Bring your own key: a census of 126 listings

Entirely your own inference: it drives the Claude Code and Codex sessions already installed on your machine and needs no account or key of its own.

Source retrieved 2026-09-02

Agents are wired into the client's own systems and infrastructure where the architecture allows, with credentials held outside prompts under least privilege.

Source retrieved 2026-09-09

Every adapter and integration takes credentials you pass in config, and local runtime adapters mean the inference itself can stay on your own machine.

Source retrieved 2026-09-09

You supply each provider's own API key by environment variable, and the runtime runs on your compute.

Source retrieved 2026-09-02

Bring-your-own-key is the only model: keys go in on the command line, in environment variables, a .env file or the YAML config, and inference can be your own local server instead.

Source retrieved 2026-09-09

Your own cloud and your own model are both offered - AWS, Azure, GCP, VPC, hybrid or on-premises deployment, with proprietary models routed through the gateway - but supplying your own provider API keys is documented nowhere.

Source retrieved 2026-09-03

You can bring your own sending infrastructure - custom SMTP or SendGrid alongside Gmail and Outlook mailboxes - but nothing published offers bring-your-own model keys, inference account or cloud tenancy.

Source retrieved 2026-09-10

You can run the CLI on your own Gemini API key with no account session, or on your own Google Cloud project; the plans page still says bring-your-own-key is unsupported, which contradicts this.

Source retrieved 2026-09-10

Own keys accepted across the stack: STT/TTS accounts, LLM providers including Azure OpenAI and Vertex AI, and your own SIP carriers.

Source retrieved 2026-09-03

You can supply your own machines or cloud for execution, but all inference is billed through Augment; no bring-your-own model key is documented.

Source retrieved 2026-09-02

Every key and endpoint is yours: OpenAI, Azure OpenAI with key or Entra token auth, Anthropic, Azure AI Foundry, or a local Ollama server, all billed to you.

Source retrieved 2026-09-02

Builds are explicitly assembled on the platforms, APIs and AI models the client already runs, and the self-hosted case study shows inference kept on customer-owned infrastructure.

Source retrieved 2026-09-11

You can bring your own telephony and, on Enterprise, your own cloud or hardware, but never your own model keys.

Source retrieved 2026-09-11

Bring-your-own-cloud is an Enterprise deployment option; no tier lets you supply your own model API keys or inference provider.

Source retrieved 2026-09-11

Bring-your-own-LLM is Enterprise-only and sales-gated, and the mechanism is building an SDK integration rather than pasting a key; on other plans Botpress makes and bills the model calls. No bring-your-own-cloud.

Source retrieved 2026-09-02

Supplying your own model key is the published escape from the credit ceiling, and white-label agencies can mark that inference cost up when billing their own clients.

Source retrieved 2026-09-13

You may bring your own model provider, your own proxies, and on Enterprise your own S3 storage.

Source retrieved 2026-09-02

No bring-your-own LLM key: Cartesia bills the LLM itself. You can bring your own carrier via SIP trunking and host the agent's reasoning code yourself.

Source retrieved 2026-09-02

Your own Anthropic key, your own proxy via ANTHROPIC_BASE_URL, or your own cloud through Bedrock, Claude Platform on AWS, Google Cloud or Microsoft Foundry.

Source retrieved 2026-09-02

Bring your own Anthropic API key, or your own cloud account via Amazon Bedrock, Google Cloud's Agent Platform or Microsoft Foundry; apiKeyHelper supports vault-issued tokens.

Source retrieved 2026-09-02

Bring-your-own-key is the default path and extends to your own cloud accounts (Bedrock, Vertex, Azure OpenAI) and your own weights on Ollama or LM Studio.

Source retrieved 2026-09-12

Bring-your-own inference exists only in the Enterprise self-hosted deployment, where the agent sends prompts to your own LLM account; hosted plans use CodeRabbit's providers.

Source retrieved 2026-09-15

Sign in with an OpenAI API key, or point the provider at Amazon Bedrock with AWS-native credentials.

Source retrieved 2026-09-02

Inference runs on your own provider accounts: you supply each provider key, or manage LLM connections centrally in the platform, and Enterprise can host the runtime in your cloud.

