Production Reliability at a price that works for you

Production Reliability at a price that works for you

Production Reliability at a price that works for you

Supported on All Plans:

Observability

Universal API & Key Management

Prompt Management

Routing

Developer

Free Forever

Free Forever

Perfect for prototyping and testing or evaluating enterprise POCs. Not suitable for production workloads.



Perfect for prototyping and testing or evaluating enterprise POCs. Not suitable for production workloads.





10k recorded logs per month

Exceeding this limit doesn’t affect your requests; only logs beyond the limit are not recorded

10k recorded logs per month

Exceeding this limit doesn’t affect your requests; only logs beyond the limit are not recorded

10k recorded logs per month

Exceeding this limit doesn’t affect your requests; only logs beyond the limit are not recorded

AI Gateway

Universal API, Fallbacks, Loadbalancing, Retries & more

AI Gateway

Universal API, Fallbacks, Loadbalancing, Retries & more

AI Gateway

Universal API, Fallbacks, Loadbalancing, Retries & more

Observability

Logs, Traces, Feedback, Custom Metadata, Filters

Observability

Logs, Traces, Feedback, Custom Metadata, Filters

Observability

Logs, Traces, Feedback, Custom Metadata, Filters

Prompt Management

3 Prompt Templates, Playground, API Endpoints, Versioning, Variables

Prompt Management

3 Prompt Templates, Playground, API Endpoints, Versioning, Variables

Prompt Management

3 Prompt Templates, Playground, API Endpoints, Versioning, Variables

Simple Caching

Simple Caching

Simple Caching

Deterministic Guardrails

Deterministic Guardrails

Deterministic Guardrails

Community Support

Community Support

Community Support

POPULAR

Production

$49/month

$49/month

Great for teams ready to deploy LLM apps in production. Not recommended for organizations requiring custom security controls or data residency guarantees


Great for teams ready to deploy LLM apps in production. Not recommended for organizations requiring custom security controls or data residency guarantees


100k recorded logs per month

+$9 overages per additional 100k requests

100k recorded logs per month

+$9 overages per additional 100k requests

100k recorded logs per month

+$9 overages per additional 100k requests

AI Gateway

Universal API, Fallbacks, Load Balancing, Retries & more

AI Gateway

Universal API, Fallbacks, Load Balancing, Retries & more

AI Gateway

Universal API, Fallbacks, Load Balancing, Retries & more

Observability

Logs, Traces, Feedback, Metadata, Filters, Alerts

Observability

Logs, Traces, Feedback, Metadata, Filters, Alerts

Observability

Logs, Traces, Feedback, Metadata, Filters, Alerts

Guardrails

LLM & Partner Guardrails

Guardrails

LLM & Partner Guardrails

Guardrails

LLM & Partner Guardrails

Prompt Management

Unlimited Templates, Playground, API Endpoints, Versioning, Variables

Prompt Management

Unlimited Templates, Playground, API Endpoints, Versioning, Variables

Prompt Management

Unlimited Templates, Playground, API Endpoints, Versioning, Variables

Security

Role-Based Access Control, Service Account API Keys

Security

Role-Based Access Control, Service Account API Keys

Security

Role-Based Access Control, Service Account API Keys

Production Support

Production Support

Production Support

Simple & Semantic Caching

Simple & Semantic Caching

Simple & Semantic Caching

Enterprise

Custom Pricing

Custom Pricing

Built for organizations with complex compliance needs and high-volume production workloads. Get full Portkey feature set with enterprise support and multiple deployment configurations

Built for organizations with complex compliance needs and high-volume production workloads. Get full Portkey feature set with enterprise support and multiple deployment configurations

