Catalog Systems Foundation models (substrate reference) OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4)

OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4)

https://openai.com/index/introducing-gpt-5/

OpenAI's foundation model family — GPT-5 (2025-08 flagship), GPT-4o (multimodal workhorse), o3/o4 reasoning series. Substrate for ChatGPT, the OpenAI API, Microsoft Copilot, Azure OpenAI, and many downstream agents in this catalog (Devin, Codex CLI, Operator, Cursor mode). Parametric memory in weights; discrete user memory ships in ChatGPT Memory feature (separate row).

Active · Verified 2026-10-31 · fresh as of 2026-10-31 · 37 cited facts, 1 with a third-party source · 2 recorded changes · Suggest a correction

At a glance

Type
Frontier foundation model family (GPT-5 / GPT-4o / o3 / o4) vendor fix
Tier
T1
Section
Foundation models (substrate reference)
Created
2018 (GPT-1); 2020-06 (GPT-3); 2023-03 (GPT-4); 2024-05 (GPT-4o); 2024-09 (o1); 2025-01 (o3); 2025-08 (GPT-5) vendor fix
Latest release
GPT-6.1 Terra (2026-10-26; computer use) and GPT-6.1 Sol; earlier GPT-6 Sol / Luna / Instant in ChatGPT (2026-10-07) and API flagship GPT-6 Astra (announced 2026-09-03) vendor fix
License
proprietary (API only) vendor fix
GitHub
not applicable — no GitHub repo fix
Pricing
API flagship GPT-6 Astra $10 input / $50 output per 1M tokens (Fast mode 2x price); ChatGPT Free / Go / Plus / Pro / Business / Enterprise plans vendor fix
Funding
$57.9B+ total raised; $500B valuation (2025 secondary tender); Microsoft $13B+ strategic investment vendor fix
Freshness
2026-10-31 fix
Layer
large-models repo fix
Licensing
commercial vendor fix
Deployment locus
cloud vendor fix
Platform vs product
both vendor fix
SDK languages
csharp, go, java, python, rest, ruby, typescript vendor fix
Protocols
mcp-client vendor fix
Compliance
gdpr, hipaa, soc2-type2 vendor fix

When to use

Optimised for: general-purpose reasoning, coding, multimodal, voice/real-time

Anti-fit: weights closed; data residency limited (US/EU/Asia regions only); rate-limited without enterprise; no open-weights option; Sora video gated

Pros & cons

Pros

Most-deployed frontier LLM (800M+ MAU ChatGPT); full multimodal stack (vision + audio + image gen + video gen); largest ecosystem of fine-tunes / RAG / agent integrations; Azure distribution.

Cons

Closed weights; expensive at Pro/o3 tier; legal exposure (multiple ongoing NYT / Authors Guild lawsuits); Sora & advanced features behind waitlists; SWE-bench trails Claude Opus 4.5.

Claims & capabilities

GPT-5 Aug-2025 unified reasoning + non-reasoning; o3 first to score >85% on AIME 2025; GPT-4o multimodal (vision/audio/text); 128k context (GPT-5: 400k); function-calling, structured outputs, real-time API

Technical surface

API surface
REST + SDK (Python, TS, Java, Go, .NET); Azure OpenAI variant; Realtime API (WebRTC)
Backend storage
not applicable — substrate foundation model
Deployment
Managed-only — OpenAI API + ChatGPT, also Microsoft Azure and AWS Bedrock (separate gpt-oss open-weight models exist)
Embedding model
not applicable — not a memory product
Multi-tenancy
not applicable — substrate foundation model
MCP
not applicable — substrate foundation model
A2A
not applicable — substrate foundation model
OpenTelemetry
not applicable — substrate foundation model

Compare OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) with…

Similar systems

Other foundation models (substrate reference) in the catalog, ranked by inbound references.

  • Anthropic Claude (foundation models) T1

    Claude family of frontier foundation models — Sonnet 4 (workhorse), Opus 4.5 (frontier capability), Haiku 4.5 (fast/cheap). Frontier model used as substrate by Claude Code, Anthropic Memory tool, Cline, Aider, Continue.dev, Cursor, Goose, and dozens of other catalog entries. Memory in Claude is parametric (in weights) — discrete episodic memory lives outside the model in the Claude Memory tool (see Platform-provider memory section).

  • Google Gemini 3 family T1

    Google DeepMind's Gemini 3 frontier model family — Gemini 3 Pro (top tier), 3 Flash (fast), 3 Nano (on-device). Substrate for Google Workspace AI, Vertex AI Agent Platform, Gemini Code Assist, Project Mariner, and Project Astra. Multimodal-native; 1M-10M context window. Largest context window of any frontier model. Used by Gemini Enterprise Agent Platform Memory Bank (separate row).