Source retrieved 2026-09-13

Your own keys for OpenAI, Anthropic, Google, Azure OpenAI and AWS Bedrock; chat models only, Zero Data Retention does not apply, and Enterprise admins can disable BYOK.

Source retrieved 2026-09-02

Bring your own LLM, your own TTS, or both, and the rate drops accordingly; Bedrock and Groq require your own endpoint and credentials, and the browser SDK can point at a proxied or self-hosted WebSocket URL.

Source retrieved 2026-09-02

Your own AWS KMS key encrypts data at rest, but only on the Enterprise Assured deployment; no bring-your-own-inference is documented.

Source retrieved 2026-09-02

Bring your own provider keys, billed to your own provider account, and run them alongside or instead of bundled credits; own cloud via self-host or VPC.

Source retrieved 2026-09-02

Point an agent at your own OpenAI-compatible endpoint with your own key held in workspace secret storage; inference then bills to you, not to ElevenLabs credits.

Source retrieved 2026-09-02

You bring your own documents and your institution's publisher subscriptions; the vendor documents no way to supply your own model keys or inference.

BYOK covers your own OpenAI/Anthropic keys, OpenAI-compatible gateways, local models and AWS Bedrock; keys stay on your machine.

Source retrieved 2026-09-02

Bringing your own inference means self-hosting: the open-source path lets you choose where the stack runs and connect your own providers. Firecrawl Cloud accepts no customer LLM key on any endpoint or tier.

Source retrieved 2026-09-03

Your key is an overflow path, not the billing model: once the daily agent quota is spent you can set geminicodeassist.geminiApiKey to a Gemini or Vertex AI key. Inference stays on Google.

Source retrieved 2026-09-02

Agents you host on your own computer run on your hardware with your own model access and spend no Genspark credits, but cloud agents give no option to supply your own provider keys.

Source retrieved 2026-09-15

Local keys are supported in VS Code, JetBrains, Xcode, the CLI, the desktop app and the SDK; enterprise-wide custom models are a public preview, and admins can disable local BYOK for Business and Enterprise users.

Source retrieved 2026-09-02

Customer Key lets you use your own provider keys, and credits are discounted for doing so; Glean's Universal Model Key is the alternative.

Source retrieved 2026-09-02

Inference always runs on your own credentials: the quickstart has you write your own model API key into a local env file, and the runtime is yours to host.

Source retrieved 2026-09-15

Keys are always yours: you paste provider API keys, point the OpenAI provider at your own vLLM or proxy endpoint, define custom providers in JSON, or run models locally with no key at all.

Source retrieved 2026-09-16

Bring-your-own-key is the only model: your LLM and retriever credentials go in environment variables on infrastructure you run.

Source retrieved 2026-09-16

Your own provider keys are accepted on both plans and zero the token charge, but the orchestration fee doubles to sixteen per cent of the notional list cost.

Source retrieved 2026-09-09

You can bring your own telephony: existing numbers, a Twilio or Exotel account, or a SIP trunk registered through the API. There is no bring-your-own model key, inference endpoint, or cloud account.

Source retrieved 2026-09-10

Enforcement already runs on hardware you own, and Enterprise can place the shared control plane inside your own network boundary; no bring-your-own model key applies because Guard calls no model.

Source retrieved 2026-09-07

Bringing your own models or your own cloud only holds in the private deployment line; hosted customers choose between IrisAgent's private models and OpenAI, not their own keys.

Source retrieved 2026-09-03

You bring your own inference: either an existing provider subscription or your own API keys, stored locally in an owner-only credentials file, and local models via Ollama are equally supported.

Source retrieved 2026-09-17

You store your own keys for external tools Julius should call; there is no documented way to supply your own inference credentials or cloud.

Junie CLI takes your own OpenAI, Anthropic, Google, xAI, OpenRouter or GitHub Copilot credentials with no JetBrains subscription; in the IDE chat, Junie is JetBrains-AI-only.

Source retrieved 2026-09-02

Own provider keys at list price, shared org keys on Teams, or fully local inference.

