LLM provider
- OpenAPI 3.1.0 document: https://api.rollstack.com/public/v1/openapi.json
- The whole reference in Markdown: https://docs.rollstack.com/llms-full.txt
- An index of the reference: https://docs.rollstack.com/llms.txt
The organization's own LLM provider for the slides agent: its Anthropic, OpenAI, Azure AI Foundry, Amazon Bedrock or Google Vertex AI account, used instead of Rollstack's. Credentials are write-only: reads answer the provider's settings and status, never its keys.
Setting one up is part of the Enterprise plan. Saving tests every model on the new keys first, so a provider that cannot answer is never saved.
Get LLM provider
GET https://api.rollstack.com/public/v1/organization/llm-provider
The organization's custom LLM provider, without its credentials. Only owners, and members an owner allowed to manage the AI provider, may call it.
Requires the organization:read scope.
Operation ID: getLLMProvider.
Response 200
Success
application/json
id(string, required): Unique identifier for the organization's LLM provider. It stays the same when you replace the provider withsetLLMProvider; setting one up again afterdeleteLLMProvidergives a new one.type(string, required): The provider the organization's slides agent runs on, instead of Rollstack's own AI providers:anthropic(the Anthropic API),openai(the OpenAI API),azure_foundry(an Azure AI Foundry resource),amazon_bedrock(Amazon Bedrock in an AWS account) orgoogle_vertex_ai(Vertex AI in a Google Cloud project). Insights don't use it: they run on the organization'sllmProvider, fromgetOrganization. One ofanthropic,openai,azure_foundry,amazon_bedrock,google_vertex_ai.auth(string, required): How Rollstack signs in to the provider. WithapiKey, it uses a secret saved with the provider: an API key or, on Google Vertex AI, a service account key. Withoidc, the setup is keyless: your provider trusts short-lived tokens from Rollstack's OpenID Connect issuer for your organization, so no secret is saved. One ofapiKey,oidc.hasCredentials(true, required): Whether the provider has saved credentials: alwaystrue. Its secrets,apiKeyorprivateKey, are never returned, not even insettings: to change them, send the whole setup again withsetLLMProvider.settings(object, required): The provider's saved setup without its secrets: thecredentialsit was last saved with, as in thesetLLMProviderbody, minusapiKeyandprivateKey. It containsauthand, depending ontype:dataResidency(OpenAI);resourceNameandmodels(Azure AI Foundry);region,dataLocationandmodels(Amazon Bedrock); orprojectId,regionandmodels, plusclientEmailwith a service account key (Google Vertex AI). A keyless setup also contains its ids, such astenantIdandclientId, orroleArn.updatedAt(string (date-time), required): When the provider was last saved, withsetLLMProvideror in the app. Recording or clearing afailuredoesn't change it.updatedBy(object or null, required): The member who last saved the provider, withsetLLMProvideror in the app. Whenfailureis set, Rollstack notifies them, or the organization's owners if they're no longer an active member.nullif that user's account no longer exists.name(string or null, required): The name of the member who last saved the provider, as shown in Rollstack.email(string, required): The email address of the member who last saved the provider.
failure(string or null, required): Why the slides agent's calls to the provider are failing, when only a change on your provider's side can fix it.nullwhile calls work.key_invalid: the provider doesn't accept the API key or the keyless sign-in.forbidden: the key or sign-in isn't allowed to usefailedModel.model_not_found:failedModelisn't available to the account; on Azure AI Foundry, it isn't deployed under its own name, and on Amazon Bedrock or Google Vertex AI, it isn't enabled.out_of_credit: the provider account is out of credit. When it's set, Rollstack notifies the member inupdatedBy, or the owners if they're no longer an active member. It's cleared once a call tofailedModelworks again or the provider is saved again. One ofkey_invalid,forbidden,model_not_found,out_of_credit.failedAt(string (date-time) or null, required): When a slides agent call to the provider first failed with the currentfailure.nullwhile calls work.failedModel(string or null, required): The model whose call failed, such asclaude-haiku-5-5. Until the provider is saved again, only a working call to this model clearsfailure, so a failingfastmodel stays flagged even while thesmartone works.nullwhile calls work.
