> ## Documentation Index > Fetch the complete documentation index at: https://veryfront.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # List models > Returns available AI models and providers. A project-scoped credential, or a selector header naming a project the caller can see, narrows the list to what that project's inference policy permits. ## OpenAPI ````yaml /cloud/rest/openapi.json get /ai/models openapi: 3.1.0 info: title: Veryfront REST API reference version: 1.0.0 description: >- ## Explore the API | API | Use it to | | --- | --- | | [Agents API](#tag/agents-api) | Define agents, tasks and workflows, and configure their prompts, skills, tools and resources. | | [Execution API](#tag/execution-api) | Start and monitor agent, task, and workflow runs. | | [Evaluations API](#tag/evaluations-api) | Define agent evaluations, run them, and inspect results. | | [AI Gateway API](#tag/ai-gateway-api) | Generate messages, responses, embeddings, and images. | | [Knowledge API](#tag/knowledge-api) | Store document metadata, index file chunks, and search project content. | | [Integrations API](#tag/integrations-api) | Connect external accounts, invoke integration tools, and configure messaging channels. | | [Projects API](#tag/projects-api) | Create projects and manage source files, branches, and uploads. | | [Deployment API](#tag/deployment-api) | Create releases and deploy them to project environments. | | [Sandbox API](#tag/sandbox-api) | Create isolated sessions, run commands, and manage files. | | [Cache API](#tag/cache-api) | Read and write cached values in project or user scope. | | [Observability API](#tag/observability-api) | Query logs, metrics, traces, and alerts to investigate application behavior. | | [Identity and Access API](#tag/identity-and-access-api) | Authenticate callers and manage account and project access. | | [Billing and Usage API](#tag/billing-and-usage-api) | Manage subscriptions, payments, credits, budgets, and usage. | [API discovery and metadata](#tag/api-discovery-and-metadata) · [OpenAPI specification (JSON)](/openapi.json) contact: name: Veryfront API Support url: https://veryfront.com/docs email: support@veryfront.com x-api-id: 5f1f0b8a-6b0e-4c1a-9b35-0f3a1e6d84c7 x-audience: external-public servers: - url: https://api.veryfront.com security: - bearerAuth: [] - apiKeyAuth: [] tags: - name: Agents API description: >- Define agents, tasks and workflows, and configure their prompts, skills, tools and resources. | Endpoint group | Use it to | | --- | --- | | [Accessible agents](/cloud/rest/apis/agents-api#accessible-agents) | List agents you can access across projects. Each result includes the project needed to locate its definition. | | [Agent templates](/cloud/rest/apis/agents-api#agent-templates) | Browse agent templates. Use [agent installation](/cloud/rest/apis/agents-api#agent-installation) to add a selected template. | | [Project agents](/cloud/rest/apis/agents-api#project-agents) | Create and edit project agent definitions. Use [Runs](/cloud/rest/apis/execution-api#runs) to start and monitor agent runs. | | [Agent Capabilities](/cloud/rest/apis/agents-api#agent-capabilities) | Read project capabilities and the capabilities enabled for an agent. | | [Agent Tool References](/cloud/rest/apis/agents-api#agent-tool-references) | Search tools that can be attached to agents. | | [Agent Labels](/cloud/rest/apis/agents-api#agent-labels) | List, create, update, or delete labels on an agent. | | [Agent Avatars](/cloud/rest/apis/agents-api#agent-avatars) | Preview, generate, or read agent avatars. | | [Agent Installation](/cloud/rest/apis/agents-api#agent-installation) | Install or remove agents from selected projects. | | [Project prompts](/cloud/rest/apis/agents-api#project-prompts) | Manage prompts stored in project source. List prompts, read their source, and edit supported fields for the selected source version. | | [Project skills](/cloud/rest/apis/agents-api#project-skills) | Manage skills stored in project source. List skills, read their source, and edit the fields supported by the selected source and definition format. | | [Project tools](/cloud/rest/apis/agents-api#project-tools) | Manage tool definitions in project source. Use [integration tool endpoints](/cloud/rest/apis/integrations-api#integration-tools) to discover and invoke connected-service tools. | | [Project tasks](/cloud/rest/apis/agents-api#project-tasks) | Manage task definitions stored in project source. List definitions, read their source, and edit supported fields. To start a task run, use [`POST /runs`](/cloud/rest/api-reference/runs/create-run) with `kind: "task"` and the task’s execution target. | | [Project workflows](/cloud/rest/apis/agents-api#project-workflows) | Manage workflow definitions stored in project source. List definitions, read their source, and edit supported fields. To start a workflow run, use [`POST /runs`](/cloud/rest/api-reference/runs/create-run) with `kind: "workflow"` and the workflow’s execution target. | | [Project resources](/cloud/rest/apis/agents-api#project-resources) | Create and edit project resource documents. Manage servers and other deployment infrastructure through the [Deployment API](/cloud/rest/apis/deployment-api). | - name: Accessible agents description: >- List agents you can access across projects. Each result includes the project needed to locate its definition. - name: Agent templates description: >- Browse agent templates. Use [agent installation](/cloud/rest/apis/agents-api#agent-installation) to add a selected template. - name: Project agents description: >- Create and edit project agent definitions. Use [Runs](/cloud/rest/apis/execution-api#runs) to start and monitor agent runs. - name: Agent Capabilities description: Read project capabilities and the capabilities enabled for an agent. - name: Agent Tool References description: Search tools that can be attached to agents. - name: Agent Labels description: List, create, update, or delete labels on an agent. - name: Agent Avatars description: Preview, generate, or read agent avatars. - name: Agent Installation description: Install or remove agents from selected projects. - name: Project prompts description: >- Manage prompts stored in project source. List prompts, read their source, and edit supported fields for the selected source version. - name: Project skills description: >- Manage skills stored in project source. List skills, read their source, and edit the fields supported by the selected source and definition format. - name: Project tools description: >- Manage tool definitions in project source. Use [integration tool endpoints](/cloud/rest/apis/integrations-api#integration-tools) to discover and invoke connected-service tools. - name: Project tasks description: >- Manage task definitions stored in project source. List definitions, read their source, and edit supported fields. To start a task run, use [`POST /runs`](/cloud/rest/api-reference/runs/create-run) with `kind: "task"` and the task’s execution target. - name: Project workflows description: >- Manage workflow definitions stored in project source. List definitions, read their source, and edit supported fields. To start a workflow run, use [`POST /runs`](/cloud/rest/api-reference/runs/create-run) with `kind: "workflow"` and the workflow’s execution target. - name: Project resources description: >- Create and edit project resource documents. Manage servers and other deployment infrastructure through the [Deployment API](/cloud/rest/apis/deployment-api). - name: Execution API description: >- Start and monitor agent, task, and workflow runs. | Endpoint group | Use it to | | --- | --- | | [Runs](/cloud/rest/apis/execution-api#runs) | Start, list, inspect, cancel, and resume agent, task, and workflow runs, follow their events, answer their input requests, and find the runs that schedules, webhooks, and evaluations start. | | [Conversations](/cloud/rest/apis/execution-api#conversations) | Create, read, update, or delete conversations. Find runs and input requests under [Runs](/cloud/rest/apis/execution-api#runs). | | [Conversation Messages](/cloud/rest/apis/execution-api#conversation-messages) | List, send, read, edit, or delete messages. | | [Conversation Branches](/cloud/rest/apis/execution-api#conversation-branches) | Fork messages and select the active branch. | | [Conversation Participants](/cloud/rest/apis/execution-api#conversation-participants) | List, add, or remove participants. | | [Conversation Read State](/cloud/rest/apis/execution-api#conversation-read-state) | Read or update conversation read state. | | [Participant lookup](/cloud/rest/apis/execution-api#participant-lookup) | Find an existing participant identity by user or agent ID. Use the conversation participant endpoints to [add](/cloud/rest/api-reference/conversation-participants/add-participant) or [remove](/cloud/rest/api-reference/conversation-participants/remove-participant) users. | | [Project schedules](/cloud/rest/apis/execution-api#project-schedules) | Configure schedules. To start a run from an existing schedule, use [`POST /projects/{project_reference}/schedules/{schedule_id}/runs`](/cloud/rest/api-reference/runs/create-scheduled-run). | | [Project webhooks](/cloud/rest/apis/execution-api#project-webhooks) | Configure automation webhooks and replay recorded deliveries. Start a webhook run and list its runs under [Runs](/cloud/rest/apis/execution-api#runs). | - name: Runs description: >- Start, list, inspect, cancel, and resume agent, task, and workflow runs, follow their events, answer their input requests, and find the runs that schedules, webhooks, and evaluations start. | Operations | Use them to | | --- | --- | | Lifecycle | Create, list, get, cancel, pause, and resume runs, and read account run analytics. | | Events | Read, summarize, and stream run events, and list the event types. | | Input requests | Create, find, cancel, and respond to the input requests a run waits for. | | Children | List the child runs a run starts. | | Triggers | Start runs from schedules, webhooks, and evaluations, and list the runs they started. | - name: Conversations description: >- Create, read, update, or delete conversations. Find runs and input requests under [Runs](/cloud/rest/apis/execution-api#runs). - name: Conversation Messages description: List, send, read, edit, or delete messages. - name: Conversation Branches description: Fork messages and select the active branch. - name: Conversation Participants description: List, add, or remove participants. - name: Conversation Read State description: Read or update conversation read state. - name: Participant lookup description: >- Find an existing participant identity by user or agent ID. Use the conversation participant endpoints to [add](/cloud/rest/api-reference/conversation-participants/add-participant) or [remove](/cloud/rest/api-reference/conversation-participants/remove-participant) users. - name: Project schedules description: >- Configure schedules. To start a run from an existing schedule, use [`POST /projects/{project_reference}/schedules/{schedule_id}/runs`](/cloud/rest/api-reference/runs/create-scheduled-run). - name: Project webhooks description: >- Configure automation webhooks and replay recorded deliveries. Start a webhook run and list its runs under [Runs](/cloud/rest/apis/execution-api#runs). - name: Evaluations API description: >- Define agent evaluations, run them, and inspect results. | Endpoint group | Use it to | | --- | --- | | [Evaluation Definitions](/cloud/rest/apis/evaluations-api#evaluation-definitions) | List and create evaluation definitions stored in project source. Read the source document to inspect its dataset, metrics, and editable fields, then update supported fields. | - name: Evaluation Definitions description: >- List and create evaluation definitions stored in project source. Read the source document to inspect its dataset, metrics, and editable fields, then update supported fields. - name: AI Gateway API description: >- Generate messages, responses, embeddings, and images. | Endpoint group | Use it to | | --- | --- | | [Model discovery](/cloud/rest/apis/ai-gateway-api#model-discovery) | Find available models and inspect their metadata. Provider-compatible model lists are grouped with [inference models](/cloud/rest/apis/ai-gateway-api#inference-models). | | [Anthropic Messages](/cloud/rest/apis/ai-gateway-api#anthropic-messages) | Create Anthropic-compatible messages or count message tokens. | | [OpenAI Chat Completions](/cloud/rest/apis/ai-gateway-api#openai-chat-completions) | Create OpenAI-compatible chat completions. | | [OpenAI Responses](/cloud/rest/apis/ai-gateway-api#openai-responses) | Create OpenAI-compatible responses. | | [Embeddings](/cloud/rest/apis/ai-gateway-api#embeddings) | Create embeddings. | | [Inference Models](/cloud/rest/apis/ai-gateway-api#inference-models) | List provider-compatible inference models. | | [Gemini Models](/cloud/rest/apis/ai-gateway-api#gemini-models) | Call Gemini-compatible generateContent methods. | | [Image generation](/cloud/rest/apis/ai-gateway-api#image-generation) | Generate images from a prompt. Manage generated images through [project upload endpoints](/cloud/rest/apis/projects-api#project-uploads). | | [Provider gateway](/cloud/rest/apis/ai-gateway-api#provider-gateway) | Use [billing finalization](/cloud/rest/api-reference/provider-gateway/finalize-gateway-billing-group) when your integration manages gateway billing groups. Inspect spending limits through [budgets](/cloud/rest/apis/billing-and-usage-api#budgets). | | [Project inference policy](/cloud/rest/apis/ai-gateway-api#project-inference-policy) | Read, replace, or clear project inference constraints. These endpoints require a signed-in project administrator. Record standard-tier consent through [the opt-in endpoint](/cloud/rest/api-reference/project-inference-policy/opt-in-to-standard-tier-serving). | - name: Model discovery description: >- Find available models and inspect their metadata. Provider-compatible model lists are grouped with [inference models](/cloud/rest/apis/ai-gateway-api#inference-models). - name: Anthropic Messages description: Create Anthropic-compatible messages or count message tokens. - name: OpenAI Chat Completions description: Create OpenAI-compatible chat completions. - name: OpenAI Responses description: Create OpenAI-compatible responses. - name: Embeddings description: Create embeddings. - name: Inference Models description: List provider-compatible inference models. - name: Gemini Models description: Call Gemini-compatible generateContent methods. - name: Image generation description: >- Generate images from a prompt. Manage generated images through [project upload endpoints](/cloud/rest/apis/projects-api#project-uploads). - name: Provider gateway description: >- Use [billing finalization](/cloud/rest/api-reference/provider-gateway/finalize-gateway-billing-group) when your integration manages gateway billing groups. Inspect spending limits through [budgets](/cloud/rest/apis/billing-and-usage-api#budgets). - name: Project inference policy description: >- Read, replace, or clear project inference constraints. These endpoints require a signed-in project administrator. Record standard-tier consent through [the opt-in endpoint](/cloud/rest/api-reference/project-inference-policy/opt-in-to-standard-tier-serving). - name: Knowledge API description: >- Store document metadata, index file chunks, and search project content. | Endpoint group | Use it to | | --- | --- | | [Project documents](/cloud/rest/apis/knowledge-api#project-documents) | List, create, or update metadata records in the project’s retrieval-augmented generation (RAG) store. Use [project file endpoints](/cloud/rest/apis/projects-api#project-files) to edit source content. | | [File Chunks](/cloud/rest/apis/knowledge-api#file-chunks) | Read file chunks used for indexing. Create or delete chunks on a branch, or read chunks from a branch, environment, or release. | | [Project embeddings](/cloud/rest/apis/knowledge-api#project-embeddings) | Store and retrieve vectors by chunk ID. Generate vectors through [the embeddings endpoint](/cloud/rest/api-reference/embeddings/create-embeddings) or your provider before storing them here. | | [Vector search](/cloud/rest/apis/knowledge-api#vector-search) | Search indexed content with an embedding vector. Choose the branch, environment, or release endpoint for the content you need. | | [Project knowledge](/cloud/rest/apis/knowledge-api#project-knowledge) | Search metadata in project knowledge files. Specify a branch, environment, or release to query the required content version. | - name: Project documents description: >- List, create, or update metadata records in the project’s retrieval-augmented generation (RAG) store. Use [project file endpoints](/cloud/rest/apis/projects-api#project-files) to edit source content. - name: File Chunks description: >- Read file chunks used for indexing. Create or delete chunks on a branch, or read chunks from a branch, environment, or release. - name: Project embeddings description: >- Store and retrieve vectors by chunk ID. Generate vectors through [the embeddings endpoint](/cloud/rest/api-reference/embeddings/create-embeddings) or your provider before storing them here. - name: Vector search description: >- Search indexed content with an embedding vector. Choose the branch, environment, or release endpoint for the content you need. - name: Project knowledge description: >- Search metadata in project knowledge files. Specify a branch, environment, or release to query the required content version. - name: Integrations API description: >- Connect external accounts, invoke integration tools, and configure messaging channels. | Endpoint group | Use it to | | --- | --- | | [Integration catalog](/cloud/rest/apis/integrations-api#integration-catalog) | Browse integrations and read their metadata, icons, and connection summaries. Configure project-specific settings through the [project integration endpoints](/cloud/rest/apis/integrations-api#project-integrations). | | [Project integrations](/cloud/rest/apis/integrations-api#project-integrations) | Read or update an integration’s project configuration and connection state. Some integrations also expose service-specific metadata, such as Salesforce objects and fields. | | [Integration OAuth](/cloud/rest/apis/integrations-api#integration-oauth) | Authorize or disconnect an external account. Use [platform authentication](/cloud/rest/apis/identity-and-access-api#authentication) to sign in to Veryfront. Inspect connection status and retrieve tokens with the required permissions. | | [Connections](/cloud/rest/apis/integrations-api#connections) | List connected external accounts across projects you can access. | | [Integration tools](/cloud/rest/apis/integrations-api#integration-tools) | List