Official Technical Resources: OpenAI (page 6)
Official Technical Resources · OpenAI: 258 entries in total; this page lists entries 76–90.
Rate limits
Rate limits are restrictions that our API imposes on the number of times a user or client can access our services within a specified period of time.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Model Deployment Options
Link last checked: 2026-09-24
Realtime conversations
Learn how to manage Realtime speech-to-speech conversations.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Speech Recognition and Synthesis · Streaming Output
Link last checked: 2026-09-24
Realtime transcription
Learn how to transcribe live audio with realtime transcription sessions.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Speech Recognition and Synthesis · Streaming Output
Link last checked: 2026-09-24
Realtime with tools
Learn how to configure function tools and MCP tools in a Realtime session.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Speech Recognition and Synthesis · Streaming Output
Link last checked: 2026-09-24
Reasoning models
Learn how to use OpenAI reasoning models in the Responses API, choose a reasoning effort, manage reasoning tokens, and keep reasoning state across turns.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Context Compaction · Agent Memory
Link last checked: 2026-09-24
Red teaming
Learn how red teaming fits into AI evaluation, including Promptfoo open source and OpenAI Red Teaming for enterprise teams.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Guardrails · AI Red Teaming
Link last checked: 2026-09-24
Reinforcement fine-tuning
Fine-tune models for expert-level performance within a domain.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Model Evaluation and Benchmarks · Fine-tuning
Link last checked: 2026-09-24
Results and state
Learn which result surfaces matter most in the OpenAI Agents SDK and how they connect to resumable workflow state.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Context Compaction · Agent Memory
Link last checked: 2026-09-24
Retrieval
Learn how to search your data using semantic similarity with the OpenAI API.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Model Evaluation and Benchmarks · Fine-tuning
Link last checked: 2026-09-24
Run and continue sessions
Start work, follow progress, and continue the conversation.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Context Compaction · Agent Memory
Link last checked: 2026-09-24
Running agents
Learn how to run agents, stream output, and choose the right conversation-state strategy in the OpenAI Agents SDK.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Context Compaction · Agent Memory
Link last checked: 2026-09-24
Safety best practices
Learn how to implement safety measures like moderation, adversarial testing, human oversight, and prompt engineering to ensure responsible AI deployment.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Guardrails · AI Red Teaming
Link last checked: 2026-09-24
Safety classifiers
Learn how API safety classifiers identify potential abuse and how safety identifiers help limit disruption to other users.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Guardrails · AI Red Teaming
Link last checked: 2026-09-24
Sandbox Agents
Learn how sandboxes fit into Agents SDK workflows, when to use them, and how orchestration stays separate from execution.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Code Execution and Sandboxing · AI Coding Tools
Link last checked: 2026-09-24
Sandbox security
Isolate workloads, restrict network access, and protect credentials.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Code Execution and Sandboxing · AI Coding Tools
Link last checked: 2026-09-24