Replace LLM provider
PUT https://api.rollstack.com/public/v1/organization/llm-provider
Creates or replaces the organization's custom LLM provider, on the Enterprise plan only. Only owners, and admins an owner allowed to manage the AI provider, may call it: members' keys can't carry organization:write. The keys are saved only once one short call on each of their models works: otherwise nothing is saved and the call fails with a 400 (code ai-provider-test-failed); the AI provider setting in the app says which model failed and why. Calls are limited to 10 a minute for each organization. Every owner gets an email when the provider is set up, replaced or deleted. Web search uses OpenAI, so saving a provider that moves it to Rollstack's OpenAI account (any provider but OpenAI on its global host) turns web search off, unless the organization already had that kind of provider; an owner can turn it back on.
Requires the organization:write scope.
Operation ID: setLLMProvider.
Headers
Idempotency-Key(string): A unique value, such as a UUID, that makes retrying this call safe. A retry with the same key within 24 hours answers the first call's result instead of running it again. Use a new key for each new call. From 1 to 255 printable ASCII characters.
Request body, required
application/json
- When
typeisanthropictype(anthropic, required): Runs the slides agent on your own Anthropic organization, through the Anthropic API, with Claude Opus 5.5 (claude-opus-5-5) for its main work and Claude Haiku 5.5 (claude-haiku-5-5) for its quick steps. There are no models to pick or deploy.credentials(object, required): How Rollstack signs in to your Anthropic organization: with an API key (apiKey), or without a key, through Anthropic's workload identity federation (oidc).- When
authisapiKeyauth(apiKey, required): Rollstack signs in to the provider with a secret you send in this request: an API key or, on Google Vertex AI, a service account key (clientEmailandprivateKey). Rollstack saves the secret and never returns it, so to change it, send the whole setup again.apiKey(string, required): An Anthropic API key, created in the Claude Console under API keys, in a workspace for Rollstack where you can also set a spend limit. Rollstack never returns it. Example:your-anthropic-api-key.
- When
authisoidcauth(oidc, required): Rollstack signs in without a saved secret: its OpenID Connect issuer signs a short-lived token for the subjectrollstack:org:<id>, where<id>is your organization'sidfromgetOrganization, and your provider exchanges the token for temporary credentials. Set up your provider to trust that issuer and to check that subject, so it accepts only your organization:setLLMProviderfails if the setup also accepts another organization's token. The AI provider setting in the app, under Settings › Features, shows the issuer, subject and audience to trust.anthropicOrganizationId(string (uuid), required): The ID of your Anthropic organization, the one where you added Rollstack's issuer in the Claude Console under Settings › Workload identity federation. Example:7c9e1f3a-5b7d-4e9f-8a1c-3e5a7c9e1f3a.federationRuleId(string, required): The ID of the federation rule that lets Rollstack act asserviceAccountId. Create it in the Claude Console under Settings › Workload identity federation, once Rollstack's issuer is added there: set its subject to your organization's (seeauth), add a claim condition that the audience (aud) ishttps://api.anthropic.com, and enable it only inworkspaceId. Starts withfdrl_. Example:fdrl_01example.serviceAccountId(string, required): The ID of the service account Rollstack acts as in your Anthropic organization, created in the Claude Console in the workspace the slides agent should use (workspaceId). Starts withsvac_. Example:svac_01example.workspaceId(string, required): The ID of the Claude Console workspace the slides agent's calls run in: the workspace ofserviceAccountId, where the federation rule is enabled. Starts withwrkspc_. Example:wrkspc_01example.
