API Pricing
Powered by our frontier models
Our industry-leading models deliver advanced intelligence and multimodal capabilities.
GPT-5.6 Sol
Flagship model for ambitious agentic work
Price
Input:$5.00 / 1M tokensCached input:$0.50 / 1M tokensOutput:$30.00 / 1M tokens
GPT-5.6 Terra
Balanced model for efficient, high-volume work
Price
Input:$2.00 / 1M tokensCached input:$0.20 / 1M tokensOutput:$12.00 / 1M tokens
GPT-5.6 Luna
Fast, affordable model for everyday work
Price
Input:$0.20 / 1M tokensCached input:$0.02 / 1M tokensOutput:$1.20 / 1M tokens
Pricing above reflects standard processing rates for context lengths under 270K.
Learn more about Batch Processing(opens in a new window) and Data residency & Regional Processing(opens in a new window)
Multimodal models
Power applications across text, image, and audio with models built for real-time interaction and rich media generation.
GPT-Image-2
State-of-the-art image generation model.
Price
Image:$8.00 / 1M tokens for inputs$2.00 / 1M tokens for cached inputs$30.00 / 1M tokens for outputsText:$5.00 / 1M tokens for inputs$1.25 / 1M tokens for cached inputs
GPT-Realtime-2.1
Our most capable model for realtime voice interactions with advanced reasoning built in.
Price
Audio:$32.00 / 1M tokens for inputs$0.40 / 1M tokens for cached inputs$64.00 / 1M tokens for outputsText:$4.00 / 1M tokens for inputs$0.40 / 1M tokens for cached inputs$24.00 / 1M tokens for outputsImage:$5.00 / 1M tokens for inputs$0.50 / 1M tokens for cached inputs
GPT-Realtime-2.1 mini
Our strongest mini model yet for realtime voice interactions with advanced reasoning built in.
Price
Audio:$10.00 / 1M tokens for inputs$0.30 / 1M tokens for cached inputs$20.00 / 1M tokens for outputsText:$0.60 / 1M tokens for inputs$0.06 / 1M tokens for cached inputs$2.40 / 1M tokens for outputsImage:$0.80 / 1M tokens for inputs$0.08 / 1M tokens for cached inputs
GPT-Live-Transcribe
A streaming speech-to-text model that transcribes speech live as the speaker talks.
Price
$0.017 per minute / $0.00028 per second
GPT-Transcribe
A speech-to-text model for asynchronous and batch workloads.
Price
$0.0045 per minute / $0.00008 per second
GPT-Realtime-Translate
A model that translates speech in real time and keeps pace with the speaker.
Price
$0.034 per minute / $0.00057 per second
Tools
Extend model capabilities with built-in tools for retrieval, execution, and external data access.
Web search
Retrieve up-to-date information from the web to ground model responses.
Price
$10.00 / 1k callsSearch content tokens are free.
Containers
Run code and tools in secure, scalable environments alongside your models.
Price
Now:1 GB for $0.03 / 64GB for $1.92 per containerStarting March 31, 2026:1 GB for $0.03 / 64GB for $1.92 per 20-minute session per container
Service tiers
Balance performance, predictable costs, and availability based on your needs.
Batch API
Save 50% on inputs and outputs with the Batch API and run tasks asynchronously over 24 hours.
Fast mode
Offers reliable, high-speed performance with the flexibility to pay-as-you-go.
Flex processing
Provides lower costs for requests in exchange for slower response times and occasional resource unavailability. Ideal for non-production or lower priority tasks.
Enterprise offerings
Contact our sales team to learn more about Data residency(opens in a new window), Scale Tier and Reserved Capacity designed for cutting-edge customers running larger workloads.