Source retrieved 2026-09-02

dcode is bring-your-own-key; the LLM Gateway accepts your provider keys on every plan, and Enterprise adds bring-your-own-cloud.

Source retrieved 2026-09-02

You paste your own provider keys into the Model Providers pane, and the OpenAI-compatible provider points at any endpoint you host yourself.

Source retrieved 2026-09-03

You supply provider keys directly in your own code, and the LLM Gateway's bring-your-own-key row is checked on every plan. Enterprise adds hybrid and self-hosted so inference and data stay in your cloud.

Source retrieved 2026-09-02

You bring your own model and tokens when driving over MCP, and only three tools touch billing. There is no way to supply your own provider key for the in-app agent, which runs on the included AI budget.

Source retrieved 2026-09-02

You can bring your own telephony carrier instead of switching phone systems, but nothing documents bringing your own model API keys, inference endpoint or cloud account.

Source retrieved 2026-09-09

Every plan supports your own provider keys or coding subscriptions, and usage then bypasses Letta credits.

Source retrieved 2026-09-02

You can store your own tool API keys as workspace credentials; no bring-your-own inference key or cloud is offered

Provider plugins run on your own account, key and billing, and self-hosted agents run in your own cloud. Bringing your own key to traffic routed through LiveKit Inference is not supported.

Source retrieved 2026-09-02

Self-hosted deployments call providers with your own keys; on the v1 hosted API 'Use your own API key' bills 1 credit per page.

Source retrieved 2026-09-02

Bringing a private or fine-tuned model is offered, but it sits in the custom-enterprise add-on table with no published rate, so the entry plans cannot buy it off the page.

Source retrieved 2026-09-09

BYOK is an explicit Gateway access mode on every plan; keys are stored encrypted and used only to route your requests. Self-hosting your own inference endpoint is also supported.

Source retrieved 2026-09-02

You bring the inference: your provider account and credentials (Azure identity, provider API key) or a local runtime such as Ollama, Foundry Local or ONNX. Microsoft supplies no inference with the SDK.

Source retrieved 2026-09-02

Provider API keys are optional, not required: every plan can connect its own keys instead of the Service Router, and Business can additionally deploy custom or self-hosted models.

Source retrieved 2026-09-02

You cannot bring your own inference for the reasoning engine, but a plugin can call an external LLM API with your own credentials held in a connector.

Source retrieved 2026-09-02

Your own provider credentials are the default and can be mixed per node with n8n Gateway credits (Cloud Starter and Pro only); on self-hosted the AI Assistant is BYOK, so no credit ceiling applies.

Source retrieved 2026-09-02

You bring your own telephony and messaging accounts, importing numbers from Twilio, RingCentral, Vonage or Exotel and WhatsApp via your own Meta credentials, but the agent model config offers only the vendor's own catalogue, with no field for your own LLM key or cloud.

Source retrieved 2026-09-09

You supply your own API key and can point the client at any base URL or custom OpenAI-compatible endpoint; inference runs on your provider account.

Source retrieved 2026-09-02

Your keys, your subscriptions or your own hardware: provider credentials are yours, and local servers such as Ollama, vLLM and llama.cpp keep inference on your machine.

Source retrieved 2026-09-02

Any provider works from your own API keys, and Zen additionally accepts your own OpenAI or Anthropic keys billed by the provider.

Source retrieved 2026-09-02

Your own LLM keys work on every tier; Enterprise additionally runs on your own compute in your own VPC.

Source retrieved 2026-09-02

Your own LLM endpoint with your own key or bearer token, your own Twilio numbers and your own S3 bucket for recordings; the runtime itself stays PolyAI-hosted.

Source retrieved 2026-09-02

Provider keys are yours by default - the library reads them from your environment - and the Gateway keeps BYOK as a first-class path alongside its own billed providers.

Source retrieved 2026-09-02

Bring your own LLM API keys to bypass Vendor Credits, but only on paid plans

Source retrieved 2026-09-02

Custom LLM mode gives you response generation on your own server and model; custom telephony over SIP carries no Retell telephony charge, and integration credentials are your own keys.