- When
- When
typeisopenaitype(openai, required): Runs the slides agent on your own OpenAI project, through the OpenAI API, with GPT-6.1 Sol (gpt-6.1-sol) for its main work and GPT-6 Luna (gpt-6-luna) for its quick steps. There are no models to pick or deploy.credentials(object, required): Your OpenAI project's data residency, and how Rollstack signs in to the project: with an API key (apiKey), or without a key, through an OpenAI workload identity provider (oidc).- When
authisapiKeydataResidency(string, required): The data residency of the OpenAI project Rollstack uses, which decides the OpenAI host Rollstack calls:globalfor OpenAI's global host,usoreufor its US or EU host. Withglobal, the slides agent's web search also uses your OpenAI project. Withusoreu, it uses Rollstack's OpenAI account instead, so saving turns web search off, unless the organization's provider was already OpenAI withusoreu; an owner can turn it back on in the app. One ofglobal,us,eu.auth(apiKey, required): Rollstack signs in to the provider with a secret you send in this request: an API key or, on Google Vertex AI, a service account key (clientEmailandprivateKey). Rollstack saves the secret and never returns it, so to change it, send the whole setup again.apiKey(string, required): An API key for the OpenAI project Rollstack uses, created on the OpenAI platform. The project must allowgpt-6.1-solandgpt-6-luna, the models the slides agent runs on, in Project settings › Limits › Model usage. You can also give the project a monthly budget. Rollstack never returns the key. Example:your-openai-api-key.
- When
authisoidcdataResidency(string, required): The data residency of the OpenAI project Rollstack uses, which decides the OpenAI host Rollstack calls:globalfor OpenAI's global host,usoreufor its US or EU host. Withglobal, the slides agent's web search also uses your OpenAI project. Withusoreu, it uses Rollstack's OpenAI account instead, so saving turns web search off, unless the organization's provider was already OpenAI withusoreu; an owner can turn it back on in the app. One ofglobal,us,eu.auth(oidc, required): Rollstack signs in without a saved secret: its OpenID Connect issuer signs a short-lived token for the subjectrollstack:org:<id>, where<id>is your organization'sidfromgetOrganization, and your provider exchanges the token for temporary credentials. Set up your provider to trust that issuer and to check that subject, so it accepts only your organization:setLLMProviderfails if the setup also accepts another organization's token. The AI provider setting in the app, under Settings › Features, shows the issuer, subject and audience to trust.identityProviderId(string, required): The ID of the identity provider you create on the OpenAI platform, under Settings › Security › Workload Identity Provider, with Rollstack's issuer and the audiencehttps://api.openai.com. Map it to the service account inserviceAccountId, withsubset to your organization's subject (seeauth) andaudto that audience. Example:idp_example.serviceAccountId(string, required): The User ID of the OpenAI service account Rollstack acts as. Create the service account with Restricted permissions and Model capabilities set to Write, in a project with the data residency indataResidencythat allowsgpt-6.1-solandgpt-6-luna. Example:user-example.
- When
- When
typeisazure_foundrytype(azure_foundry, required): Runs the slides agent on Claude or GPT models deployed in your Azure AI Foundry resource, the ones you pick incredentials.models.credentials(object, required): Your Azure AI Foundry resource, the models on it the slides agent runs on, and how Rollstack signs in: with the resource's API key (apiKey), or without a key, as an app registered in Microsoft Entra ID (oidc).- When
authisapiKeyresourceName(string, required): The name of your Azure AI Foundry resource, which Rollstack calls athttps://<resourceName>.services.ai.azure.com. It's the first part of the host in any deployment's Target URI, such asacme-aiinhttps://acme-ai.services.ai.azure.com. 2 to 63 lowercase letters, digits and hyphens, starting with a letter or digit. Example:acme-ai.models(object, required): The models the slides agent runs on:smartfor its main work,fastfor its quick steps. Make them available first: on Azure AI Foundry, deploy each under its model's name (Foundry's default), such asclaude-opus-5-5; on Amazon Bedrock, enable them in Model access inregion.smart(string, required): The model that runs the slides agent and does its main work, such as editing slides and writing queries:claude-opus-5-5(Claude Opus 5.5) orgpt-6.1-sol(GPT-6.1 Sol). One ofclaude-opus-5-5,gpt-6.1-sol.fast(string): The model for the slides agent's quick steps around its main work, such as naming the chat and inspecting slides, to save cost:claude-haiku-5-5(Claude Haiku 5.5) orgpt-6-luna(GPT-6 Luna). It can be from a different family thansmart. If omitted, thesmartmodel runs these steps too. One ofclaude-haiku-5-5,gpt-6-luna.
auth(apiKey, required): Rollstack signs in to the provider with a secret you send in this request: an API key or, on Google Vertex AI, a service account key (clientEmailandprivateKey). Rollstack saves the secret and never returns it, so to change it, send the whole setup again.apiKey(string, required): An API key of your Azure AI Foundry resource. Rollstack uses it for every model it calls on the resource, Claude and GPT alike, and never returns it. Example:your-azure-api-key.