Recorded Logs

10 Mn Plus Recorded logs per month

Recorded Logs

10 Mn Plus Recorded logs per month

Recorded Logs

10 Mn Plus Recorded logs per month

Custom Retention Periods

Custom retention periods for Logs & Metrics

Custom Retention Periods

Custom retention periods for Logs & Metrics

Custom Retention Periods

Custom retention periods for Logs & Metrics

Guardrails

Custom Guardrail Hooks, Advanced Evaluation Templates

Guardrails

Custom Guardrail Hooks, Advanced Evaluation Templates

Guardrails

Custom Guardrail Hooks, Advanced Evaluation Templates

Governance

Role-Based Access Control, SSO, Granular Budget & Rate Limits

Governance

Role-Based Access Control, SSO, Granular Budget & Rate Limits

Governance

Role-Based Access Control, SSO, Granular Budget & Rate Limits

Enterprise Essentials

Private Cloud Deployment, Data Export to Data Lakes, VPC Hosting, Advanced Compliance (SOC2 Type 2, GDPR, HIPAA), Custom BAAs, Data Isolation

Enterprise Essentials

Private Cloud Deployment, Data Export to Data Lakes, VPC Hosting, Advanced Compliance (SOC2 Type 2, GDPR, HIPAA), Custom BAAs, Data Isolation

Enterprise Essentials

Private Cloud Deployment, Data Export to Data Lakes, VPC Hosting, Advanced Compliance (SOC2 Type 2, GDPR, HIPAA), Custom BAAs, Data Isolation

Support

Dedicated Onboarding & Priority Support

Support

Dedicated Onboarding & Priority Support

Support

Dedicated Onboarding & Priority Support

Also available in:

  • With 30 million policies a month, managing over 25 GenAI use cases became a pain. Portkey helped with prompt management, tracking costs per use case, and ensuring our keys were used correctly. It gave us the visibility we needed into our AI operations.

    Prateek Jogani

    CTO, Qoala

    Portkey is a no-brainer for anyone using AI in their GitHub workflows. It has saved us thousands of dollars by caching tests that don't require reruns, all while maintaining a robust testing and merge platform. This prevents merging PRs that could degrade production performance. Portkey is the best caching solution for our needs.

    Kiran Prasad

    Senior ML Engineer, Ario

    We are using Portkey in staging and production, and it works really well for us. With reporting and observability being so bad on OpenAI and Azure, Portkey helps get visibility into how and where we are using AI models as we start using it at scale within our company and products.

    Swapan R

    CTO, Haptik

    Swapan R picture

    Portkey stood out among AI Gateways we evaluated for several reasons: excellent, dedicated support even during the proof of concept phase, easy-to-use APIs that reduce time spent adapting code for different models, and detailed observability features that give deep insights into traces, errors, and caching

