No free plan. The cheapest way in is GPT-5.4 (Flagship) at $2.50 input / $15.00 output per 1M tokens. Consider free alternatives in the ai models category if budget is tight.
The Responses API adds built-in tools (web search, file search, code interpreter, computer use), server-side tool orchestration (the model chains multiple tool calls in one request), guaranteed structured outputs, and a richer conversation model. It's designed for agent workflows. Chat Completions still works but new features focus on Responses.
No. There is no API surcharge — you pay the same per-token rates regardless of which API you use (Responses, Chat Completions, Realtime, Batch, or Assistants). The only additional costs are for built-in tool usage: web search calls, file search calls, and container sessions.
Yes. Custom function definitions work alongside web search, file search, and code interpreter in the same request. The model can decide to use any combination of built-in and custom tools within a single orchestration loop.
MCP (Model Context Protocol) is a standard for connecting AI models to external tools and data sources. The Responses API supports MCP, meaning agents can invoke any MCP-compatible tool server — accessing databases, APIs, or custom services through a standardized interface.
All current OpenAI models including GPT-5.4, GPT-5.4-mini, GPT-5.4-nano, GPT-5.4-pro, reasoning models (o3, o4-mini), and legacy GPT-4o/4.1 series. Each model has different pricing and capability tradeoffs.
See OpenAI Responses API plans and find the right tier for your needs.
See Pricing Plans →Still not sure? Read our full verdict →
Last verified March 2026