API
The complete OpenAI API tutorial
The OpenAI API is the unified entry point for calling GPT-5.6, o-series, GPT Image 2, and GPT-Realtime. This channel takes you from account setup and your first request through real-world Responses API patterns in the Python and Node SDKs, streaming, function calling, error handling, and billing — from zero to production in a week.
24 article(s) total
What you'll learn in this channel
These are the core topics this channel covers. Each featured article unpacks several of them in depth.
- Account & API key
- Python / Node first call
- Responses API
- Streaming
- Function Calling
- Errors & billing
openai-python 3.49.0 and openai-node 7.55.0: typed async function tools for the Agents API
The 2026-11-10 SDK pair: python v3.49.0 and node v7.55.0 add typed support for the existing async setting on beta Agents function-tool shapes; python also fixes Microphone WAV encoding. Verified against tag sources.
Read articleopenai-python 3.48.0 and openai-node 7.54.0: agent session event-stream obfuscation padding and stream_options
The 2026-11-09 SDK pair: python v3.48.0 adds obfuscation switches for agent session streams (stream_options, include_obfuscation, 33 event types); node v7.54.0 adds rosalind types and scheduling retention. Verified against tag sources.
Read articleopenai-node 7.46–7.50: Five Releases, 12-Hour Caching and Service Tiers Land in the SDK (2026)
Five openai-node releases shipped between October 31 and November 3, carrying 12-hour Responses caching, project service tiers, workload identity providers, and a Live Responses expansion into the TypeScript layer.
Read articleopenai-python 3.42.0 and openai-node 7.46/7.47: agent compaction and review settings, external keys, SIP DTMF
openai-python v3.42.0 and openai-node v7.46/7.47 (2026-10-31): agent compaction, review, and spend-cap settings; time awareness; external keys; SIP DTMF; typed WebSocket warmup; image markup overlays.
Read articleopenai-python 3.40/3.41 and openai-node 7.45.1: breakpoint TTL semantics, tool_usage, and Realtime item references
openai-python v3.40.0/v3.41.0 and openai-node v7.45.1 (2026-10-27/28): breakpoint TTL wording, Response.tool_usage, Realtime item_reference, session metadata filters, WS binary-frame preservation, and the /v1/audio/translations deprecation.
Read articleDecisions API goes GA: a fast, low-cost judgment endpoint, explained
The 2026-10-22 announcement makes the Decisions API generally available: POST /v1/decisions, gpt-6-luna only, uncached input at $0.10 per 1M tokens with free output, up to 400 questions per request. The beta first shipped 2026-10-06.
Read articleOpenAI SDKs Ship Four Releases in One Day: safety_identifier and Translation (v3.33-3.34, v7.36-7.37)
On 2026-10-17 openai-python shipped v3.33.0/v3.34.0 and openai-node shipped v7.36.0/v7.37.0: safety_identifier reached image requests and responses, Realtime Translation sessions landed, and node added GPT-4 alias shutdown notices.
Read articleopenai-python 3.32.0 and openai-node 7.35.0: prompt-created voices, Live audio fixtures, and Decisions in Live
Both official SDKs shipped on 2026-10-16: voices created from a text description (Live only), 30-second Live audio fixtures, Decisions transcript triggers, and prompt caching for the Decisions API - all from the CHANGELOGs and tag sources.
Read articleBrowser and Computer Toolsets (1/4) Land in the OpenAI SDKs: BrowserToolset Turns Driver Methods into Function Tools
On 2026-10-14 the official SDKs shipped four releases: openai-python 3.30/3.31 and openai-node 7.33/7.34. The (1/4) browser and computer toolsets headline: BrowserToolset wraps a caller-supplied driver as ordinary function tools.
Read articleHosted agent environments surface in the OpenAI SDKs: prewarmed creation, idle suspension, expiration
Four releases in three days, October 9-11, 2026: openai-python 3.27-3.29 and openai-node 7.32 surface one agent environment API — prewarmed beta creation, idle suspension, expiration. Quoted from release notes and SDK source.
Read articleOpenAI API 429 Rate Limit Errors: RateLimitError and SDK Retries Explained
A 429 is two problems in one status: throughput limits vs quota exhaustion. The Python SDK already retries twice and honors Retry-After — this guide explains the mechanics from source.
Read articleopenai-node v7.20.0 Explained: Environment-Variable Vault Credentials, External Storage, and Safety Cases
Six PRs in one openai-node release: environment_variable vault credentials, external storage management, safety case retrieval with two webhook events, a SIP media security field, and a legacy GET fix — each traced to PR and tag sources.
Read article