Source retrieved 2026-09-02

You can bring your own telephony by importing a Twilio number at no Ringly markup, which is also the only route to non-US numbers. There is no bring-your-own model key, inference endpoint or cloud.

Source retrieved 2026-09-09

Enterprise customers supply their own enrichment-provider API keys and 'BYOK Encryption' is an Enterprise-only row in the plan comparison; self-serve accounts can add keys for HG Insights only, and inference keys are never the buyer's.

Source retrieved 2026-09-03

Provider usage and support sit outside the fee and the subscriptions stay with the client, so inference is effectively on the buyer's own accounts; the vendor never says buyers supply their own keys.

Source retrieved 2026-09-04

Own inference via BYOLLM from four providers with your own credentials, but requests still route through Salesforce's Models API; own encryption keys require the Salesforce Shield add-on, and the agent runtime always stays on Salesforce.

Source retrieved 2026-09-03

You bring your own MCP client and its model subscription, and may supply your own Anthropic API key for the vendor's AI features; no own-cloud deployment.

Source retrieved 2026-09-03

Bring-your-own provider keys pay the provider at base rates with no markup; hosted keys carry a 1.1x multiplier.

Source retrieved 2026-09-03

You bring your own LLM and its keys, but the STT and TTS providers are sipgate-side selections, and there is no bring-your-own-cloud option.

Source retrieved 2026-09-03

You may bring your own enrichment provider key (Lusha, Wiza, Apollo, FullEnrich or Lemlist), but not your own model keys, inference endpoint or cloud.

Source retrieved 2026-09-15

Organisations can attach their own provider API keys, make them the workspace default, and switch off StackAI-supplied keys so all inference bills to their own accounts.

Source retrieved 2026-09-09

Your own OpenAI or Azure OpenAI key can power supported models, but the option is enabled per account; telephony can also be your own carrier or SIP trunk.

Source retrieved 2026-09-03

The browser extension is explicitly bring-your-own-key and never proxies calls through TecAdRise; for agency deployments the API and phone fees are billed on top but key ownership is not stated.

Source retrieved 2026-09-12

You may bring your own carrier by routing calls over third-party SIP and you choose the cloud region your data sits in, but nothing offers your own OpenAI, STT or TTS keys, so inference runs on TelEcho's provider accounts.

Source retrieved 2026-09-16

You may bring your own LLM and TTS providers, storing third-party keys as integration secrets; ElevenLabs voices are explicitly billed on your own key rather than by Telnyx.

Source retrieved 2026-09-09

Bring-your-own-subscription and bring-your-own-model are both documented and the Agents row says custom models are supported, but the two pages disagree on who gets it: the pricing table shows bring your own model only in the Enterprise column.

Source retrieved 2026-09-03

Provider keys for transcriber, LLM, voice and storage; with your key the model cost drops out of the Vapi bill entirely.

Source retrieved 2026-09-03

Connect your own provider key to switch providers, or run entirely locally against your own Anthropic key or an Ollama instance.

Source retrieved 2026-09-03

Three levels: your own provider key stored on your device, your own OpenAI-compatible endpoint, and Enterprise BYOLLM through your AWS or Google Cloud account. Device-local keys do not reach cloud agents, and orgs over ten employees need Business or Enterprise.

Source retrieved 2026-09-03

You save your own third-party API keys and the agent calls them mid-run; inference keys are not a thing here because the models are not selectable.

Source retrieved 2026-09-03

Bring your own provider keys on any plan, including the free one; keys are stored in the system keychain and spend goes to your provider.

Source retrieved 2026-09-03

Your own OpenAI or Anthropic key works on every plan and those calls consume no credits, and custom providers go further with local, VPC or third-party endpoints.

Source retrieved 2026-09-09

No bring-your-own-LLM-key or own-cloud inference. BYOK exists only as encryption-key control in a paid privacy add-on.

Source retrieved 2026-09-03

Bring your own everything: provider API keys, existing Claude/ChatGPT/Kimi/Copilot subscriptions, keys fetched from a password manager, or your own AWS, Azure, Vertex or local endpoint.

Source retrieved 2026-09-03