Home

    Overview

    0

    Input and output tokens

    0

    Requests in the selected range

    0

    Before discounts, exemptions, and credits

    Credit balance

    0

    Current balance for this account

    Loading account overview

    Read our latest blog post

    November 16, 2026

    Zero Data Retention Is Not Zero Data Exposure

    A look at zero data retention across 12 AI providers and services: what the promise covers, where it stops, and why verifiable privacy requires more than a contract.

    Read post

    Resources

    Documentation

    Quickstarts, SDKs, and API reference.

    Pricing

    Compare model and infrastructure pricing.

    Tinfoil Chat

    Access the latest AI models without exposing your data.

    • Access to projects
    • Ability to search the web
    • Chat across web and iOS
    • Sync across devices

    Tinfoil Chat

    Access the latest AI models without exposing your data.

    • Access to projects
    • Ability to search the web
    • Chat across web and iOS
    • Sync across devices

    Tinfoil Inference

    Inference API access to powerful models, all running privately.

    • Access to all our models
    • OpenAI-compatible SDKs
    • Private web search API
    • Private document processing
    • Dashboard and usage metrics
    • Team organization

    Tinfoil Containers

    Run any containerized workload in a secure enclave.

    • CPU-only containers included
    • Dedicated vCPUs that are never preempted
    • Attestation and transparency infrastructure
    • Zero-downtime updates and relaunches
    • Health checks and monitoring
    • Debug mode environment
    • Email and Slack support

    Prices in USD.

    Prices in USD.

    Your instances

    All containers in your organization. Create new ones or manage running instances.

    Containers

    Container configs

    A config groups instances and secrets for a repository. The first instance or config secret creates the group automatically; setting up a configuration does not create an instance.

    Configs

    Status
    Latest deployment
    Status
    Latest deployment
    Status
    Latest deployment

    Volumes

    Storage owned by your organization. Volumes live on one host, attach only to containers on that host, and survive container deletion.

    Your volumes

    Create empty volumes and attach them to instances.

    Container secrets

    Store sensitive values like API keys and tokens. Secrets are injected into your containers at runtime as environment variables.

    Secrets

    Secrets are visible to Tinfoil's infrastructure.

    SSH keys

    Manage SSH keys for accessing your debug containers. Adding SSH keys allows you to deploy containers in debug mode and SSH into the container to get access to the Docker logs.

    SSH keys

    Custom domains

    Add and verify custom domains for your containers.

    Domains

    Registry authentication

    Configure credentials for private container registries to pull images during instance launch.

    GitHub Container Registry

    ghcr.io

    Google Container Registry

    gcr.io

    Docker Hub

    docker.io

    Prepare model weights

    Create a verified model-weight artifact from Hugging Face. This prepares the weights for a container config; the model is deployed from the All Instances tab.

    Recent wraps

    Finished jobs include copyable config snippets.

    Bunkers

    Tinfoil Bunkers are persistent, private cloud computers for your agents.

    Volumes

    Storage owned by your organization. Volumes live on one host, attach only to containers on that host, and survive container deletion.

    Your volumes

    Create empty volumes and attach them to instances.

    Config registry

    Publish and manage your organization's signed config versions under your namespace.

    Publish a config version

    Config path

    Config YAML

    Renew the endorsement automatically

    Config versions

    API keys

    Manage your inference API keys

    API keys

    NameStatusKeyCreatedExpiresLast usedCreated byLimitsActions

    Admin keys

    Admin keys provide programmatic access to your personal account, including access to billing and inference API keys. You do not need admin keys unless you're building advanced services with Tinfoil. Please read the documentation before getting started.

    Admin keys have elevated privileges and can perform high-privilege operations including creating new API access keys. Never store admin keys in client-side code, browser storage, or any user-accessible location.

    Admin API keys

    NameKeyCreatedExpiresCreated byActions

    Inference Rate Limits

    Your usage tier and the rate limits that apply to each model.

    Usage tier

    Higher tiers unlock higher API rate limits. Your account moves up automatically when the total of your paid invoices and credit purchases reaches each threshold.

