GPT models: a census of 149 listings

OpenAI and Microsoft Azure's OpenAI are both listed as model subprocessors for all services, and ChatGPT is a supported MCP client, but model choice is not exposed to the customer.

Checked 2026-10-11

OpenAI's Codex CLI is the other half of the supported pair, listed as a prerequisite install alongside Claude Code.

Checked 2026-10-10

OpenAI is listed among the platforms it integrates, though no service page or case study names a delivered GPT build.

Checked 2026-09-09

A native OpenAI adapter is published for the GPT family with streaming, parallel tool calls and multimodal input, alongside an Azure OpenAI adapter for enterprise tenants.

Checked 2026-10-11

OpenAI models are the documented default path, with both Chat Completions and Responses adapters exposed as separate provider keys.

Checked 2026-10-11

Codex and ChatGPT are listed supported clients, which covers GPT-based agents, but the model itself comes from the client and is not part of what Loadout provides or prices.

Checked 2026-10-03

OpenAI models are listed among the best-supported engines and have their own provider page, with the entry command shown using an OpenAI key.

Checked 2026-09-30

OpenAI models are named among the selectable third-party foundation models, and the Prompts Studio documentation exposes editable prompts for an Azure OpenAI GPT model, so GPT is a first-class option.

Checked 2026-09-24

ChatGPT is likewise a supported MCP client that can search and enrich against your account, but nothing on the site says GPT is the model behind Duo's own drafting.

Checked 2026-09-10

The only OpenAI-lineage option in the reasoning-model table is the open-weight GPT-OSS-120b, absent on Enterprise; no proprietary GPT model appears anywhere in that per-plan matrix.

Checked 2026-09-10

ChatGPT connectors and OpenAI's Codex are both documented clients, with step-by-step setup against the hosted MCP endpoint.

Checked 2026-09-26

OpenAI models are named in the same delivered stack, evidencing hands-on GPT work on a client engagement rather than a supported-model list across all projects.

Checked 2026-10-03

OpenAI GPT models are pre-deployed on the platform, so an agent can use them with no key of your own, and realtime speech-to-speech GPT variants are included too.

Checked 2026-09-24

GPT-5.1 through GPT-5.6 variants are selectable, and a GPT Prism router is offered.

Checked 2026-09-02

OpenAI is the primary documented model client, installed as an extra, and GPT models are used in nearly every example throughout the guides.

Checked 2026-09-19

OpenAI models are named repeatedly across the generative AI, chatbot and white-label pages as a foundation they build customer solutions on, including GPT integration into CRMs and ERPs.

Checked 2026-09-11

First-party OpenAI integration maintained by Botpress, covering text generation plus image generation and speech-to-text, billed at cost to workspace AI Spend.

Checked 2026-09-02

OpenAI is the one model provider the vendor names, and bringing your own OpenAI key is the published route to uncapped message volume beyond the monthly credit allowance.

Checked 2026-09-13

OpenAI models are reachable through Model Gateway with only a Browserbase API key.

Checked 2026-09-02

OpenAI GPT models appear in the same supported-models table.

GPT models are supported on the same footing as Claude, through the Cline provider, an OpenAI key of your own, or Azure OpenAI on the enterprise path.

Checked 2026-09-12

OpenAI is named alongside Anthropic as a provider that processes code during reviews; the choice between them is CodeRabbit's, not the customer's, on hosted plans.

Checked 2026-09-15

GPT-5.6 Sol, Terra and Luna are all marked available in Codex CLI, selected with --model.

Checked 2026-09-02

The free included model is OpenAI's open-weight GPT OSS 120B and OpenAI is a named AI sub-processor, but no proprietary GPT model is listed as selectable.

Checked 2026-09-28

OpenAI is a listed sub-processor and Crescendo announced GPT-5 across CX Assistant, Voice of Customer and CX Insights, available to all customers rather than gated to a tier.