tools exposed by connected services and invoke them with the required connection context. Manage source-defined tools through the [Agents API](/cloud/rest/apis/agents-api#project-tools). | | [Channel Bindings](/cloud/rest/apis/integrations-api#channel-bindings) | List, create, read, update, delete, or test channel bindings. | | [Channel Platforms](/cloud/rest/apis/integrations-api#channel-platforms) | Read, update, delete, or test platform channel configuration. | | [Channel Assistants](/cloud/rest/apis/integrations-api#channel-assistants) | List assistants that can receive channel messages. | | [Slack Channels](/cloud/rest/apis/integrations-api#slack-channels) | List Slack conversations available to a project channel integration. | | [Provider Files](/cloud/rest/apis/integrations-api#provider-files) | Browse, upload, move, import, or delete provider files. Use [project files](/cloud/rest/apis/projects-api#project-files) for files already stored in a project. | | [Provider Folders](/cloud/rest/apis/integrations-api#provider-folders) | Create folders through a connected storage provider. | | [Provider Search](/cloud/rest/apis/integrations-api#provider-search) | Search files through a connected storage provider. | - name: Integration catalog description: >- Browse integrations and read their metadata, icons, and connection summaries. Configure project-specific settings through the [project integration endpoints](/cloud/rest/apis/integrations-api#project-integrations). - name: Project integrations description: >- Read or update an integration’s project configuration and connection state. Some integrations also expose service-specific metadata, such as Salesforce objects and fields. - name: Integration OAuth description: >- Authorize or disconnect an external account. Use [platform authentication](/cloud/rest/apis/identity-and-access-api#authentication) to sign in to Veryfront. Inspect connection status and retrieve tokens with the required permissions. - name: Connections description: List connected external accounts across projects you can access. - name: Integration tools description: >- List tools exposed by connected services and invoke them with the required connection context. Manage source-defined tools through the [Agents API](/cloud/rest/apis/agents-api#project-tools). - name: Channel Bindings description: List, create, read, update, delete, or test channel bindings. - name: Channel Platforms description: Read, update, delete, or test platform channel configuration. - name: Channel Assistants description: List assistants that can receive channel messages. - name: Slack Channels description: List Slack conversations available to a project channel integration. - name: Provider Files description: >- Browse, upload, move, import, or delete provider files. Use [project files](/cloud/rest/apis/projects-api#project-files) for files already stored in a project. - name: Provider Folders description: Create folders through a connected storage provider. - name: Provider Search description: Search files through a connected storage provider. - name: Projects API description: >- Create projects and manage source files, branches, and uploads. | Endpoint group | Use it to | | --- | --- | | [Projects](/cloud/rest/apis/projects-api#projects) | List, create, read, update, or delete projects. | | [Project Labels](/cloud/rest/apis/projects-api#project-labels) | List, create, update, or delete project labels. | | [Account Projects](/cloud/rest/apis/projects-api#account-projects) | List or create projects assigned to an account. | | [Project Templates](/cloud/rest/apis/projects-api#project-templates) | List or search starter templates before creating a project. | | [Project Files](/cloud/rest/apis/projects-api#project-files) | List, read, write, move, delete, diff, or batch-read project files. | | [Project File Versions](/cloud/rest/apis/projects-api#project-file-versions) | List or read saved project file versions. | | [File search](/cloud/rest/apis/projects-api#file-search) | Search project or branch files by text. Use the [Knowledge API](/cloud/rest/apis/knowledge-api#vector-search) for vector search. | | [Branches](/cloud/rest/apis/projects-api#branches) | Create, read, delete, preview, check, or merge branches. | | [Branch Approvals](/cloud/rest/apis/projects-api#branch-approvals) | List, create, or dismiss branch approvals. | | [Branch Status Checks](/cloud/rest/apis/projects-api#branch-status-checks) | List or upsert branch status checks. | | [Branch Policies](/cloud/rest/apis/projects-api#branch-policies) | List, create, or delete branch policies. | | [Project Commits](/cloud/rest/apis/projects-api#project-commits) | Commit project file changes. | | [Branch Files](/cloud/rest/apis/projects-api#branch-files) | Read branch files and diffs. | | [Branch File Versions](/cloud/rest/apis/projects-api#branch-file-versions) | List or read saved branch file versions. | | [Branch File Drafts](/cloud/rest/apis/projects-api#branch-file-drafts) | Read, replace, or discard pending file drafts. | | [Environment Files](/cloud/rest/apis/projects-api#environment-files) | Read files and diffs from a named environment. Manage environment settings through [Environments](/cloud/rest/apis/deployment-api#environments). | | [Release Files](/cloud/rest/apis/projects-api#release-files) | Read files and diffs from a specific release. | | [Project Uploads](/cloud/rest/apis/projects-api#project-uploads) | List, upload, read, move, restore, delete, or get download URLs for uploads. | | [Upload Folders](/cloud/rest/apis/projects-api#upload-folders) | Create, rename, or delete upload folders. | | [Upload Grants](/cloud/rest/apis/projects-api#upload-grants) | List, set, or revoke upload grants. | | [Upload Visibility](/cloud/rest/apis/projects-api#upload-visibility) | Set or remove upload path visibility. | | [Dependencies](/cloud/rest/apis/projects-api#dependencies) | Resolve and pin project dependencies. Read recent dependency metadata to inspect the recorded configuration. | | [Style artifacts](/cloud/rest/apis/projects-api#style-artifacts) | Read or register the current CSS artifact and request its background build. Select the project and style profile in the request. | | [Favorites](/cloud/rest/apis/projects-api#favorites) | List, add, or remove favorite projects for the current user. Favorites do not grant project access. | - name: Projects description: List, create, read, update, or delete projects. - name: Project Labels description: List, create, update, or delete project labels. - name: Account Projects description: List or create projects assigned to an account. - name: Project Templates description: List or search starter templates before creating a project. - name: Project Files description: List, read, write, move, delete, diff, or batch-read project files. - name: Project File Versions description: List or read saved project file versions. - name: File search description: >- Search project or branch files by text. Use the [Knowledge API](/cloud/rest/apis/knowledge-api#vector-search) for vector search. - name: Branches description: Create, read, delete, preview, check, or merge branches. - name: Branch Approvals description: List, create, or dismiss branch approvals. - name: Branch Status Checks description: List or upsert branch status checks. - name: Branch Policies description: List, create, or delete branch policies. - name: Project Commits description: Commit project file changes. - name: Branch Files description: Read branch files and diffs. - name: Branch File Versions description: List or read saved branch file versions. - name: Branch File Drafts description: Read, replace, or discard pending file drafts. - name: Environment Files description: >- Read files and diffs from a named environment. Manage environment settings through [Environments](/cloud/rest/apis/deployment-api#environments). - name: Release Files description: Read files and diffs from a specific release. - name: Project Uploads description: >- List, upload, read, move, restore, delete, or get download URLs for uploads. - name: Upload Folders description: Create, rename, or delete upload folders. - name: Upload Grants description: List, set, or revoke upload grants. - name: Upload Visibility description: Set or remove upload path visibility. - name: Dependencies description: >- Resolve and pin project dependencies. Read recent dependency metadata to inspect the recorded configuration. - name: Style artifacts description: >- Read or register the current CSS artifact and request its background build. Select the project and style profile in the request. - name: Favorites description: >- List, add, or remove favorite projects for the current user. Favorites do not grant project access. - name: Deployment API description: >- Create releases and deploy them to project environments. | Endpoint group | Use it to | | --- | --- | | [Releases](/cloud/rest/apis/deployment-api#releases) | Create, read, delete, or find project releases. | | [Release Versions](/cloud/rest/apis/deployment-api#release-versions) | List the versions recorded for a release. | | [Release Source Manifests](/cloud/rest/apis/deployment-api#release-source-manifests) | Export the source manifest for a release. | | [Release Asset Manifests](/cloud/rest/apis/deployment-api#release-asset-manifests) | Read, write, build, or update release asset manifests. | | [Environments](/cloud/rest/apis/deployment-api#environments) | Create