    Need higher or custom limits? Contact us.

    Contact us

    Rate limits

    API usage is limited per model in requests per minute (RPM) and tokens per minute (TPM).

    Container Resource Limits

    How many containers you can run and how much storage you can allocate.

    Infrastructure tier

    Higher tiers allow more containers, bunkers, and storage. Organizations with GPU access are automatically Tier 3.

    Need higher or custom limits? Contact us.

    Contact us

    Usage

    What counts against your limits right now.

    Bunker Resource Limits

    How many bunkers you can run and the resources each one gets.

    Infrastructure tier

    Higher tiers allow more containers, bunkers, and storage. Organizations with GPU access are automatically Tier 3.

    Need higher or custom limits? Contact us.

    Contact us

    Usage

    What counts against your limits right now.

    Bunker resources

    Every bunker gets the same compute. You choose its workspace size when you create it.

    Usage

    API token and request volume over time. All chart dates are in UTC.

    Input tokens

    0

    Includes cache reads

    Output tokens

    0

    Generated tokens reported by the model

    Model requests

    0

    Excludes request-based services

    Token volume

    Cost

    Estimated API usage cost at current model prices, before account discounts, exemptions, and credits. All chart dates are in UTC.

    Estimated API cost

    0

    Includes token-based and per-request services

    Estimated cache savings

    0

    Already reflected in API cost; not an additional credit

    Requests

    0

    Recorded usage events in the selected range

    For the amount due after account adjustments, see Billing. For container costs, switch to Containers on this page.

    API cost over time

    Prompt caching

    See how much input is served from the prompt cache. Cache reads are included in total input tokens, not added to them.

    Uncached input tokens

    0

    Input tokens not served from cache

    Cache read tokens

    0

    Input tokens served from cache

    Cache read ratio

    0

    Cached input ÷ total input; not a request hit rate

    Estimated savings

    0

    Versus uncached input at current prices, before account discounts and exemptions

    Only models with discounted cached-input pricing are included. Cache-miss reasons and cache-write counts are not recorded. Savings may be unavailable for models without pricing data.

    Input token caching

    Logs

    Request metadata for the current account. All dates are in UTC.

    Usage

    Container runtime over time.

    Running containers over time

    Number of containers running over time.

    Usage

    Bunker runtime over time. All chart dates are in UTC.

    Running bunkers over time

    Average number of running bunkers in each interval.

    Overview

    Review your current-period spending and usage.

    API spend this period

    0

    Accumulated API usage for the current billing period. This will appear on your next invoice.

    Loading billing

    Prompt caching

    0

    0

    Estimated savings · last 7 days

    For models with discounted cached input, before account discounts and exemptions. Included in reported API cost.

    Token volume

    0

    Input and output tokens · last 7 days

    0View the Usage page for a breakdown by model.

    Usage tier

    0

    0

    Higher tiers raise your per-model requests and tokens per minute.

    Credits and limits

    Review your balance, usage limit, and credit history.

    Available Balance

    0

    Automatically applied to your next invoice.

    Loading billing

    Usage limit

    Set an optional cap on API usage for each billing period. Access pauses when recorded usage reaches the cap.

    This billing period

    Limit per billing period

    Leave empty or enter $0 for no limit. Usage resets each billing period.

    Notify at % of limit

    Send an email when usage crosses this threshold.

    How the limit behaves with concurrent or streaming requests

    Promo codes

    Redeem promotions and review discounts or credits for your account.

    Enter a promo code to receive a discount or usage credits.

    Subscriptions

    Review your subscriptions, billing periods, and payment methods.

    Transactions

    View your invoices, payments, and receipts.

    Audit log

    Recorded actions performed via admin API keys and the dashboard.

    Activity

    Infrastructure, configuration, billing, access, and key changes. Routine reads are shown separately.

    TimeActionActorAuthTargetResultIP

    OAuth apps

    Register apps that sign in Tinfoil users and call the inference API on their behalf.

    Registered apps

    Backoffice

    Members

    Leave organization

    You lose access to its resources until someone invites you again.