Checked 2026-09-12

OpenAI and Microsoft are named sub-processors supplying natural-language APIs; model choice per task is not published.

Checked 2026-09-02

OpenAI has a native SDK integration covering both Chat Completions and the Responses API, and gpt-4o-mini is the framework's documented default model.

Checked 2026-09-13

OpenAI models are available in the picker and priced per million tokens from the Other Models pool.

Checked 2026-09-02

OpenAI is named as an AI provider and appears as an LLM subprocessor on the trust centre, yet no page offers the customer a choice of GPT.

Checked 2026-09-14

OpenAI is a managed provider; the nano and mini GPT models bill at the Standard tier and the full models at Advanced, which roughly doubles the per-minute rate.

Checked 2026-09-02

OpenAI models are selectable in Devin CLI, with gpt among the three the vendor recommends trying first.

Checked 2026-09-02

Same gate as Claude: OpenAI frontier models come with Pro and above, while Free is marked "Limited model availability" with premium models crossed out.

Checked 2026-09-03

OpenAI models are covered by bundled message credits, or via your own key.

Checked 2026-09-02

GPT is named in the Business plan model bullet, and the model access tier tables list GPT variants in every tier including Ultra.

Checked 2026-10-01

OpenAI models are natively supported and are the one provider family the vendor says stays fully available under EU data residency.

Checked 2026-09-02

OpenAI appears in the same subprocessor inventory with the same purpose, so GPT models also serve responses, again chosen by Elicit rather than selected by the user.

Checked 2026-09-14

ChatGPT is named as a supported MCP client that can call every Faceless operation, but GPT is not selectable as the model that generates the video.

Checked 2026-10-03

OpenAI GPT-5 series models are offered natively, including Codex variants, each with a billing multiplier.

Checked 2026-09-02

OpenAI models are part of the same automatic failover pool as Anthropic and Google, so GPT is used by the platform but is not a model the customer chooses or configures on any tier.

Checked 2026-09-18

Self-hosted deployments can point LLM-backed extraction at an OpenAI-compatible provider; on Cloud the extraction model is managed by Firecrawl and not named.

Checked 2026-09-24

OpenAI models are in the routing lineup for reasoning and analysis, and the vendor states a zero data retention agreement is in place with OpenAI.

Checked 2026-09-14

OpenAI models are named in the vendor's own model-partner claim on the business page, and GPT image and Sora video models appear in plan and troubleshooting material.

Checked 2026-09-15

GPT models are in the catalog from the Free plan up, including the Codex variants; OpenAI models are hosted by OpenAI and GitHub's Azure infrastructure under a zero data retention agreement.

Checked 2026-09-02

OpenAI models are listed in the Model Hub text-model table, via Azure or OpenAI directly.

Checked 2026-09-02

OpenAI models reach ADK two ways: a native Go package the vendor marks experimental, and the LiteLLM connector for Python, so the path depends on your language.

Checked 2026-09-15

OpenAI models are supported directly, through Azure OpenAI and through a ChatGPT Plus/Pro sign-in for GPT-5 Codex; the docs exclude o1-mini and o1-preview because goose depends on tool calling.

Checked 2026-09-16

OpenAI is the default provider for the fast, smart and strategic model slots, so GPT models work out of the box.

Checked 2026-09-16

OpenAI is a listed provider and the available-models table carries several GPT entries served through OpenAI directly.

Checked 2026-09-30

OpenAI's Codex harness is listed as supported on the stable channel across shell, prompt, MCP, file-read and tool-result events.

Checked 2026-09-29

OpenAI models appear in the same in-stack leaderboard, and the security FAQ names OpenAI-based models as one of the two GenAI options offered to customers.

Checked 2026-09-24

OpenAI and the Codex CLI are named providers alongside GitHub Copilot, and any OpenAI-compatible endpoint can be pointed at, so GPT models run on your own key or an existing subscription.