  • Mistral Large 2 / Mixtral family T1

    French frontier-model lab (Paris). Family includes Mistral Large 2 (123B dense, Jul-2024), Mixtral 8x22B (open-weights MoE), Mistral Small 3 (24B, open-weights Jan-2025), Codestral (code specialist). EU-headquartered alternative to US/China model labs; GDPR-friendly data residency. Distinct from the Mistral Le Chat memory feature (already in catalog) — this row covers the model family itself as substrate.

  • xAI Grok 4 T1

    Elon Musk's xAI frontier model — Grok 4 launched 2025-07. Trained on Colossus (100k+ GPU supercluster in Memphis). Deeply integrated with X/Twitter (real-time tweet data access). Grok 4 Heavy variant for premium tier. No frontier-tier open-weights — Grok 1 (314B MoE) is the only weight release. The x.ai site now brands itself SpaceXSI (page title, checked 2026-10-29).

  • Cohere Command R+ / Command A T1

    Toronto-based foundation-model lab (Aidan Gomez, ex-Google Brain 'Attention Is All You Need' co-author). Command family is enterprise / RAG-optimised: Command A (Mar-2025, 111B dense, 256k ctx), Command R+ (104B MoE), Command R7B (smallest tier). Announced merger with Aleph Alpha April-2026. Open weights via CC-BY-NC (non-commercial); Cohere-hosted for commercial.

  • DeepSeek R1 / V3 family T1

    DeepSeek (Hangzhou-based, Liang Wenfeng founder) — released DeepSeek-V3 671B MoE (37B active) Dec-2024, then R1 reasoning model Jan-2025 that matched o1 at ~3% of inference cost. Caused 'DeepSeek moment' in markets Jan-27-2025 — NVIDIA dropped 17%. MIT license. Substrate for cost-conscious OSS deployers and an active reasoning-research baseline.

Sources (36 cited facts, 1 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

What changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 2026-10-28
    • Latest release “GPT-6 Sol / Luna / Instant in ChatGPT (2026-10-07); API flagship GPT-6 Astra (announced 2026-09-03, staged rollout)” → “GPT-6.1 Terra (2026-10-26; computer use) and GPT-6.1 Sol; earlier GPT-6 Sol / Luna / Instant in ChatGPT (2026-10-07) and API flagship GPT-6 Astra (announced 2026-09-03)” source
    #290
  2. 2026-10-26
    • License “not applicable — not OSS” → “proprietary (API only)” source
    • Latest release “GPT-5 (2025-08), o4-mini, GPT-4.1 series” → “GPT-6 Sol / Luna / Instant in ChatGPT (2026-10-07); API flagship GPT-6 Astra (announced 2026-09-03, staged rollout)” source
    • Pricing “Pay-per-token API (GPT-5 $1.25/$10 per 1M; GPT-4o $2.50/$10; o3 $2/$8); ChatGPT Free + Plus ($20/mo) + Pro ($200/mo) + Team + Enterprise” → “API flagship GPT-6 Astra $10 input / $50 output per 1M tokens (Fast mode 2x price); ChatGPT Free / Go / Plus / Pro / Business / Enterprise plans” source
    • Deployment “Managed-only (OpenAI API + Microsoft Azure OpenAI)” → “Managed-only — OpenAI API + ChatGPT, also Microsoft Azure and AWS Bedrock (separate gpt-oss open-weight models exist)” source
    #258

Related systems

Referenced by (103)

  • 1X Technologies depends on at runtime — adjacent-infrastructure cell: OpenAI Startup Fund portfolio; Norwegian / US robotics ecosystem
  • Adept ACT depends on at runtime — adjacent-infrastructure cell: Amazon AGI (parent post-acquisition); spiritual predecessor to Anthropic Computer Use + OpenAI Operator + Project Mariner
  • Agent Router (formerly Envoy AI Gateway) depends on at runtime — Open-source, Envoy-powered control plane giving agents one OpenAI-compatible API for every model and one router for MCP tools, with provider credentials, failover and token limits.
  • agentgateway integrates with — agentgateway integrations docs have a OpenAI provider page. (verified 2026-10-29)
  • AgentOps integrates with — AgentOps docs have a OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) integration page. (verified 2026-10-29)
  • Arize Phoenix integrates with — Arize Phoenix docs have a OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) integration page. (verified 2026-10-29)
  • AutoGen / AG2 integrates with — AG2 model configuration docs list OpenAI as a supported model provider with a config example. (verified 2026-10-29)
  • Backboard depends on at runtime — adjacent-infrastructure cell: BYO LLM (OpenAI/Anthropic/Gemini/Ollama keys)
  • Bifrost (Maxim AI) depends on at runtime — Open-source Go AI gateway from Maxim AI with one OpenAI-compatible API for many models, failover, load balancing, semantic caching, virtual keys and budgets, and a built-in MCP gateway for agents.
  • Braintrust integrates with — Braintrust docs have a OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) integration page. (verified 2026-10-29)
  • Browser Use depends on at runtime — adjacent-infrastructure cell: Playwright; Anthropic / OpenAI / Gemini APIs; Browserbase / Hyperbrowser substrates
  • ChatGPT — Codex (cloud agent) depends on at runtime — adjacent-infrastructure cell: OpenAI Codex (model) + cloud sandbox
  • Cline (harness) depends on at runtime — adjacent-infrastructure cell: OpenAI-compatible API; MCP
  • Cloudflare AI Gateway depends on at runtime — Gateway in front of 20+ model providers with an OpenAI-compatible unified API, caching, rate and spend limits, dynamic routing, guardrails, DLP and BYOK, plus logging and analytics.
  • Cognition Devin v2 / Spec Mode depends on at runtime — adjacent-infrastructure cell: absorbed Windsurf IP (Aug 2025); Anthropic + OpenAI models
  • Comet ML integrates with — Comet's Opik docs have a OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) integration page. (verified 2026-10-29)
  • Composio integrates with — Composio's SDKs and frameworks page lists a OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) provider. (verified 2026-10-29)
  • Continue.dev depends on at runtime — adjacent-infrastructure cell: any OpenAI-compatible API; MCP
  • CrewAI integrates with — CrewAI LLM docs include an OpenAI provider configuration section. (verified 2026-10-29)
  • Cursor (IDE) depends on at runtime — adjacent-infrastructure cell: Anthropic Claude + OpenAI GPT + own Cursor-Tab model
  • Datadog Agent Observability (LLM Observability) integrates with — Datadog LLM Observability auto-instrumentation page lists a OpenAI LLM integration. (verified 2026-10-29)
  • Daytona integrates with — Daytona docs have a guide for running OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) with Daytona sandboxes. (verified 2026-10-29)
  • Decagon depends on at runtime — Backed by OpenAI. ElevenLabs partnership for voice (2025).
  • DSPy integrates with — DSPy language model docs have an OpenAI setup tab for dspy.LM. (verified 2026-10-29)
  • Elasticsearch integrates with — Elastic Search Labs has a OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) integration page. (verified 2026-10-29)
  • Figure AI depends on at runtime — adjacent-infrastructure cell: BMW manufacturing; OpenAI partnership (ended Feb 2025); Microsoft Azure
  • Galileo integrates with — Galileo's third-party integrations docs list OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) as a supported integration. (verified 2026-10-29)
  • GitHub Copilot (Agent Mode) depends on at runtime — adjacent-infrastructure cell: Azure OpenAI + Anthropic Claude + Google Gemini (multi-model 2024+)
  • GitHub Copilot Workspace depends on at runtime — adjacent-infrastructure cell: Azure OpenAI + Anthropic Claude (GitHub-hosted models)
  • Golem integrates with — Golem "Adding LLM and AI Capabilities (TypeScript)" guide shows the official OpenAI SDK working in Golem agents. (verified 2026-10-29)
  • Google Agent Development Kit (ADK) integrates with — ADK docs have an OpenAI model page for ADK agents. (verified 2026-10-29)
