OpenAI API Pricing

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments.

gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b.

GPT-4.1 nano is OpenAI's ultra-cheap model — matching Gemini Flash pricing while packing a 1M context window. Ideal for high-volume classification and extraction at minimal cost.

GPT-4o mini is OpenAI's most affordable mainstream model — a lightweight version of GPT-4o optimized for speed and cost. It's ideal for simple tasks that don't require the full capability of GPT-4o.

GPT-4o mini Search Preview is a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.

GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.

GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks.

GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks.

GPT-4.1 mini brings GPT-4.1-class quality to a budget price point — with the same 1M context window at a fraction of the cost. A strong replacement for GPT-4o mini in most pipelines.

GPT-3.5 Turbo is the previous workhorse model from OpenAI. Cheap and fast, but generally outclassed by GPT-4o mini at similar or lower price points. Still common in legacy integrations.

A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency.

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.

GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with `reasoning. mode` set to `pro` for higher-quality responses on complex tasks.

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series.

GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.

o4-mini brings OpenAI's chain-of-thought reasoning to a smaller, faster, and cheaper form factor. It offers strong performance on STEM tasks at a fraction of o3's cost.

OpenAI o1-mini is the budget version of o1 — chain-of-thought reasoning at a fraction of the cost, optimized for STEM tasks. Largely succeeded by o4-mini but still widely deployed.

OpenAI o3-mini delivers o3-class reasoning at o4-mini pricing — the sweet spot for teams that need reliable step-by-step reasoning without paying for full o3. Strong on coding and math.

OpenAI o4-mini-high is the same model as o4-mini with reasoning_effort set to high.

OpenAI o3-mini-high is the same model as o3-mini with reasoning_effort set to high.

GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks.

GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5.

GPT-5.1 Chat (AKA Instant is the fast, lightweight member of the 5.1 family, optimized for low-latency chat while retaining strong general intelligence.

GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows.

GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows.

GPT-5 Chat is designed for advanced, natural, multimodal, and context-aware conversations for enterprise applications.

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.

This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.

GPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more directly helpful.

GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2.

GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows.

GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence.

GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1.

OpenAI o3 is a frontier reasoning model that thinks step-by-step before answering. It significantly outperforms previous models on math, science, and complex coding tasks — but at a higher cost due to extended chain-of-thought processing.

GPT-4.1 is OpenAI's 2025 flagship text model — more capable than GPT-4o with a massive 1M token context window. It hits a strong balance between quality and cost for production workloads.

o4-mini-deep-research is OpenAI's faster, more affordable deep research model—ideal for tackling complex, multi-step research tasks. Note: This model always uses the 'web_search' tool which adds additional cost.

GPT-4o is OpenAI's flagship multimodal model — capable of processing text, images, and audio. It's the default choice for most production OpenAI workloads, balancing cost, speed, and capability.

GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with `reasoning. mode` set to `pro` for higher-quality responses on complex tasks.

GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier.

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system.

The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency.

GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by GPT-5 Mini, with GPT Image 1 Mini for efficient image generation.

GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.

The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability.

The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more here.

This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost.

GPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, served with `reasoning. mode` set to `pro` for higher-quality responses on complex tasks.

GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series.

GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT.

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks.

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs.

GPT-5.4 Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2.

GPT-4 Turbo is the predecessor to GPT-4o — still widely deployed, especially in enterprise stacks pinned to it. Largely superseded by GPT-4o on both price and multimodal capability.

GPT-5 Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities.

o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks. Note: This model always uses the 'web_search' tool which adds additional cost.

The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023.

OpenAI o1 is the original frontier reasoning model — extended chain-of-thought processing for maximum accuracy on math, science, and complex coding. Pricier than o3/o4-mini but benchmarked at the top of its generation.

GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.

The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning.

GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro.

GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads.

GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks.

OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning.

The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning.