic 10-second video clips with synchronized audio. Users can describe scenes, motion, camera angles, and sound effects, and Sora 2 brings them to life with cinematic realism or stylized visuals. Perfect for storytelling, social media content, and creative experimentation, while maintaining high-quality visuals and immersive audio.
$0.080 / second
topaz-video-upscale
The AI Video Upscaler is a powerful tool designed to enhance the resolution and quality of videos. Whether you're working with low-resolution videos that need a boost or aiming to improve the clarity of existing footage, this upscaler leverages advanced machine learning models to deliver high-quality, upscaled videos.
$2.400 / second
openai-sora-2-pro-text-to-video
Sora 2 Pro T2V is the high-fidelity version of OpenAI’s video generation model. It converts your text prompts into cinematic, richly detailed video clips with synchronized audio, realistic motion, strong physics, and creative control over style, mood, and pacing. Perfect for creators, storytellers, advertisers, and anyone who wants top-quality video content from text.
$0.500 / second
openai-sora
Sora is a text-to-video generative AI model developed by OpenAI. It can generate short video clips based on descriptive text inputs, producing content that ranges from photorealistic scenes to stylized animations.
$2.400 / second
openai-sora-2-pro-image-to-video
Sora 2 Pro I2V brings still images to life, transforming them into short videos with natural motion, realistic lighting, and synchronized audio. Upload your image, describe the movement (camera motion, subject action, ambience), add optional dialogue or sound effects, and watch it animate. Ideal for cinematic reveals, promo videos, social content, or storytelling from a static photo.
$0.580 / second
openai-sora-2-pro-storyboard
Sora 2 Pro enables creators to structure video narratives by chaining multiple scenes through storyboard “cards.” Each card defines a segment of the video—setting, characters, actions, timing—and the model stitches them into a cohesive multi-scene video. This gives you more control over pacing, transitions, and storytelling flow.
Image Generation Models
$0.090 / 1K tokens
gpt-image-2-text-to-image
Generate high-quality images from text prompts using GPT Image 2, supporting up to 20,000 character prompts for detailed and precise image creation.
$0.040 / 1K tokens
gpt4o-text-to-image
Generate images from text prompts using GPT-4o's vision capabilities. Ideal for basic concept visuals, diagrams, and abstract compositions.
$0.040 / generation
gpt4o-image-to-image
Transform an input image based on a new prompt — like changing style, lighting, or composition. Useful for reinterpreting visuals while keeping structure.
$0.075 / generation
topaz-image-upscale
Topaz Image Upscale is a high-quality image-to-image enhancement model that increases resolution, sharpness, and detail using AI super-resolution. It improves clarity, restores texture, reduces noise, and produces crisp, high-res output while preserving natural look and fine edges.
$0.054 / 1K tokens
gpt-image-1.5
GPT-Image-1.5 is a high-quality text-to-image generation model designed for rich visual reasoning, detailed compositions, and strong prompt understanding. It excels at complex scenes, symbolic imagery, cinematic lighting, surreal concepts, product visuals, and imaginative world-building while maintaining coherence and fine detail.
$0.054 / generation
gpt-image-1.5-edit
GPT-Image-1.5 Edit applies precise, instruction-based modifications to an existing image while preserving composition, lighting, perspective, and visual coherence. It’s well-suited for object replacement, concept evolution, symbolic edits, and creative transformations that feel natural and intentional rather than destructive.
$0.040 / generation
gpt4o-edit
Edit a specific part of an image using natural language. Ideal for object removal, replacement, or content-aware filling.
$0.090 / generation
gpt-image-2-image-to-image
Transform and edit existing images using GPT Image 2 with text instructions. Supports up to 16 input images for precise style transfer, editing, and image transformation.
Text & Chat Models
$0.000 / 1K tokens
gpt-5-6-luna
GPT 5.6 Luna is OpenAI's fast, cost-effective multimodal reasoning model. Supports mixed text and image inputs, adjustable reasoning effort, and integrated web search tools. Pricing: $2.00/M input tokens, $12.00/M output tokens.
$0.001 / 1K tokens
gpt-5-6-sol
GPT 5.6 Sol is OpenAI's flagship reasoning model, optimized for complex math, programming, and scientific research. Supports mixed text and image inputs, adjustable reasoning effort, and integrated web search tools. Pricing: $10.00/M input tokens, $60.00/M output tokens.
$0.000 / 1K tokens
gpt-5-nano
GPT-5 Nano is a lightweight, high-speed language model from the GPT-5 family designed for instant text generation. It delivers intelligent, context-aware responses for creative writing, summarization, dialogue, code generation, and automation — all at low latency and cost. Perfect for chatbots, assistants, content tools, and real-time applications that need fast, reliable text output.
$0.000 / 1K tokens
gpt-codex
OpenAI GPT Codex delivers advanced coding capabilities with scalable reasoning depth. Supports multiple model variants (gpt-5-codex through gpt-5.4-codex) and multimodal inputs. Token-based pricing: $1.25/M input tokens, $9.00/M output tokens. Two endpoints: standard async (/gpt-codex) and live streaming (/gpt-codex/stream) via SSE.
$0.000 / 1K tokens
gpt-5-5
GPT 5.5 is OpenAI's state-of-the-art flagship reasoning model for high-complexity problems. Supports image and file uploads, system prompts, web search capabilities, and reasoning effort control. Pricing: $2.40/M input tokens, $16.00/M output tokens.
$0.000 / 1K tokens
gpt-5-2
GPT 5.2 is a lightweight reasoning model with fast response times and deep coding capabilities. Supports image inputs, system prompts, web search capabilities, and reasoning effort control. Pricing: $1.25/M input tokens, $9.00/M output tokens.
$0.000 / 1K tokens
gpt-5-6-terra
GPT 5.6 Terra is OpenAI's balanced multimodal reasoning model for general business and analytical tasks. Supports mixed text and image inputs, adjustable reasoning effort, and integrated web search tools. Pricing: $5.00/M input tokens, $30.00/M output tokens.
$0.000 / 1K tokens
gpt-5-mini
GPT‑5 Mini is a compact yet powerful AI that converts plain text ideas into detailed, structured prompts suitable for use in text-to-image, text-to-video, and other generative AI models. It’s perfect for creators who want to quickly craft high-quality prompts without manually thinking about style, composition, and descriptive details. The model helps accelerate workflows for artists, video producers, and designers.
$0.100 / 1K tokens
openai-sora-2-pro-characters
Create consistent AI characters for your Sora 2 videos. Provide a previous video's task ID and a prompt to define or refine your character.
$0.000 / 1K tokens
gpt-5-4
GPT-5.4 delivers powerful reasoning, coding, and professional knowledge work. Supports multimodal inputs (text and image) with adjustable reasoning depth. Token-based pricing: $1.25/M input tokens, $9.00/M output tokens. Two endpoints: standard async (/gpt-5-4) and live streaming (/gpt-5-4/stream) via SSE.