Checked 2026-09-17

OpenAI models appear in the same paid-plan bundle as Anthropic's and are chosen from the model selector; free users get Julius Lite models only, so GPT access starts at the entry paid tier.

Checked 2026-09-17

OpenAI models are reachable both through the JetBrains subscription's curated cloud set and by connecting your own OpenAI key directly, with built-in CLI aliases routing to them.

Checked 2026-09-18

The only model-vendor disclosure anywhere on the site is a sub-processor entry naming OpenAI for voice processing and transcription; there is no plan row, docs page or settings screen that offers GPT as a selectable model, so this is a supply-chain fact rather than a supported-model claim.

Checked 2026-09-26

GPT models are in the hosted catalogue and available via an OpenAI BYOK key.

Checked 2026-09-02

A first-party langchain-openai package covers GPT models and Azure OpenAI deployments, and the gateway accepts OpenAI Chat Completions and Responses requests for them.

Checked 2026-09-18

OpenAI GPT models are supported in every installation via the core Language Model component, and the OpenAI bundle adds extra request parameters plus OpenAI embeddings.

Checked 2026-09-25

First-party ChatOpenAI integration, plus AzureChatOpenAI for GPT models hosted on Azure; both are listed in the featured chat-model table.

Checked 2026-09-02

ChatGPT in developer mode and Codex are supported MCP clients, and the vendor markets driving the product from ChatGPT on the same footing as Claude.

Checked 2026-09-18

GPT is named alongside Claude in the vendor's description of the multiple-LLM feature, so OpenAI models are an available choice for the agent's reasoning layer.

Checked 2026-09-09

OpenAI API keys and ChatGPT Plus/Pro Codex subscriptions both connect; toolsets switch per model family.

Checked 2026-09-02

OpenAI is named alongside Anthropic and Gemini as a model family a user picks per task, and model choice is not gated by plan according to Lindy's billing documentation.

Checked 2026-09-19

GPT-4o, GPT-4.1 and the GPT-5 families are served through LiveKit Inference with no separate OpenAI key, or via the OpenAI plugin on your own account.

Checked 2026-09-02

OpenAI models are supported directly or through Azure OpenAI.

Checked 2026-09-02

OpenAI is one of the two named providers the reasoning loop calls, and the hosted default routes through Azure OpenAI inside Microsoft's enterprise boundary.

Checked 2026-09-09

OpenAI is a disclosed foundational-model subprocessor for Manus itself, and GPT is nameable for LLM features in generated apps, but the agent's model is never user-selectable.

Checked 2026-09-02

OpenAI is a named first-class provider in the model router, with provider-specific options such as reasoningEffort.

Checked 2026-09-02

OpenAI models are named as engines Maven runs on, and the vendor publishes its own enterprise phone-call evaluation of OpenAI's newest realtime voice model, so GPT-family support is asserted rather than implied.

Checked 2026-09-25

Both OpenAI directly and Azure OpenAI are listed model providers, covering Chat Completions and the Responses API, with Microsoft Foundry as a third route to the same models.

Checked 2026-09-19

OpenAI models are available through the vendor's own routing layer with no separate OpenAI account required, and the catalogue lists GPT models by publisher.

Checked 2026-09-20

The privacy policy states that AI chat and content generation run on the OpenAI GPT model, and that conversation data is transmitted to OpenAI for processing after explicit consent.

Checked 2026-10-03

OpenAI is named among the AI model vendors that process prompts for Modurian, though the site never states which specific GPT models the router can select.

Checked 2026-10-09

GPT models are the foundation models behind reasoning and are the only family selectable in LLM Actions, with gpt-5.4-mini as the default.

Checked 2026-09-20

OpenAI Chat Model node plus a full OpenAI app node (assistant, text, image, audio, video operations); Azure OpenAI has its own node.

Checked 2026-09-02

OpenAI models, routed through Cloudflare's AI Gateway, are named as the primary processor behind resume parsing, chat, cover letters and auto-apply.

Checked 2026-09-29

Agents run on OpenAI's computer-use models, driven by the buyer's own OpenAI API key rather than vendor-supplied inference.

Checked 2026-10-08

GPT models are documented as a supported option for client automations, and OpenAI appears in the stack they list for AI product builds.

Checked 2026-09-26

OpenAI models are the largest block in the published catalogue, offered both directly and through Azure, and the agent API accepts them by name.

Checked 2026-09-09

OpenAI models are the default path, supported natively through both the Responses API and the Chat Completions API, with a GPT-5 family model used when an agent sets none.

Checked 2026-09-20

The endpoint runs OpenAI's own gpt-realtime speech-to-speech models with reasoning effort and function calling.

Checked 2026-09-02

OpenAI models work through a platform API key or a ChatGPT/Codex sign-in, with the Codex app-server able to run the embedded agent turn itself.

Checked 2026-09-21

GPT models are listed on the Zen gateway endpoint table with their own model IDs, alongside direct OpenAI and Azure provider support.

Checked 2026-09-21

GPT-5 and GPT-5 Codex appear in the vendor's own model price list, and Azure OpenAI is a documented provider route too.

Checked 2026-09-21

The Agent API lists the GPT-5 family with per-token rates; the consumer plans surface GPT as a selectable preferred model.

Checked 2026-09-02

OpenAI is named first among the catalogue's providers and GPT and ChatGPT model cards are selectable in the builder, with cost per model shown on the same page.

Checked 2026-09-09

OpenAI GPT and Codex are named in the same model inventory, and the edge-privacy page names OpenAI again as an approved external processor.

Checked 2026-10-03

OpenAI GPT is one of the third-party models you can run instead of Raven; the model docs list GPT options under the OpenAI provider tab, selectable per channel.

Checked 2026-09-02

OpenAI is the first listed built-in provider and appears throughout the docs as openai:gpt-… model strings, with an openai extra installed by the default package.

Checked 2026-09-21

OpenAI and Azure OpenAI Service are named generative-AI subprocessors.

Checked 2026-09-02

The vendor's own model/vendor table lists GPT supplied by OpenAI with no logging and no training, available when you supply no API key of your own.

Checked 2026-09-22

OpenAI GPT variants appear in the published model catalogue for both paid modes; Free Mode routes automatically and offers no picker.

Checked 2026-09-22

Multiple GPT tiers are offered as conversation models, each with its own per-minute rate and an optional faster tier for lower latency.

Checked 2026-09-23

The vendor states in its own changelog that the rebuilt agent runs on OpenAI's GPT line; buyers inherit that choice rather than making it, since no model setting is exposed.

Checked 2026-09-09

OpenAI, LLC is a named AI service-provider subprocessor under zero data retention; as with every model in Rox, the vendor routes it and the buyer cannot pick it.

Checked 2026-09-03

GPT-4o is named alongside Claude and Gemini as a model the MCP integration connects live client data to, with no tier restriction stated.

Checked 2026-09-28

OpenAI and Azure OpenAI GPT models fill most of the supported-model table, and the out-of-the-box Salesforce Default option is a GPT-based managed mix.

Checked 2026-09-03

Both OpenAI surfaces are listed on every plan: ChatGPT via remote MCP and Codex as a documented connection path.

Checked 2026-09-25

The homepage hero states the product is powered by GPT agents, which is the only model family the vendor names anywhere on its own site; no version or selection is disclosed.

Checked 2026-09-25

OpenAI is used for images, embeddings and some text tasks rather than as the main writer, though a workspace may elect to run its text generation on OpenAI with its own key.

Checked 2026-10-03

OpenAI is listed as an AI-services subprocessor, so GPT models are used under the hood, chosen by Sierra's router rather than by the buyer.

Checked 2026-09-26

OpenAI models are supported, with hosted GPT-5/GPT-4.1 rates published at a 1.1x multiplier.

