OpenAI Model Catalog — Pricing, Context & Capabilities

Previous generation image generation model.

Cost-efficient version of GPT Image 1.

State-of-the-art image generation model.

OpenAI's most advanced image generation model with native reasoning — thinks before drawing. 2K resolution, multi-image consistency, magazine-quality typography, and image editing. Released April 21, 2026.

OpenAI's image model tuned for fast, high-quality everyday image generation. Same per-token billing as GPT Image 2. Released September 8, 2026.

OpenAI's image model tuned for workflows where editing precision matters most. Same per-token billing as GPT Image 2. Released September 8, 2026.

OpenAI's open-source 120B model with hybrid reasoning, extended thinking, efficient code generation, agentic search, computer use, and tool use capabilities.

OpenAI's open-source 20B model with hybrid reasoning, extended thinking, efficient code generation, agentic search, and tool use. Cost-effective alternative to the 120B variant.

OpenAI's advanced safety reasoning model (120B). Nuanced policy interpretation, multi-turn safety analysis, and justified decisions for content moderation.

OpenAI's safety classification model (20B). Policy reasoning, content filtering, risk analysis, and justification generation.

OpenAI's smartest non-reasoning model. Excels at instruction following and tool calling with broad knowledge across domains. Features a 1M token context window and low latency.

Smaller, faster version of GPT-4.1. Excels at instruction following and tool calling with a 1M token context window and low latency without a reasoning step.

Fastest, most cost-efficient version of GPT-4.1. Excels at instruction following and tool calling with a 1M token context window and minimal latency.

OpenAI's versatile, high-intelligence flagship model. Accepts text and image inputs, produces text outputs including structured outputs. Best model for most tasks outside reasoning-heavy use cases.

Fast, affordable small model for focused tasks. Accepts text and image inputs, produces text outputs. Ideal for fine-tuning and cost-efficient workloads.

Speech-to-text model powered by GPT-4o mini.

Text-to-speech model powered by GPT-4o mini.

Speech-to-text model powered by GPT-4o.

Transcription model that identifies who is speaking when.

OpenAI's intelligent reasoning model for coding and agentic tasks with configurable reasoning effort. Features a 400K context window and 128K max output.

GPT-5 chat-optimized variant (no codex / no reasoning specialization).

A faster, cost-efficient version of GPT-5 for well-defined tasks. Features reasoning token support with a 400K context window and 128K max output at a fraction of the cost.

Fastest, most cost-efficient version of GPT-5. Great for summarization and classification tasks with reasoning token support. Features a 400K context window and 128K max output.

Version of GPT-5 that produces smarter and more precise responses with deeper reasoning.

Version of GPT-5 optimized for agentic coding in Codex.

OpenAI's previous flagship reasoning model for coding and agentic tasks with configurable reasoning effort. Features a 400K context window and 128K max output.

GPT-5.1 chat-optimized variant.

Version of GPT-5.1 optimized for agentic coding in Codex.

Smaller, more cost-effective version of GPT-5.1-Codex.

Version of GPT-5.1 Codex optimized for long-running tasks.

OpenAI's best model for coding and agentic tasks across industries. Features a 400K context window with 128K max output, reasoning token support, and state-of-the-art long-context reasoning.

GPT-5.2 chat-optimized variant.

OpenAI's premium flagship model for the most demanding reasoning and agentic tasks. Extended context and maximum capabilities. 400K context, 128K max output.

Intelligent coding model optimized for long-horizon, agentic coding tasks.

Pinned "latest" alias for the ChatGPT-style chat-tuned variant of GPT-5.3. Tracks current revision; pricing matches GPT-5.3 base.

Most capable agentic coding model to date.

Best intelligence at scale for agentic, coding, and professional workflows.

Strongest mini model for coding, computer use, and subagents. Fast and cost-efficient with reasoning token support, 400K context window and 128K max output.

Smallest and fastest GPT-5.4 variant for lightweight agentic tasks. 400K context window and 128K max output with reasoning support.

Version of GPT-5.4 that produces smarter and more precise responses.

Next-generation frontier model with 1M context, advanced reasoning, and multimodal input for agentic, coding, and professional workflows.

Version of GPT-5.5 that produces smarter and more precise responses with enhanced reasoning depth.

OpenAI's GPT-5.6 family (Luna tier). The cost/efficiency entry point into the 5.6 generation.

OpenAI's GPT-5.6 family (Sol tier). The most capable of the three 5.6 tiers.

OpenAI's GPT-5.6 family (Terra tier). Frontier reasoning and coding at the GPT-5.5 price/quality tier.

OpenAI's GPT-6 family. The only GPT-6 SKU (no mini/nano/pro/codex variants exist per OpenAI's own docs); most capable model, built for the hardest end-to-end work.

Audio inputs and outputs with the Chat Completions API.

Best voice model for audio in, audio out with Chat Completions.

Cost-efficient version of GPT Audio.

Successor to gpt-realtime-2. Not currently servable: the conversational realtime family needs a bidirectional WebSocket serving path, which this gateway does not implement, so it ships gated.

Cost-efficient successor to gpt-realtime-mini. Gated for the same reason as gpt-realtime-2.1 — no bidirectional WebSocket serving path.

Whisper-class automatic speech recognition over the realtime channel. Audio in, transcribed text out.

First-generation reasoning model. Uses chain-of-thought for complex problems in science, coding, and math. Succeeded by o3 — kept available for workloads pinned to o1.

OpenAI's powerful reasoning model that pushes the frontier across coding, math, science, and visual perception. Excels in complex queries requiring multi-faceted analysis. Succeeded by GPT-5.

Version of o3 with more compute for better, more precise responses. Best for complex reasoning tasks where accuracy is paramount.

Fast, cost-efficient reasoning model with a 200K context window. Ideal for tasks requiring reasoning at lower cost. Succeeded by GPT-5 Mini.

Text-to-speech model optimized for speed.

Text-to-speech model optimized for quality.

General-purpose speech recognition model.