    Home

    Overview

    0

    Input and output tokens

    0

    Requests in the selected range

    0

    Before discounts, exemptions, and credits

    Credit balance

    0

    Current balance for this account

    Loading account overview

    Read our latest blog post

    November 16, 2026

    Zero Data Retention Is Not Zero Data Exposure

    A look at zero data retention across 12 AI providers and services: what the promise covers, where it stops, and why verifiable privacy requires more than a contract.

    Read post

    Resources

    Documentation

    Quickstarts, SDKs, and API reference.

    Pricing

    Compare model and infrastructure pricing.

    Tinfoil Chat

    Access the latest AI models without exposing your data.

    • Access to projects
    • Ability to search the web
    • Chat across web and iOS
    • Sync across devices

    Tinfoil Chat

    Access the latest AI models without exposing your data.

    • Access to projects
    • Ability to search the web
    • Chat across web and iOS
    • Sync across devices

    Tinfoil Inference

    Inference API access to powerful models, all running privately.

    • Access to all our models
    • OpenAI-compatible SDKs
    • Private web search API
    • Private document processing
    • Dashboard and usage metrics
    • Team organization

    Tinfoil Containers

    Run any containerized workload in a secure enclave.

    • CPU-only containers included
    • Dedicated vCPUs that are never preempted
    • Attestation and transparency infrastructure
    • Zero-downtime updates and relaunches
    • Health checks and monitoring
    • Debug mode environment
    • Email and Slack support

    Prices in USD.

    Prices in USD.

    Your instances

    All containers in your organization. Create new ones or manage running instances.

    Containers

    Container configs

    A config groups instances and secrets for a repository. The first instance or config secret creates the group automatically; setting up a configuration does not create an instance.

    Configs

    Status
    Latest deployment
    Status
    Latest deployment
    Status
    Latest deployment

    Volumes

    Storage owned by your organization. Volumes live on one host, attach only to containers on that host, and survive container deletion.

    Your volumes

    Create empty volumes and attach them to instances.

    Container secrets

    Store sensitive values like API keys and tokens. Secrets are injected into your containers at runtime as environment variables.

    Secrets

    Secrets are visible to Tinfoil's infrastructure.

    SSH keys

    Manage SSH keys for accessing your debug containers. Adding SSH keys allows you to deploy containers in debug mode and SSH into the container to get access to the Docker logs.

    SSH keys

    Custom domains

    Add and verify custom domains for your containers.

    Domains

    Registry authentication

    Configure credentials for private container registries to pull images during instance launch.

    GitHub Container Registry

    ghcr.io

    Google Container Registry

    gcr.io

    Docker Hub

    docker.io

    Prepare model weights

    Create a verified model-weight artifact from Hugging Face. This prepares the weights for a container config; the model is deployed from the All Instances tab.

    Recent wraps

    Finished jobs include copyable config snippets.

    Bunkers

    Tinfoil Bunkers are persistent, private cloud computers for your agents.

    Volumes

    Storage owned by your organization. Volumes live on one host, attach only to containers on that host, and survive container deletion.

    Your volumes

    Create empty volumes and attach them to instances.

    Config registry

    Publish and manage your organization's signed config versions under your namespace.

    Publish a config version

    Config path

    Config YAML

    Renew the endorsement automatically

    Config versions

    API keys

    Manage your inference API keys

    API keys

    NameStatusKeyCreatedExpiresLast usedCreated byLimitsActions

    Admin keys

    Admin keys provide programmatic access to your personal account, including access to billing and inference API keys. You do not need admin keys unless you're building advanced services with Tinfoil. Please read the documentation before getting started.

    Admin keys have elevated privileges and can perform high-privilege operations including creating new API access keys. Never store admin keys in client-side code, browser storage, or any user-accessible location.

    Admin API keys

    NameKeyCreatedExpiresCreated byActions

    Inference Rate Limits

    Your usage tier and the rate limits that apply to each model.

    Usage tier

    Higher tiers unlock higher API rate limits. Your account moves up automatically when the total of your paid invoices and credit purchases reaches each threshold.