Checked 2026-09-03

GPT is named in the streaming guide as a model you wire behind the webhook; inference is yours to arrange and pay for.

Checked 2026-09-26

ChatGPT and Codex are named as supported MCP clients, so GPT models reach the tools through OpenAI's own products; the vendor never states which model its web audit runs on.

Checked 2026-10-03

OpenAI models are selectable directly, and the docs also describe adding them through an Azure OpenAI private-cloud connection for latency and compliance reasons.

Checked 2026-09-09

The model selector lists GPT-4o, GPT-4.1 and multiple GPT-5 variants for agent responses.

Checked 2026-09-03

Codex runs as a supported harness and OpenAI is listed among the cloud providers Tale serves, with ChatGPT subscriptions usable through the broker.

Checked 2026-10-03

OpenAI is one of three providers a user can select in the published Chrome extension; for the delivered agency services the vendor does not state which model powers a deployment.

Checked 2026-09-12

GPT is the platform's reasoning layer: the pricing calculator meters GPT-5, GPT-5 Mini, GPT-5 Nano, GPT 4.1 and GPT 4.1 Mini, and OpenAI is the sole LLM provider named in the sub-processor table.

Checked 2026-09-16

GPT models run as an external provider you supply credentials for: you create an OpenAI API key, store it as an integration secret and select the model, and OpenAI free-plan keys are rejected outright.

Checked 2026-09-09

OpenAI is a first-class provider in the Agents model documentation and in the platform LLM configuration table, selectable per agent alongside Anthropic and Google.

Checked 2026-09-03

Named as the reasoning engine only in the January 2024 whitepaper, which the homepage itself labels the v1 engine; no current page names any model provider.

Every tier lists GPT model access, with the newer advanced model reserved for the Business plan.

Checked 2026-09-27

OpenAI GPT models are selectable as the assistant's LLM.

Checked 2026-09-03

OpenAI models appear in the same catalog under openai/ model IDs, so a buyer can select GPT through the membership rather than a separate OpenAI account.

Checked 2026-09-27

OpenAI models are selectable, and the shipped Quality, Balanced and Fast inference profiles are all built on GPT models out of the box.

Checked 2026-09-27

OpenAI is one of the named providers that can run the live conversation, and it is the sole provider used for two-way call translation.

Checked 2026-09-22

OpenAI is a selectable LLM provider per agent, and also appears as an STT and TTS provider.

Checked 2026-09-03

OpenAI is the named language-model subprocessor in the published DPA schedule, so GPT models do the comprehension work; the buyer does not select the model and the vendor may swap providers.

Checked 2026-10-03

All AI features run on OpenAI's pre-trained models; Warmly trains no models of its own.

Checked 2026-09-03

OpenAI models are listed in the vendor's own model table alongside Anthropic and Google; Codex is also supported as an alternative harness.

Checked 2026-09-03

GPT-5.4 is named by the vendor as one of the two models the Hound 1.0 research harness is built with, though buyers cannot select it themselves.

Checked 2026-09-27

ChatGPT is the default provider and the product's headline use case, including Pro accounts, driven through the signed-in web session.

Checked 2026-09-21

OpenAI GPT models are in the hosted catalogue with published token rates, and the Pro trial runs on a GPT model as its only hosted option.

Checked 2026-09-29

OpenAI models are in the managed catalogue on paid plans and the Codex CLI can run as the agent runtime; the largest GPT tier needs Pro Plus or above.

Checked 2026-09-09

Generative features run on OpenAI via zero-data-retention endpoints; Zendesk names the provider, not a model version.

Checked 2026-09-03

OpenAI is supported through both the Chat Completions and Responses APIs with a key, and through a ChatGPT Plus or Pro subscription via the Codex login flow.

Checked 2026-09-28

OpenAI models are the most frequently named across the site, with a dedicated GPT integration service and GPT-4o cited for complex reasoning in their routing approach.

Checked 2026-09-25