- When
authisoidcresourceName(string, required): The name of your Azure AI Foundry resource, which Rollstack calls athttps://<resourceName>.services.ai.azure.com. It's the first part of the host in any deployment's Target URI, such asacme-aiinhttps://acme-ai.services.ai.azure.com. 2 to 63 lowercase letters, digits and hyphens, starting with a letter or digit. Example:acme-ai.models(object, required): The models the slides agent runs on:smartfor its main work,fastfor its quick steps. Make them available first: on Azure AI Foundry, deploy each under its model's name (Foundry's default), such asclaude-opus-5-5; on Amazon Bedrock, enable them in Model access inregion.smart(string, required): The model that runs the slides agent and does its main work, such as editing slides and writing queries:claude-opus-5-5(Claude Opus 5.5) orgpt-6.1-sol(GPT-6.1 Sol). One ofclaude-opus-5-5,gpt-6.1-sol.fast(string): The model for the slides agent's quick steps around its main work, such as naming the chat and inspecting slides, to save cost:claude-haiku-5-5(Claude Haiku 5.5) orgpt-6-luna(GPT-6 Luna). It can be from a different family thansmart. If omitted, thesmartmodel runs these steps too. One ofclaude-haiku-5-5,gpt-6-luna.
auth(oidc, required): Rollstack signs in without a saved secret: its OpenID Connect issuer signs a short-lived token for the subjectrollstack:org:<id>, where<id>is your organization'sidfromgetOrganization, and your provider exchanges the token for temporary credentials. Set up your provider to trust that issuer and to check that subject, so it accepts only your organization:setLLMProviderfails if the setup also accepts another organization's token. The AI provider setting in the app, under Settings › Features, shows the issuer, subject and audience to trust.tenantId(string (uuid), required): The Directory (tenant) ID of your Microsoft Entra ID tenant, where you register the app Rollstack signs in as. Example:4d6f8a0c-2e3a-4b5c-8d7e-9f1a3b5c7d9e.clientId(string (uuid), required): The Application (client) ID of the app you register for Rollstack in Microsoft Entra ID, with no client secret. Give it a federated credential that trusts Rollstack's issuer for your organization's subject (seeauth), with the audienceapi://AzureADTokenExchange, and the Cognitive Services User role on the resource. A new trust can take a few minutes to apply. Example:2b4d6f8a-0c1e-4a3b-9d5f-7b9d1f3a5c7e.
- When
- When
typeisamazon_bedrocktype(amazon_bedrock, required): Runs the slides agent on Claude or GPT models in Amazon Bedrock, in your AWS account, the ones you pick incredentials.models.credentials(object, required): Where Rollstack calls Amazon Bedrock, the models the slides agent runs on, and how Rollstack signs in: with a Bedrock API key (apiKey), or without a key, by assuming an IAM role (oidc).- When
authisapiKeyregion(string, required): The AWS region Rollstack calls Amazon Bedrock in, such asus-east-1. It must be indataLocation: aus-region forus, aneu-region foreu,ap-southeast-2orap-southeast-4forau,ap-northeast-1orap-northeast-3forjp, and any region forglobal. Example:us-east-1.dataLocation(string, required): Where Amazon Bedrock may process the slides agent's requests to Claude models:us(United States),eu(Europe),au(Australia),jp(Japan) orglobal. Rollstack calls Claude through this location's cross-region inference profile, such asus.anthropic.claude-opus-5-5orglobal.anthropic.claude-opus-5-5, and GPT models inregiondirectly. One ofus,eu,au,jp,global.models(object, required): The models the slides agent runs on:smartfor its main work,fastfor its quick steps. Make them available first: on Azure AI Foundry, deploy each under its model's name (Foundry's default), such asclaude-opus-5-5; on Amazon Bedrock, enable them in Model access inregion.smart(string, required): The model that runs the slides agent and does its main work, such as editing slides and writing queries:claude-opus-5-5(Claude Opus 5.5) orgpt-6.1-sol(GPT-6.1 Sol). One ofclaude-opus-5-5,gpt-6.1-sol.fast(string): The model for the slides agent's quick steps around its main work, such as naming the chat and inspecting slides, to save cost:claude-haiku-5-5(Claude Haiku 5.5) orgpt-6-luna(GPT-6 Luna). It can be from a different family thansmart. If omitted, thesmartmodel runs these steps too. One ofclaude-haiku-5-5,gpt-6-luna.
auth(apiKey, required): Rollstack signs in to the provider with a secret you send in this request: an API key or, on Google Vertex AI, a service account key (clientEmailandprivateKey). Rollstack saves the secret and never returns it, so to change it, send the whole setup again.apiKey(string, required): A long-term Amazon Bedrock API key, created with an expiry for an IAM user whose policy allows only the models inmodels; the AI provider setting in the app shows that policy. Rollstack uses it for Claude and GPT models alike, and never returns it. Example:your-bedrock-api-key.
- When
authisoidcregion(string, required): The AWS region Rollstack calls Amazon Bedrock in, such asus-east-1. It must be indataLocation: aus-region forus, aneu-region foreu,ap-southeast-2orap-southeast-4forau,ap-northeast-1orap-northeast-3forjp, and any region forglobal. Example:us-east-1.dataLocation(string, required): Where Amazon Bedrock may process the slides agent's requests to Claude models:us(United States),eu(Europe),au(Australia),jp(Japan) orglobal. Rollstack calls Claude through this location's cross-region inference profile, such asus.anthropic.claude-opus-5-5orglobal.anthropic.claude-opus-5-5, and GPT models inregiondirectly. One ofus,eu,au,jp,global.models(object, required): The models the slides agent runs on:smartfor its main work,fastfor its quick steps. Make them available first: on Azure AI Foundry, deploy each under its model's name (Foundry's default), such asclaude-opus-5-5; on Amazon Bedrock, enable them in Model access inregion.smart(string, required): The model that runs the slides agent and does its main work, such as editing slides and writing queries:claude-opus-5-5(Claude Opus 5.5) orgpt-6.1-sol(GPT-6.1 Sol). One ofclaude-opus-5-5,gpt-6.1-sol.fast(string): The model for the slides agent's quick steps around its main work, such as naming the chat and inspecting slides, to save cost:claude-haiku-5-5(Claude Haiku 5.5) orgpt-6-luna(GPT-6 Luna). It can be from a different family thansmart. If omitted, thesmartmodel runs these steps too. One ofclaude-haiku-5-5,gpt-6-luna.
auth(oidc, required): Rollstack signs in without a saved secret: its OpenID Connect issuer signs a short-lived token for the subjectrollstack:org:<id>, where<id>is your organization'sidfromgetOrganization, and your provider exchanges the token for temporary credentials. Set up your provider to trust that issuer and to check that subject, so it accepts only your organization:setLLMProviderfails if the setup also accepts another organization's token. The AI provider setting in the app, under Settings › Features, shows the issuer, subject and audience to trust.roleArn(string, required): The ARN of the IAM role Rollstack assumes to call Amazon Bedrock. Its trust policy must trust Rollstack's issuer, added as an OIDC provider in your AWS account, for your organization's subject (seeauth) and the audiencests.amazonaws.com. Its permissions should allow only the models inmodels. The AI provider setting in the app gives the AWS CLI commands. Example:arn:aws:iam::123456789012:role/rollstack-agent.
- When
- When
typeisgoogle_vertex_aitype(google_vertex_ai, required): Runs the slides agent on Claude models in Vertex AI, in your Google Cloud project: Claude Opus 5.5 for its main work and, if you add it incredentials.models, Claude Haiku 5.5 for its quick steps.credentials(object, required): Your Google Cloud project and Vertex AI location, the models the slides agent runs on, and how Rollstack signs in: with a service account's JSON key (apiKey), or without a key, through workload identity federation (oidc).- When
authisapiKeyprojectId(string, required): The ID of the Google Cloud project Rollstack calls Vertex AI in, where you enable the models in Model Garden. Use the project ID, such asacme-ai, not its name or number. Example:acme-ai.region(string, required): Where Vertex AI processes the slides agent's requests:global(Vertex AI's global endpoint),us(the US multi-region) oreu(the EU multi-region). One ofglobal,us,eu.models(object, required): The Claude models the slides agent runs on:smartfor its main work,fastfor its quick steps. Enable them in Vertex AI's Model Garden forprojectId.smart(claude-opus-5-5, required): The model that runs the slides agent and does its main work, such as editing slides and writing queries. Alwaysclaude-opus-5-5(Claude Opus 5.5): on Google Vertex AI, the slides agent runs on Claude only.fast(claude-haiku-5-5): The model for the slides agent's quick steps around its main work, such as naming the chat and inspecting slides, to save cost:claude-haiku-5-5(Claude Haiku 5.5). If omitted,claude-opus-5-5runs these steps too.
auth(apiKey, required): Rollstack signs in to the provider with a secret you send in this request: an API key or, on Google Vertex AI, a service account key (clientEmailandprivateKey). Rollstack saves the secret and never returns it, so to change it, send the whole setup again.clientEmail(string (email), required): The email of the Google Cloud service account Rollstack signs in as:client_emailin its JSON key. The service account needs the Vertex AI User role. Example:rollstack@acme-ai.iam.gserviceaccount.com.privateKey(string, required): The service account's private key:private_keyin its JSON key. Rollstack keeps only this andclientEmailfrom the key, and never returns the private key. Example:your-private-key.
- When
authisoidcprojectId(string, required): The ID of the Google Cloud project Rollstack calls Vertex AI in, where you enable the models in Model Garden. Use the project ID, such asacme-ai, not its name or number. Example:acme-ai.region(string, required): Where Vertex AI processes the slides agent's requests:global(Vertex AI's global endpoint),us(the US multi-region) oreu(the EU multi-region). One ofglobal,us,eu.models(object, required): The Claude models the slides agent runs on:smartfor its main work,fastfor its quick steps. Enable them in Vertex AI's Model Garden forprojectId.smart(claude-opus-5-5, required): The model that runs the slides agent and does its main work, such as editing slides and writing queries. Alwaysclaude-opus-5-5(Claude Opus 5.5): on Google Vertex AI, the slides agent runs on Claude only.fast(claude-haiku-5-5): The model for the slides agent's quick steps around its main work, such as naming the chat and inspecting slides, to save cost:claude-haiku-5-5(Claude Haiku 5.5). If omitted,claude-opus-5-5runs these steps too.
auth(oidc, required): Rollstack signs in without a saved secret: its OpenID Connect issuer signs a short-lived token for the subjectrollstack:org:<id>, where<id>is your organization'sidfromgetOrganization, and your provider exchanges the token for temporary credentials. Set up your provider to trust that issuer and to check that subject, so it accepts only your organization:setLLMProviderfails if the setup also accepts another organization's token. The AI provider setting in the app, under Settings › Features, shows the issuer, subject and audience to trust.poolProjectNumber(string, required): The number of the Google Cloud project that contains the workload identity pool, asgcloud projects describeprints it. Digits only: the project number, not its ID. Example:123456789012.poolId(string, required): The ID of the workload identity pool that contains the provider inproviderId, such asrollstack. Example:rollstack.providerId(string, required): The ID of the OIDC provider in the pool that trusts Rollstack's issuer, such asrollstack. Mapgoogle.subjecttoassertion.sub, and keep Google's default audience, the provider's own resource name, which is the audience Rollstack's token carries. Grant the Vertex AI User role only to your organization's subject (seeauth) in the pool. Example:rollstack.
- When
Response 204
Success, no content
Delete LLM provider
DELETE https://api.rollstack.com/public/v1/organization/llm-provider
Deletes the organization's custom LLM provider, on any plan. Only owners, and admins an owner allowed to manage the AI provider, may call it: members' keys can't carry organization:write. Every owner gets an email.
Requires the organization:write scope.
Operation ID: deleteLLMProvider.
Headers
Idempotency-Key(string): A unique value, such as a UUID, that makes retrying this call safe. A retry with the same key within 24 hours answers the first call's result instead of running it again. Use a new key for each new call. From 1 to 255 printable ASCII characters.
Response 204
Success, no content