    Need higher or custom limits? Contact us.

    Contact us

    Rate limits

    API usage is limited per model in requests per minute (RPM) and tokens per minute (TPM).

    Container Resource Limits

    How many containers you can run and how much storage you can allocate.

    Infrastructure tier

    Higher tiers allow more containers, bunkers, and storage. Organizations with GPU access are automatically Tier 3.

    Need higher or custom limits? Contact us.

    Contact us

    Usage

    What counts against your limits right now.

    Bunker Resource Limits

    How many bunkers you can run and the resources each one gets.

    Infrastructure tier

    Higher tiers allow more containers, bunkers, and storage. Organizations with GPU access are automatically Tier 3.

    Need higher or custom limits? Contact us.

    Contact us

    Usage

    What counts against your limits right now.

    Bunker resources

    Every bunker gets the same compute. You choose its workspace size when you create it.

    Usage

    API token and request volume over time. All chart dates are in UTC.

    Input tokens

    0

    Includes cache reads

    Output tokens

    0

    Generated tokens reported by the model

    Model requests

    0

    Excludes request-based services

    Token volume

    Cost

    Estimated API usage cost at current model prices, before account discounts, exemptions, and credits. All chart dates are in UTC.

    Estimated API cost

    0

    Includes token-based and per-request services

    Estimated cache savings

    0

    Already reflected in API cost; not an additional credit

    Requests

    0

    Recorded usage events in the selected range

    For the amount due after account adjustments, see Billing. For container costs, switch to Containers on this page.

    API cost over time

    Prompt caching

    See how much input is served from the prompt cache. Cache reads are included in total input tokens, not added to them.

    Uncached input tokens

    0

    Input tokens not served from cache

    Cache read tokens

    0

    Input tokens served from cache

    Cache read ratio

    0

    Cached input ÷ total input; not a request hit rate

    Estimated savings

    0

    Versus uncached input at current prices, before account discounts and exemptions

    Only models with discounted cached-input pricing are included. Cache-miss reasons and cache-write counts are not recorded. Savings may be unavailable for models without pricing data.

    Input token caching

    Logs

    Request metadata for the current account. All dates are in UTC.

    Usage

    Container runtime over time.

    Running containers over time

    Number of containers running over time.

    Usage

    Bunker runtime over time. All chart dates are in UTC.

    Running bunkers over time

    Average number of running bunkers in each interval.

    Overview

    Review your current-period spending and usage.

    API spend this period

    0

    Accumulated API usage for the current billing period. This will appear on your next invoice.

    Loading billing

    Prompt caching

    0

    0

    Estimated savings · last 7 days

    For models with discounted cached input, before account discounts and exemptions. Included in reported API cost.

    Token volume

    0

    Input and output tokens · last 7 days

    0View the Usage page for a breakdown by model.

    Usage tier

    0

    0

    Higher tiers raise your per-model requests and tokens per minute.

    Credits and limits

    Review your balance, usage limit, and credit history.

    Available Balance

    0

    Automatically applied to your next invoice.

    Loading billing

    Usage limit

    Set an optional cap on API usage for each billing period. Access pauses when recorded usage reaches the cap.

    This billing period

    Limit per billing period

    Leave empty or enter $0 for no limit. Usage resets each billing period.

    Notify at % of limit

    Send an email when usage crosses this threshold.

    How the limit behaves with concurrent or streaming requests

    Promo codes

    Redeem promotions and review discounts or credits for your account.

    Enter a promo code to receive a discount or usage credits.

    Subscriptions

    Review your subscriptions, billing periods, and payment methods.

    Transactions

    View your invoices, payments, and receipts.

    Audit log

    Recorded actions performed via admin API keys and the dashboard.

    Activity

    Infrastructure, configuration, billing, access, and key changes. Routine reads are shown separately.

    TimeActionActorAuthTargetResultIP

    OAuth apps

    Register apps that sign in Tinfoil users and call the inference API on their behalf.

    Registered apps

    Backoffice

    Members

    Leave organization

    You lose access to its resources until someone invites you again.