and manage deployment environments. Use the environment ID when configuring [deployments](/cloud/rest/apis/deployment-api#project-deployments), [domains](/cloud/rest/apis/deployment-api#environment-domains), [variables](/cloud/rest/apis/deployment-api#environment-variables), or [servers](/cloud/rest/apis/deployment-api#environment-servers). | | [Project deployments](/cloud/rest/apis/deployment-api#project-deployments) | Deploy a release to an environment. Read deployment records to inspect the resulting configuration. Investigate application behavior through [project logs](/cloud/rest/apis/observability-api#project-logs). | | [Project Domains](/cloud/rest/apis/deployment-api#project-domains) | List domains across a project. | | [Environment Domains](/cloud/rest/apis/deployment-api#environment-domains) | Create, read, update, or delete domains for an environment. | | [Environment Variable Keys](/cloud/rest/apis/deployment-api#environment-variable-keys) | List environment variable keys without values. | | [Environment variables](/cloud/rest/apis/deployment-api#environment-variables) | List, create, read, update, or delete environment variables. | | [Project servers](/cloud/rest/apis/deployment-api#project-servers) | List, read, or delete project server records. | | [Environment Servers](/cloud/rest/apis/deployment-api#environment-servers) | Create a server for an environment. | | [Proxy metadata](/cloud/rest/apis/deployment-api#proxy-metadata) | Read routing or access metadata for proxy requests. These endpoints have separate freshness and authorization requirements. | - name: Releases description: Create, read, delete, or find project releases. - name: Release Versions description: List the versions recorded for a release. - name: Release Source Manifests description: Export the source manifest for a release. - name: Release Asset Manifests description: Read, write, build, or update release asset manifests. - name: Environments description: >- Create and manage deployment environments. Use the environment ID when configuring [deployments](/cloud/rest/apis/deployment-api#project-deployments), [domains](/cloud/rest/apis/deployment-api#environment-domains), [variables](/cloud/rest/apis/deployment-api#environment-variables), or [servers](/cloud/rest/apis/deployment-api#environment-servers). - name: Project deployments description: >- Deploy a release to an environment. Read deployment records to inspect the resulting configuration. Investigate application behavior through [project logs](/cloud/rest/apis/observability-api#project-logs). - name: Project Domains description: List domains across a project. - name: Environment Domains description: Create, read, update, or delete domains for an environment. - name: Environment Variable Keys description: List environment variable keys without values. - name: Environment variables description: List, create, read, update, or delete environment variables. - name: Project servers description: List, read, or delete project server records. - name: Environment Servers description: Create a server for an environment. - name: Proxy metadata description: >- Read routing or access metadata for proxy requests. These endpoints have separate freshness and authorization requirements. - name: Sandbox API description: >- Create isolated sessions, run commands, and manage files. | Endpoint group | Use it to | | --- | --- | | [Sandbox Sessions](/cloud/rest/apis/sandbox-api#sandbox-sessions) | Create, read, update, or delete sandbox sessions. | | [Sandbox Commands](/cloud/rest/apis/sandbox-api#sandbox-commands) | Run commands and inspect command output. | | [Sandbox Files](/cloud/rest/apis/sandbox-api#sandbox-files) | List, read, or write sandbox files. | | [Sandbox Terminal](/cloud/rest/apis/sandbox-api#sandbox-terminal) | Open a sandbox terminal. | | [Sandbox Health](/cloud/rest/apis/sandbox-api#sandbox-health) | Check sandbox health, readiness, and heartbeat state. | - name: Sandbox Sessions description: Create, read, update, or delete sandbox sessions. - name: Sandbox Commands description: Run commands and inspect command output. - name: Sandbox Files description: List, read, or write sandbox files. - name: Sandbox Terminal description: Open a sandbox terminal. - name: Sandbox Health description: Check sandbox health, readiness, and heartbeat state. - name: Cache API description: >- Read and write cached values in project or user scope. | Endpoint group | Use it to | | --- | --- | | [Project Cache](/cloud/rest/apis/cache-api#project-cache) | Read and write individual values or batches. Inspect keys and statistics, delete matching keys, or clear the project cache. | | [User Cache](/cloud/rest/apis/cache-api#user-cache) | Read, write, or delete values in the authenticated user’s cache. | - name: Project Cache description: >- Read and write individual values or batches. Inspect keys and statistics, delete matching keys, or clear the project cache. - name: User Cache description: Read, write, or delete values in the authenticated user’s cache. - name: Observability API description: >- Query logs, metrics, traces, and alerts to investigate application behavior. | Endpoint group | Use it to | | --- | --- | | [Project logs](/cloud/rest/apis/observability-api#project-logs) | Query project logs to investigate activity and failures. Each endpoint reference lists the supported filters. | | [Project metrics](/cloud/rest/apis/observability-api#project-metrics) | Query project metrics to inspect measurements over time. | | [Project traces](/cloud/rest/apis/observability-api#project-traces) | Find project traces and inspect individual traces by ID. Trace spans connect related execution activity. For a run’s event history, use the [run endpoints](/cloud/rest/apis/execution-api#runs). | | [Project alerts](/cloud/rest/apis/observability-api#project-alerts) | List the alerts that fired for a project, firing and recently resolved, with links to the logs and traces they cover. | | [Account conversation analytics](/cloud/rest/apis/observability-api#account-conversation-analytics) | Read account-level conversation analytics. Find account run analytics under [Runs](/cloud/rest/apis/execution-api#runs). Use the [Billing and Usage API](/cloud/rest/apis/billing-and-usage-api) for consumption and spending data. | - name: Project logs description: >- Query project logs to investigate activity and failures. Each endpoint reference lists the supported filters. - name: Project metrics description: Query project metrics to inspect measurements over time. - name: Project traces description: >- Find project traces and inspect individual traces by ID. Trace spans connect related execution activity. For a run’s event history, use the [run endpoints](/cloud/rest/apis/execution-api#runs). - name: Project alerts description: >- List the alerts that fired for a project, firing and recently resolved, with links to the logs and traces they cover. - name: Account conversation analytics description: >- Read account-level conversation analytics. Find account run analytics under [Runs](/cloud/rest/apis/execution-api#runs). Use the [Billing and Usage API](/cloud/rest/apis/billing-and-usage-api) for consumption and spending data. - name: Identity and Access API description: >- Authenticate callers and manage account and project access. | Endpoint group | Use it to | | --- | --- | | [Authentication](/cloud/rest/apis/identity-and-access-api#authentication) | Sign in through an identity provider or magic link, create tokens, and end sessions. Retrieve public verification keys from [the JWKS endpoint](/cloud/rest/api-reference/authentication/get-jwks). | | [Current user](/cloud/rest/apis/identity-and-access-api#current-user) | Read the authenticated user’s profile. | | [Accounts](/cloud/rest/apis/identity-and-access-api#accounts) | List, create, or read accounts. | | [Account Collaboration](/cloud/rest/apis/identity-and-access-api#account-collaboration) | Read owner-wide collaboration entitlements and seat usage. The project reference selects its owner. | | [Account Members](/cloud/rest/apis/identity-and-access-api#account-members) | List, update, or remove account members. | | [Account Invitations](/cloud/rest/apis/identity-and-access-api#account-invitations) | List, create, revoke, or accept account invitations. | | [Account directory](/cloud/rest/apis/identity-and-access-api#account-directory) | List pending invitations and active members across projects you own. | | [Project Members](/cloud/rest/apis/identity-and-access-api#project-members) | List, read, remove, or update project members. | | [Project Invitations](/cloud/rest/apis/identity-and-access-api#project-invitations) | Create, read, delete, or resend project invitations. | | [Project Ownership](/cloud/rest/apis/identity-and-access-api#project-ownership) | Transfer project ownership. | | [API keys](/cloud/rest/apis/identity-and-access-api#api-keys) | Create, inspect, update, and revoke API keys. View [API key usage](/cloud/rest/apis/billing-and-usage-api#api-key-usage) in the Billing and Usage API. | | [OAuth Metadata](/cloud/rest/apis/identity-and-access-api#oauth-metadata) | Discover OAuth authorization and protected-resource metadata. | | [OAuth Clients](/cloud/rest/apis/identity-and-access-api#oauth-clients) | Register public OAuth clients. | | [OAuth Authorization Requests](/cloud/rest/apis/identity-and-access-api#oauth-authorization-requests) | Start, read, or decide MCP authorization requests. | | [OAuth Tokens](/cloud/rest/apis/identity-and-access-api#oauth-tokens) | Exchange, rotate, or revoke OAuth tokens. | | [OAuth Grants](/cloud/rest/apis/identity-and-access-api#oauth-grants) | List or revoke authorized MCP app grants. | - name: Authentication description: >- Sign in through an identity provider or magic link, create tokens, and end sessions. Retrieve public verification keys from [the JWKS endpoint](/cloud/rest/api-reference/authentication/get-jwks). - name: Current user description: Read the authenticated user’s profile. - name: Accounts description: List, create, or read accounts. - name: Account Collaboration description: >- Read owner-wide collaboration entitlements and seat usage. The project reference selects its owner. - name: Account Members description: List, update, or remove account members. - name: Account Invitations description: List, create, revoke, or accept account invitations. - name: Account directory description: List pending invitations and active members across projects you own. - name: Project Members description: List, read, remove, or update project members. - name: Project Invitations description: Create, read, delete, or resend project invitations. - name: Project Ownership description: Transfer project ownership. - name: API keys description: >- Create, inspect, update, and revoke API keys. View [API key usage](/cloud/rest/apis/billing-and-usage-api#api-key-usage) in the Billing and Usage API. - name: OAuth Metadata description: Discover OAuth authorization and protected-resource metadata. - name: OAuth Clients description: Register public OAuth clients. - name: OAuth Authorization Requests description: Start, read, or decide MCP authorization requests. - name: OAuth Tokens description: Exchange, rotate, or revoke OAuth tokens. - name: OAuth Grants description: List or revoke authorized MCP app grants. - name: Billing and Usage API description: >- Manage subscriptions, payments, credits, budgets, and usage. | Endpoint group | Use it to | | --- | --- | | [Subscriptions](/cloud/rest/apis/billing-and-usage-api#subscriptions) | Read, upgrade, or cancel the account subscription. Create [a checkout session](/cloud/rest/api-reference/subscriptions/create-checkout-session) or open [the billing portal](/cloud/rest/api-reference/subscriptions/get-billing-portal-url). | | [Billing Details](/cloud/rest/apis/billing-and-usage-api#billing-details) | Read or update account billing details. | | [Invoices](/cloud/rest/apis/billing-and-usage-api#invoices) | List invoices and upcoming invoices. | | [Payment Methods](/cloud/rest/apis/billing-and-usage-api#payment-methods) | List, attach, detach, or select payment methods. | | [Payments](/cloud/rest/apis/billing-and-usage-api#payments) | List account payments. | | [Credits](/cloud/rest/apis/billing-and-usage-api#credits) | Check the credit balance, review transactions, buy credits, or redeem a coupon. | | [Budgets](/cloud/rest/apis/billing-and-usage-api#budgets) | Set monthly AI spending caps by project, person, API key, or a combination of these fields. New budgets count spending already incurred that month; use [`PATCH /budgets/{budget_id}`](/cloud/rest/api-reference/budgets/update-budget) to change an existing cap. | | [Account usage](/cloud/rest/apis/billing-and-usage-api#account-usage) | Read account consumption, credit usage, limits, trends, and warnings. | | [Project usage](/cloud/rest/apis/billing-and-usage-api#project-usage) | Use [member usage](/cloud/rest/api-reference/project-usage/get-project-member-usage) for project AI spend by person and automation. The [project usage endpoint](/cloud/rest/api-reference/project-usage/get-project-usage) returns the project owner’s account-wide totals, not project-attributed usage. | | [API key usage](/cloud/rest/apis/billing-and-usage-api#api-key-usage) | List usage across API keys or inspect one key. Manage the keys themselves through [API key endpoints](/cloud/rest/apis/identity-and-access-api#api-keys). Manage [inference limits](/cloud/rest/api-reference/api-key-usage/get-api-key-inference-limits) for project-bound keys. | | [Feature gates](/cloud/rest/apis/billing-and-usage-api#feature-gates) | Check access to a named plan or feature gate. Individual endpoints still enforce their resource permissions. | - name: Subscriptions description: >- Read, upgrade, or cancel the account subscription. Create [a checkout session](/cloud/rest/api-reference/subscriptions/create-checkout-session) or open [the billing portal](/cloud/rest/api-reference/subscriptions/get-billing-portal-url). - name: Billing Details description: Read or update account billing details. - name: Invoices description: List invoices and upcoming invoices. - name: Payment Methods description: List, attach, detach, or select payment methods. - name: Payments description: List account payments. - name: Credits description: >- Check the credit balance, review transactions, buy credits, or redeem a coupon. - name: Budgets description: >- Set monthly AI spending caps by project, person, API key, or a combination of these fields. New budgets count spending already incurred that month; use [`PATCH /budgets/{budget_id}`](/cloud/rest/api-reference/budgets/update-budget) to change an existing cap. - name: Account usage description: Read account consumption, credit usage, limits, trends, and warnings. - name: Project usage description: >- Use [member usage](/cloud/rest/api-reference/project-usage/get-project-member-usage) for project AI spend by person and automation. The [project usage endpoint](/cloud/rest/api-reference/project-usage/get-project-usage) returns the project owner’s account-wide totals, not project-attributed usage. - name: API key usage description: >- List usage across API keys or inspect one key. Manage the keys themselves through [API key endpoints](/cloud/rest/apis/identity-and-access-api#api-keys). Manage [inference limits](/cloud/rest/api-reference/api-key-usage/get-api-key-inference-limits) for project-bound keys. - name: Feature gates description: >- Check access to a named plan or feature gate. Individual endpoints still enforce their resource permissions. - name: API discovery and metadata description: >- Discover tools, inspect schemas, and look up API error types. | Endpoint group | Use it to | | --- | --- | | [MCP discovery](/cloud/rest/apis/api-discovery-and-metadata#mcp-discovery) | List MCP tools and inspect their schemas before invoking them through the [MCP interface](https://veryfront.com/docs/cloud/rest/protocols#mcp). Use [the MCP playground](/cloud/rest/api-reference/mcp-discovery/open-mcp-playground) to explore tools. The older catalog alias is deprecated; use [the tool list](/cloud/rest/api-reference/mcp-discovery/list-public-mcp-tools) and [tool details](/cloud/rest/api-reference/mcp-discovery/get-public-mcp-tool-detail). | | [Error metadata](/cloud/rest/apis/api-discovery-and-metadata#error-metadata) | Read the meaning of a published error type. Use [logs](/cloud/rest/apis/observability-api#project-logs) or [traces](/cloud/rest/apis/observability-api#project-traces) to investigate a specific failed request. | - name: MCP discovery description: >- List MCP tools and inspect their schemas before invoking them through the [MCP interface](https://veryfront.com/docs/cloud/rest/protocols#mcp). Use [the MCP playground](/cloud/rest/api-reference/mcp-discovery/open-mcp-playground) to explore tools. The older catalog alias is deprecated; use [the tool list](/cloud/rest/api-reference/mcp-discovery/list-public-mcp-tools) and [tool details](/cloud/rest/api-reference/mcp-discovery/get-public-mcp-tool-detail). - name: Error metadata description: >- Read the meaning of a published error type. Use [logs](/cloud/rest/apis/observability-api#project-logs) or [traces](/cloud/rest/apis/observability-api#project-traces) to investigate a specific failed request. paths: /ai/models: get: tags: - Model discovery summary: List models description: >- Returns available AI models and providers. A project-scoped credential, or a selector header naming a project the caller can see, narrows the list to what that project's inference policy permits. operationId: listModels parameters: - schema: type: string minLength: 1 maxLength: 255 description: Project UUID or slug used to attribute billing finalization. required: false name: x-veryfront-project-reference in: header - schema: type: string minLength: 1 maxLength: 255 description: Project ID used to attribute billing finalization. required: false name: x-veryfront-project-id in: header - schema: type: string minLength: 1 maxLength: 255 description: Project slug used to attribute billing finalization. required: false name: x-veryfront-project-slug in: header responses: '200': description: Model catalog content: application/json: schema: type: object properties: models: type: array items: type: object properties: id: type: string description: Model identifier. example: claude-sonnet-4-6 modelId: type: string description: Unified model ID (provider/model). example: anthropic/claude-sonnet-4-6 provider: type: string description: Provider name. example: anthropic providerLabel: type: string description: Public provider display name. example: Anthropic providerLogoKey: type: string description: Public provider logo key. example: anthropic surface: type: string description: >- Gateway protocol for the model’s provider under `/ai/gateway/{provider}`. Known values are `openai`, `anthropic`, and `google`; clients must accept unknown values. Omitted if no gateway protocol is configured, in which case the gateway accepts no paths for the provider. example: anthropic operations: type: array items: type: string description: >- Operations of `surface` this model is served on, each at its canonical path (for Google, the `models/:` form). Known values: `chat-completions`, `responses`, `embeddings` on `openai`; `messages` on `anthropic`; `generate-content`, `stream-generate-content`, `embed-content`, `batch-embed-contents`, `predict`, `openai-responses`, `openai-chat-completions`, `openai-embeddings` on `google`. Not a closed enum, tolerate values you have not seen. Present exactly when `surface` is. example: - messages name: type: string description: Display name. example: Claude Sonnet description: type: string description: Short description. example: Most efficient for everyday tasks aliases: type: array items: type: string description: >- Accepted aliases for backward-compatible model selection. example: - sonnet - anthropic/claude-sonnet-4-6 capabilities: type: object properties: webResearch: type: boolean description: >- Whether Studio default chat can enable live web research. streaming: type: boolean description: Whether streaming responses are supported. tools: type: boolean description: Whether tool calls are supported. vision: type: boolean description: Whether image inputs are supported. thinking: type: boolean description: >- Whether thinking/reasoning controls are supported. supported_parameters: type: array items: type: string description: >- Supported request parameters, using OpenRouter names. Parameters not listed are removed or rejected. Parameters are listed only when support has been verified. example: - max_tokens - temperature - top_p - tools - tool_choice reasoning: type: boolean description: Whether the model reasons before answering. tool_call: type: boolean description: Whether the model can call tools. temperature: type: boolean description: >- Whether a caller-set temperature reaches the model. open_weights: type: boolean description: Whether the model weights are publicly released. attachment: type: boolean description: >- Whether file input is supported. Omitted if support has not been verified. structured_output: type: boolean description: >- Whether schema-constrained output is supported. Omitted if support has not been verified. modalities: type: object properties: input: type: array items: type: string description: Input modalities. example: - text - image required: - input description: >- Supported input modalities. Output modalities are omitted because they have not been verified. limit: type: object properties: context: type: integer exclusiveMinimum: 0 description: >- Context window in tokens: the provider's documented limit for the deployment Veryfront serves. Input plus requested output must fit within it. Absent while unevidenced. example: 1000000 output: type: integer exclusiveMinimum: 0 description: >- Maximum output tokens. Absent while unevidenced. example: 128000 description: >- Known token ceilings. Each is absent while unevidenced; `limit` is absent while neither is known. reasoning_mode: type: string description: >- Supported reasoning control. Known values are `budget` and `adaptive`. Omitted if the model does not reason or support has not been verified. Clients must accept unknown values. example: budget transport: type: string description: >- OpenAI wire API the client must use. Known values: `chat-completions`, `responses`. Absent when unconstrained. Not a closed enum. example: chat-completions reasoning_budget_tokens: type: integer exclusiveMinimum: 0 description: >- Default thinking budget in tokens when the caller does not specify one. Omitted if no default is configured or the model does not accept a budget, including models without reasoning and models with adaptive thinking. example: 2048 chat_completions_reasoning_with_function_tools: type: boolean description: >- Whether `chat-completions` supports reasoning and function tools in the same request. If false, choose one. Omitted if support has not been verified. example: false chat_completions_consecutive_system_messages: type: boolean description: >- Whether `chat-completions` accepts consecutive system messages. If true, clients can send system instructions separately. Omitted if support has not been verified. example: true required: - webResearch - streaming - tools - vision - supported_parameters - reasoning - tool_call - temperature - open_weights - modalities description: >- Model capability flags. The camelCase keys are the original Veryfront flags; the snake_case keys are the de facto names clients already parse (OpenRouter, models.dev) and are derived from the capability records. temperature: type: - object - 'null' properties: min: type: number minimum: 0 description: Minimum supported temperature. max: type: number minimum: 0 description: Maximum supported temperature. required: - min - max description: >- Per-model temperature limits; null when the runtime fixes or omits temperature. supportedProviderTools: type: array items: type: string description: >- Provider-executed agent tools supported on the deployment a request for this model is served from. example: - web_search - web_fetch pricing: type: object properties: inputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Input-token price, USD per 1M tokens. Use `inputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md outputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Output-token price, USD per 1M tokens. Use `outputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md cacheCreationInputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Default-retention cache-write input-token price, USD per 1M tokens. Use `cacheCreationInputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md cacheCreation1hInputUsdPer1M: type: number minimum: 0 description: >- Deprecated. One-hour cache-write input-token price, USD per 1M tokens. Use `cacheCreation1hInputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md cacheReadInputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Cache-read input-token price, USD per 1M tokens. Use `cacheReadInputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md audioInputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Audio input-token price, USD per 1M tokens. Use `audioInputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md audioOutputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Audio output-token price, USD per 1M tokens. Use `audioOutputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md audioCacheReadInputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Audio cache-read token price, USD per 1M tokens. Use `audioCacheReadInputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md inputEurPer1M: type: number minimum: 0 description: Input-token price. EUR per 1M tokens; see `fx`. outputEurPer1M: type: number minimum: 0 description: Output-token price. EUR per 1M tokens; see `fx`. cacheCreationInputEurPer1M: type: number minimum: 0 description: >- Default-retention cache-write input-token price, when the provider bills it separately. EUR per 1M tokens; see `fx`. cacheCreation1hInputEurPer1M: type: number minimum: 0 description: >- One-hour cache-write input-token price, when the provider bills it apart from the default cache write. EUR per 1M tokens; see `fx`. cacheReadInputEurPer1M: type: number minimum: 0 description: >- Cache-read input-token price, when the provider bills it separately. EUR per 1M tokens; see `fx`. audioInputEurPer1M: type: number minimum: 0 description: >- Audio input-token price, when the provider bills it separately. EUR per 1M tokens; see `fx`. audioOutputEurPer1M: type: number minimum: 0 description: >- Audio output-token price, when the provider bills it separately. EUR per 1M tokens; see `fx`. audioCacheReadInputEurPer1M: type: number minimum: 0 description: >- Audio cache-read token price, when the provider bills it separately. EUR per 1M tokens; see `fx`. required: - inputUsdPer1M - outputUsdPer1M - inputEurPer1M - outputEurPer1M description: >- Public Veryfront customer pricing after markup, used for client-side customer cost estimates. providerPricing: type: object properties: inputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Input-token price, USD per 1M tokens. Use `inputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md outputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Output-token price, USD per 1M tokens. Use `outputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md cacheCreationInputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Default-retention cache-write input-token price, USD per 1M tokens. Use `cacheCreationInputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md cacheCreation1hInputUsdPer1M: type: number minimum: 0 description: >- Deprecated. One-hour cache-write input-token price, USD per 1M tokens. Use `cacheCreation1hInputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md cacheReadInputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Cache-read input-token price, USD per 1M tokens. Use `cacheReadInputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md audioInputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Audio input-token price, USD per 1M tokens. Use `audioInputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md audioOutputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Audio output-token price, USD per 1M tokens. Use `audioOutputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md audioCacheReadInputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Audio cache-read token price, USD per 1M tokens. Use `audioCacheReadInputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md inputEurPer1M: type: number minimum: 0 description: Input-token price. EUR per 1M tokens; see `fx`. outputEurPer1M: type: number minimum: 0 description: Output-token price. EUR per 1M tokens; see `fx`. cacheCreationInputEurPer1M: type: number minimum: 0 description: >- Default-retention cache-write input-token price, when the provider bills it separately. EUR per 1M tokens; see `fx`. cacheCreation1hInputEurPer1M: type: number minimum: 0 description: >- One-hour cache-write input-token price, when the provider bills it apart from the default cache write. EUR per 1M tokens; see `fx`. cacheReadInputEurPer1M: type: number minimum: 0 description: >- Cache-read input-token price, when the provider bills it separately. EUR per 1M tokens; see `fx`. audioInputEurPer1M: type: number minimum: 0 description: >- Audio input-token price, when the provider bills it separately. EUR per 1M tokens; see `fx`. audioOutputEurPer1M: type: number minimum: 0 description: >- Audio output-token price, when the provider bills it separately. EUR per 1M tokens; see `fx`. audioCacheReadInputEurPer1M: type: number minimum: 0 description: >- Audio cache-read token price, when the provider bills it separately. EUR per 1M tokens; see `fx`. tiers: type: array items: type: object properties: inputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Input-token price, USD per 1M tokens. Use `inputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md outputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Output-token price, USD per 1M tokens. Use `outputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md cacheCreationInputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Default-retention cache-write input-token price, USD per 1M tokens. Use `cacheCreationInputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md cacheCreation1hInputUsdPer1M: type: number minimum: 0 description: >- Deprecated. One-hour cache-write input-token price, USD per 1M tokens. Use `cacheCreation1hInputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md cacheReadInputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Cache-read input-token price, USD per 1M tokens. Use `cacheReadInputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md audioInputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Audio input-token price, USD per 1M tokens. Use `audioInputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md audioOutputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Audio output-token price, USD per 1M tokens. Use `audioOutputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md audioCacheReadInputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Audio cache-read token price, USD per 1M tokens. Use `audioCacheReadInputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md inputEurPer1M: type: number minimum: 0 description: >- Input-token price. EUR per 1M tokens; see `fx`. outputEurPer1M: type: number minimum: 0 description: >- Output-token price. EUR per 1M tokens; see `fx`. cacheCreationInputEurPer1M: type: number minimum: 0 description: >- Default-retention cache-write input-token price, when the provider bills it separately. EUR per 1M tokens; see `fx`. cacheCreation1hInputEurPer1M: type: number minimum: 0 description: >- One-hour cache-write input-token price, when the provider bills it apart from the default cache write. EUR per 1M tokens; see `fx`. cacheReadInputEurPer1M: type: number minimum: 0 description: >- Cache-read input-token price, when the provider bills it separately. EUR per 1M tokens; see `fx`. audioInputEurPer1M: type: number minimum: 0 description: >- Audio input-token price, when the provider bills it separately. EUR per 1M tokens; see `fx`. audioOutputEurPer1M: type: number minimum: 0 description: >- Audio output-token price, when the provider bills it separately. EUR per 1M tokens; see `fx`. audioCacheReadInputEurPer1M: type: number minimum: 0 description: >- Audio cache-read token price, when the provider bills it separately. EUR per 1M tokens; see `fx`. id: type: string description: Stable provider pricing tier identifier example: long-context label: type: string description: Human-readable pricing tier label example: Long context appliesTo: type: string description: >- Condition where this provider pricing tier applies. example: Prompts over 200k tokens required: - inputUsdPer1M - outputUsdPer1M - inputEurPer1M - outputEurPer1M - id - label - appliesTo description: >- Raw provider pricing tier that is not the default catalog billing rate. description: >- Additional raw provider pricing tiers not currently represented by the default public price. required: - inputUsdPer1M - outputUsdPer1M - inputEurPer1M - outputEurPer1M description: >- What the provider charges Veryfront (our upstream cost), before markup. For a host that invoices in EUR the EUR prices are that host's published EUR list, unconverted and unrounded. pricingSources: type: object properties: directProvider: type: string format: uri description: Official provider pricing source URL. azure: type: string format: uri description: Official Azure-hosted model pricing source URL. required: - directProvider description: Official pricing source links for this model. deployments: type: array items: type: object properties: tier: type: string description: >- Residency tier of this deployment. Known values: `qualified-sovereign`, `eu-owned`, `eu-resident`, `standard`. example: eu-resident jurisdiction: type: string description: >- Legal domicile (ISO 3166-1 alpha-2) of the company operating the inference, or `unknown` where unevidenced. This is the operator's home country, NOT where inference is processed: an EU-resident deployment run by a US company reads `US`. Read `processing` for the location. example: US region: type: string description: >- Where inference is PROCESSED, not where the cloud resource was created. `eu` is an EU boundary (the EU Data Zone or an EU multi-region, depending on the host), `europe-west1` / `europe-west4` are single EU member-state regions, `global` means the route is worldwide and no region may be claimed, and `unknown` means unevidenced. example: europe-west1 processing: type: string description: >- Where inference is processed, normalised from `region` and `tier`. Known values: `eu` (inside a recorded EU boundary), `us` (in the United States), `worldwide` (in any region the operator runs), `unknown` (no processing region is recorded for this route). An open string: tolerate values you have not seen. example: eu processing_label: type: string description: >- The processing location in words, for display, e.g. `EU (EEA + Switzerland data zone)`, `EU (europe-west1, Belgium)`, `United States`, `Worldwide (any region)`, `Unknown (processing region not recorded)`. Display text only: branch on `processing`. example: EU (europe-west1, Belgium) operator: type: string description: >- Legal entity operating the inference service for this deployment, e.g. `Microsoft Corporation`, `Google LLC`, `OpenAI`, `Scaleway SAS`, or `unknown` where unrecorded. example: Google LLC quantization: type: string description: >- Weight precision served. Known values: `bf16`, `fp16`, `fp8`, `fp4`, `nvfp4`, `int4`, `unknown`. example: unknown precisionSource: type: string description: >- How `quantization` is evidenced. Known values: `contractual`, `published`, `reported`, `unknown`. example: unknown certifications: type: array items: type: string description: >- Certifications evidenced for this deployment. Empty when none is recorded. dataRetention: anyOf: - type: string - type: object properties: days: type: integer minimum: 0 required: - days description: >- Prompt retention on this deployment. Known values: `zero`, `metadata-only`, `unknown`, or `{ "days": N }`. example: unknown supportedProviderTools: type: array items: type: string description: >- Provider-executed agent tools this deployment supports. example: - web_search pricing: type: object properties: inputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Input-token price, USD per 1M tokens. Use `inputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md outputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Output-token price, USD per 1M tokens. Use `outputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md cacheCreationInputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Default-retention cache-write input-token price, USD per 1M tokens. Use `cacheCreationInputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md cacheCreation1hInputUsdPer1M: type: number minimum: 0 description: >- Deprecated. One-hour cache-write input-token price, USD per 1M tokens. Use `cacheCreation1hInputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md cacheReadInputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Cache-read input-token price, USD per 1M tokens. Use `cacheReadInputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md audioInputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Audio input-token price, USD per 1M tokens. Use `audioInputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md audioOutputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Audio output-token price, USD per 1M tokens. Use `audioOutputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md audioCacheReadInputUsdPer1M: type: number minimum: 0 description: >- Deprecated. Audio cache-read token price, USD per 1M tokens. Use `audioCacheReadInputEurPer1M`. deprecated: true x-deprecation: register_id: CR-model-catalog-usd-pricing deprecated_at: '2026-09-27' replacement: >- The EUR twin on the same object (`inputEurPer1M`, `cacheReadInputEurPer1M`, …; `input_eur_per_1m`, … on MCP). Converted from USD at the `fx` rate each response states, except provider cost on a host that invoices in EUR, which is the published EUR list of that host. rollout_state: announced old_semantics: >- Customer price (after markup) or provider cost (before markup) in USD per 1M tokens, as unrounded numbers. Each is present exactly when the model bills that dimension separately, and keeps that meaning while this entry is open. documentation: >- https://github.com/veryfront/veryfront-api/blob/main/docs/reference/api-surface-inventory.md inputEurPer1M: type: number minimum: 0 description: >- Input-token price. EUR per 1M tokens; see `fx`. outputEurPer1M: type: number minimum: 0 description: >- Output-token price. EUR per 1M tokens; see `fx`. cacheCreationInputEurPer1M: type: number minimum: 0 description: >- Default-retention cache-write input-token price, when the provider bills it separately. EUR per 1M tokens; see `fx`. cacheCreation1hInputEurPer1M: type: number minimum: 0 description: >- One-hour cache-write input-token price, when the provider bills it apart from the default cache write. EUR per 1M tokens; see `fx`. cacheReadInputEurPer1M: type: number minimum: 0 description: >- Cache-read input-token price, when the provider bills it separately. EUR per 1M tokens; see `fx`. audioInputEurPer1M: type: number minimum: 0 description: >- Audio input-token price, when the provider bills it separately. EUR per 1M tokens; see `fx`. audioOutputEurPer1M: type: number minimum: 0 description: >- Audio output-token price, when the provider bills it separately. EUR per 1M tokens; see `fx`. audioCacheReadInputEurPer1M: type: number minimum: 0 description: >- Audio cache-read token price, when the provider bills it separately. EUR per 1M tokens; see `fx`. required: - inputUsdPer1M - outputUsdPer1M - inputEurPer1M - outputEurPer1M description: >- Customer price for this deployment after markup. Excludes provider cost and the markup amount. required: - tier - jurisdiction - region - processing - processing_label - operator - quantization - precisionSource - certifications - dataRetention - supportedProviderTools - pricing description: >- A model deployment, including its location, terms, and pricing. description: >- Available deployments in routing preference order. Without a policy, requests use the first deployment. Only eligible hosts are listed. If a production deployment is eligible, only production deployments appear. Otherwise, an eligible rollout fallback appears with its own tier, region, and retention settings. required: - id - modelId - provider - providerLabel - providerLogoKey - name - aliases - capabilities - temperature - supportedProviderTools - pricing - providerPricing - pricingSources - deployments description: Available AI models. providers: type: array items: type: string description: Available provider names. defaultModelId: type: string description: Default unified model ID recommended by the API. example: mistral/mistral-small-2503 fx: type: object properties: base: type: string description: The currency one unit of which `rate` prices example: EUR quote: type: string description: The currency `rate` is expressed in example: USD rate: type: number exclusiveMinimum: 0 description: 1 `base` = `rate` `quote` example: 1.1403 source: type: string description: Where the rate is published example: ECB euro foreign exchange reference rate date: type: string description: The reference date of the rate (YYYY-MM-DD) example: '2026-09-25' required: - base - quote - rate - source - date description: >- 1 `base` = `rate` `quote`. EUR prices converted from USD are the USD price divided by `rate`, rounded to 6 decimal places. For a host that invoices in EUR the EUR prices are that host's published EUR list, unconverted and unrounded. web_tools: type: array items: type: object properties: tool: type: string description: >- The platform agent tool: `web_search` or `web_fetch`. example: web_search data_sent: type: string description: >- What the tool sends out. Known values: `query_and_search_options` (the search query, plus any domain filters and approximate user location the call states), `url_and_fetched_content` (the URL is requested and the page is returned into the run). An open string: tolerate values you have not seen. example: query_and_search_options recipient_class: type: string description: >- Who receives it. Known values: `third_party_search_provider` (the search backend of the selected deployment), `fetch_target` (the site the URL names). example: third_party_search_provider boundary_covered: type: boolean description: >- Whether this flow is covered by the accepted processing boundary. False unless a deployment carries evidence for it; never inferred from where inference runs. available: type: boolean description: >- Whether agent runs are offered the tool in this environment, under this project's policy. unavailable_reason: type: string description: >- Why the tool is not offered. Known values: `no_search_deployment`, `boundary_not_covered`, `policy_denied`. example: boundary_not_covered required: - tool - data_sent - recipient_class - boundary_covered - available description: >- What a platform web tool sends, to whom, and whether it is offered. description: >- The platform web tools' data flows. Facts about the tool, not about the model: inference residency says nothing about where a search query or fetched URL goes. required: - models - providers - defaultModelId - fx - web_tools '403': description: Forbidden content: application/problem+json: schema: $ref: '#/components/schemas/Problem' '503': description: This project's inference policy could not be read content: application/json: schema: $ref: '#/components/schemas/AiGatewayError' components: schemas: Problem: type: object properties: idempotency: type: object properties: state: type: string enum: - in_progress - payload_mismatch - outcome_unknown operation: type: string minLength: 1 retryable: type: boolean retry_after_seconds: type: - integer - 'null' minimum: 0 expires_at: type: - string - 'null' recovery: type: object properties: available: type: boolean description: type: string resource_url: type: string required: - available - description required: - state - operation - retryable - retry_after_seconds - expires_at description: Replay status, retry timing, and recovery lookup. type: type: string description: URI reference identifying the problem type example: https://api.veryfront.com/errors/validation-failed title: type: string description: Short human-readable summary of the problem example: Validation Failed status: type: integer minimum: 100 maximum: 599 description: HTTP status code example: 400 code: type: string description: Stable machine-readable error code example: RUN_INVALID_INPUT detail: type: string description: Human-readable explanation specific to this occurrence example: The 'email' field must be a valid email address instance: type: string description: URI reference identifying the specific occurrence example: /projects/my-project/members slug: type: string description: Stable identifier for the problem type example: validation-failed category: type: string enum: - AUTH - RESOURCE - VALIDATION - DATABASE - SUBSCRIPTION - INTEGRATION - INTERNAL description: API error category example: VALIDATION suggestion: type: string description: Suggested action to resolve the problem example: >- Check the request body and query parameters against the API documentation. errors: type: array items: type: object properties: field: type: string description: Field path that caused the error example: email message: type: string description: Error message for this field example: Invalid email format code: type: string description: Error code for this field example: INVALID_FORMAT required: - field - message description: Detailed field-level errors for validation failures required: - type - title - status AiGatewayError: type: object properties: error: type: string description: Error message. code: type: string description: Stable machine-readable error code. model: type: string maxLength: 256 description: Requested model ID, on model-specific refusals. successor: type: string description: The model that replaces a retired one, on `model_retired` refusals. retired_on: type: string description: >- UTC date (YYYY-MM-DD) the model was retired, on `model_retired` refusals. allowed_models: type: array items: type: string description: >- The models the calling API key may use, on `key-model-denied` refusals. required: - error securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: JWT or API Key description: >- Use a JWT bearer token or a Veryfront API key in the `Authorization` header. apiKeyAuth: type: apiKey in: header name: X-API-Key description: Alternative API key header for `vf__` tokens. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.