  • Haystack (framework) integrates with — Haystack integrations directory has an OpenAI integration page ("Use OpenAI Models with Haystack"). (verified 2026-10-29)
  • Helicone integrates with — Helicone docs have a OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) integration page. (verified 2026-10-29)
  • Highlight AI depends on at runtime — adjacent-infrastructure cell: Anthropic / OpenAI APIs; local Llama option
  • HoneyHive integrates with — HoneyHive integrations docs have a OpenAI tracing/integration page. (verified 2026-10-29)
  • Hume EVI depends on at runtime — adjacent-infrastructure cell: Twilio (telephony); Anthropic / OpenAI LLMs (or Hume's eLLM)
  • Inngest integrates with — Inngest AgentKit docs: AgentKit OpenAI model adapter (reference). (verified 2026-10-29)
  • Inspect AI integrates with — Inspect AI model-providers page documents a OpenAI provider. (verified 2026-10-29)
  • Invariant Guardrails integrates with — Invariant Gateway README has a OpenAI (Chat Completions/Responses) integration section. (verified 2026-10-29)
  • Inworld AI depends on at runtime — now sells realtime voice models (TTS-2, STT-1, speech-to-speech) and OpenAI-compatible open-model inference.
  • JetBrains AI Assistant depends on at runtime — adjacent-infrastructure cell: JetBrains Cloud (OpenAI + Anthropic + Google)
  • Keycard integrates with — Keycard docs have a "Configure OpenAI" credential-brokering page. (verified 2026-10-29)
  • Kong AI Gateway integrates with — Kong AI Gateway docs have a OpenAI AI-provider reference page. (verified 2026-10-29)
  • Laminar integrates with — Laminar integrations docs have a OpenAI observability page. (verified 2026-10-29)
  • LanceDB integrates with — LanceDB's docs have a OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) integration page. (verified 2026-10-29)
  • LangChain (framework) integrates with — LangChain docs have an OpenAI integration provider page (GPT models and comprehensive AI platform). (verified 2026-10-29)
  • Langflow integrates with — Langflow components bundle: OpenAI language model component. (verified 2026-10-29)
  • Langfuse integrates with — Langfuse's integrations directory has a OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) integration page. (verified 2026-10-29)
  • LangSmith integrates with — LangSmith docs have a tracing integration page for OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4). (verified 2026-10-29)
  • Letta / MemGPT integrates with · depends on at runtime — adjacent-infrastructure cell: BYO LLM (OpenAI/Anthropic/local); bundled storage (Postgres/SQLite)
  • LiteLLM integrates with · depends on at runtime — 100+ LLM providers behind OpenAI-compatible API
  • LiveKit Agents integrates with · depends on at runtime — adjacent-infrastructure cell: OpenAI Realtime; Anthropic; Deepgram / Cartesia / Eleven STT-TTS; Twilio (for PSTN)
  • LlamaIndex (framework) integrates with — LlamaIndex has an official LLM integration package llama-index-llms-azure-openai in its repo. (verified 2026-10-29)
  • Lovable.dev — harness depends on at runtime — adjacent-infrastructure cell: Supabase (default DB); Anthropic Claude + OpenAI
  • Lutra AI depends on at runtime — adjacent-infrastructure cell: OAuth providers; Anthropic / OpenAI; Google Workspace
  • Magnitude depends on at runtime — adjacent-infrastructure cell: Playwright; Anthropic / OpenAI APIs
  • Manus AI depends on at runtime — adjacent-infrastructure cell: Anthropic Claude (reported) + OpenAI
  • Meilisearch depends on at runtime — Automatic embedding generation + caching via OpenAI / HuggingFace / Ollama.
  • Mem0 integrates with — Mem0 docs have an OpenAI as LLM Provider LLM provider page for Mem0 open source. (verified 2026-10-29)
  • MetaGPT depends on at runtime — adjacent-infrastructure cell: OpenAI + Anthropic + Azure OpenAI
  • Microsoft Semantic Kernel integrates with — Semantic Kernel chat completion docs list an OpenAI AI service connector. (verified 2026-10-29)
  • MultiOn (now AGI, Inc.) depends on at runtime — adjacent-infrastructure cell: Playwright; Chromium-headless infrastructure; computer-use models (Claude / GPT-5 / Gemini)
  • n8n (AI agent flows) integrates with — n8n built-in AI cluster node: OpenAI Chat Model node. (verified 2026-10-29)
  • OpenAI Agents SDK depends on at runtime — Built on the OpenAI Responses API and tools.
  • OpenAI Agents SDK Memory depends on at runtime — adjacent-infrastructure cell: requires OpenAI API; BYO persistence layer
  • OpenAI ChatGPT Memory depends on at runtime — backend-storage cell: custom (OpenAI-managed)
  • OpenAI Codex CLI depends on at runtime — adjacent-infrastructure cell: OpenAI API (Codex / o-series); MCP for tool extensibility; runs locally with TLS-only network egress
  • OpenAI Operator depends on at runtime — backend-storage cell: OpenAI-hosted browser session state; no durable cross-session memory by default
  • Opencode (SST) depends on at runtime — adjacent-infrastructure cell: any OpenAI-compatible API; MCP
  • OpenHands depends on at runtime — adjacent-infrastructure cell: Docker; Anthropic + OpenAI APIs
  • OpenInference integrates with — The OpenInference repo README lists an OpenInference instrumentation package for OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4). (verified 2026-10-29)
  • OpenLLMetry (Traceloop) integrates with — OpenLLMetry's What's Supported page lists OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) as instrumented out of the box. (verified 2026-10-29)
  • OpenRouter integrates with — OpenRouter lists OpenAI as an inference provider (providers API slug "openai"). (verified 2026-10-29)
  • Phidata (now Agno) integrates with · depends on at runtime — adjacent-infrastructure cell: HuggingFace Transformers; OpenAI / Anthropic / Gemini SDKs; YC W22 alumni network
  • Pipecat (Daily) integrates with · depends on at runtime — adjacent-infrastructure cell: Daily WebRTC; OpenAI Realtime; Anthropic; Deepgram + Cartesia STT/TTS
  • Pipedream Connect integrates with — Pipedream Connect docs have an OpenAI integration page for Pipedream MCP. (verified 2026-10-29)
  • Portkey AI integrates with — Portkey docs have an OpenAI LLM provider integration page. (verified 2026-10-29)
  • Presidio integrates with — Presidio samples include synthetic data generation with OpenAI. (verified 2026-10-29)
  • Pydantic-AI integrates with — Pydantic AI docs have an OpenAI model provider page. (verified 2026-10-29)
  • Pydantic Logfire integrates with — Pydantic Logfire integrations docs have a OpenAI page. (verified 2026-10-29)
  • PyRIT integrates with — PyRIT Prompt Targets docs have OpenAI Chat, Responses, Image, Video and TTS targets. (verified 2026-10-29)
  • RepairAgent depends on at runtime — average ~270,000 tokens (~$0.14 USD) per bug using GPT-3.5 pricing
  • Retell AI depends on at runtime — adjacent-infrastructure cell: Twilio SIP; in-house STT/TTS; Anthropic / OpenAI LLMs
  • Roo Code depends on at runtime — adjacent-infrastructure cell: OpenAI-compatible APIs
  • Skyvern depends on at runtime — adjacent-infrastructure cell: Playwright; Postgres; Anthropic/OpenAI/Gemini APIs
  • smol-developer depends on at runtime — adjacent-infrastructure cell: OpenAI API (GPT-3.5/4); single-file Python script; no other dependencies beyond LLM provider
  • smolagents (Hugging Face) integrates with — smolagents models reference documents OpenAIModel. (verified 2026-10-29)
  • Sourcegraph Cody (agent) depends on at runtime — adjacent-infrastructure cell: Sourcegraph search graph; OpenAI + Anthropic + Google APIs
  • Speak depends on at runtime — OpenAI-backed.
  • Strands Agents (AWS) integrates with — Strands Agents docs have an OpenAI model provider page. (verified 2026-10-29)
  • Supabase Vector integrates with — Supabase AI integrations: OpenAI completions from Edge Functions. (verified 2026-10-29)
  • Synthflow depends on at runtime — adjacent-infrastructure cell: Twilio; Deepgram; ElevenLabs; OpenAI / Anthropic
  • TrueFoundry AI Gateway integrates with — TrueFoundry AI Gateway docs have a OpenAI model-provider page. (verified 2026-10-29)
  • v0 (Vercel) depends on at runtime — adjacent-infrastructure cell: Vercel deploy; Anthropic + OpenAI + Vercel-trained models
  • Vapi integrates with · depends on at runtime — adjacent-infrastructure cell: Twilio / Vonage SIP; Deepgram + Cartesia + Eleven STT/TTS; Anthropic / OpenAI LLMs
  • Vercel AI Gateway depends on at runtime — Vercel's unified endpoint for text, image, video and speech models across providers, used from the AI SDK and OpenAI-compatible clients.
  • Vercel AI SDK integrates with — AI SDK docs have an OpenAI official AI SDK provider page. (verified 2026-10-29)
  • Vonage AI Studio depends on at runtime — adjacent-infrastructure cell: Vonage CPaaS; Ericsson telco infra; OpenAI / Anthropic / Google Cloud
  • Weaviate integrates with — Weaviate's integrations / model-provider docs list OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) as an integration. (verified 2026-10-29)
  • Weights & Biases integrates with — W&B Weave docs have a OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) integration page. (verified 2026-10-29)
  • Windsurf (now Devin Desktop) depends on at runtime — adjacent-infrastructure cell: Anthropic Claude + OpenAI + Codeium-own models
  • Zed (Agentic Editing) depends on at runtime — adjacent-infrastructure cell: Anthropic Claude + OpenAI + local models (Ollama)
  • Zep & Graphiti integrates with — Graphiti README names OpenAI as the default LLM provider. (verified 2026-10-29)