    AI Leader

    Fortune 500 Pharma Company

    A blurred background with blue, purple, and pink colors

Open Source

Open Source

Open Source

Host it Yourself

Universal API

Universal API

Universal API

Retries & Timeouts

Retries & Timeouts

Retries & Timeouts

Routing

Routing

Routing

Guardrails

Guardrails

Guardrails

Automatic Fallbacks

Automatic Fallbacks

Automatic Fallbacks

Basic Dashboard

Basic Dashboard

Basic Dashboard

Load Balancing

Load Balancing

Load Balancing

Community Support

Community Support

Community Support

Detailed Plan Comparision

Detailed Plan Comparision

Detailed Plan Comparision

Product Features

Open Source

Host it Yourself

Developer

Free Forever

Production

$49/month

POPULAR

Enterprise

Custom Pricing

Requests per Month

No Limit

10K

100K

Custom

Requests per Month

Requests per Month

Overage

No Overage Allowed

$9/Month for Every 100K Up to 3M Requests

Custom Pricing

Overage

Overage

AI Gateway

AI Gateway

AI Gateway

Universal API

Universal API

Universal API

Automatic Fallbacks

Automatic Fallbacks

Automatic Fallbacks

Loadbalancing

Loadbalancing

Loadbalancing

Automatic Retries

Automatic Retries

Automatic Retries

Request Timeouts

Request Timeouts

Request Timeouts

Config Management

Config Management

Config Management

Virtual Keys & Key Management

With Budgeting support

Virtual Keys & Key Management

Virtual Keys & Key Management

Simple Caching

1 Day TTL Support

Unlimited TTL Stream from Cache

Unlimited TTL Stream from Cache

Simple Caching

Simple Caching

Semantic Caching

Unlimited TTL Stream from Cache

Unlimited TTL Stream from Cache

Semantic Caching

Semantic Caching

Support for AWS, GCP, Azure Private LLM Deployments

Support for AWS, GCP, Azure Private LLM Deployments

Support for AWS, GCP, Azure Private LLM Deployments

Observability

Observability

Observability

Logs

Logs

Logs

Traces

Traces

Traces

Feedback

Feedback

Feedback

Custom Metadata

Custom Metadata

Custom Metadata

Filters

Filters

Filters

Alerts

Alerts

Alerts

Retention Period

3 Days

30 Days

Custom

Retention Period

Retention Period

Prompt Managements

Prompt Managements

Prompt Managements

Prompt Templates

Upto 3 Templates

Unlimited

Unlimited

Prompt Templates

Prompt Templates

Playground

Playground

Playground

API Deployment

API Deployment

API Deployment

Versioning

Versioning

Versioning

Variable Management

Variable Management

Variable Management

Guardrails

Guardrails

Guardrails

Eval Templates

Limited Access

Unlimited

Unlimited

Eval Templates

Eval Templates

Antonomous Fine-Tune

Antonomous Fine-Tune

Antonomous Fine-Tune

Continuous Improvement

Continuous Improvement

Continuous Improvement

Security & Compilance

Security & Compilance

Security & Compilance

Role Based Access Control

Advanced

Role Based Access Control

Role Based Access Control

Team Management

Advanced

Team Management

Team Management

SSO with Okta Auth

SSO with Okta Auth

SSO with Okta Auth

SOC2, ISO27001, GDPR, HIPAA Compliance Certificates

SOC2, ISO27001, GDPR, HIPAA Compliance Certificates

SOC2, ISO27001, GDPR, HIPAA Compliance Certificates

PII Anonymizer

PII Anonymizer

PII Anonymizer

BAA Signing for Compliances

BAA Signing for Compliances

BAA Signing for Compliances

VPC Managed Hosting

VPC Managed Hosting

VPC Managed Hosting

Private Tenancy

Private Tenancy

Private Tenancy

Configurable Retention Periods

Configurable Retention Periods

Configurable Retention Periods

Configurable exports to datalakes

Configurable exports to datalakes

Configurable exports to datalakes

Org Management

Org Management

Org Management

Enterprise-Grade Reliability,

backed by robust SLAs

Enterprise-Grade Reliability,

backed by robust SLAs

Enterprise-Grade Reliability, backed by robust SLAs

Security & Compliance

Enterprise-ready with industry-standard certifications and protocols.

Security & Compliance

Enterprise-ready with industry-standard certifications and protocols.

Security & Compliance

Enterprise-ready with industry-standard certifications and protocols.

Frequently Asked Questions

Some questions we get asked the most

What is Portkey?
What is Portkey?
What is Portkey?
What key features does Portkey offer?
What key features does Portkey offer?
What key features does Portkey offer?
How does Portkey work?
How does Portkey work?
How does Portkey work?
How many providers do you support?
How many providers do you support?
How many providers do you support?
How quickly do you support new LLM models/versions?
How quickly do you support new LLM models/versions?
How quickly do you support new LLM models/versions?
Do you support SSO and team management?
Do you support SSO and team management?
Do you support SSO and team management?
Can we set different limits for different teams/environments?
Can we set different limits for different teams/environments?
Can we set different limits for different teams/environments?
Can we prevent storage of sensitive data?
Can we prevent storage of sensitive data?
Can we prevent storage of sensitive data?
Is my data secure?
Is my data secure?
Is my data secure?
How are API keys managed?
How are API keys managed?
How are API keys managed?
Will Portkey add latency?
Will Portkey add latency?
Will Portkey add latency?
Does Portkey scale?
Does Portkey scale?
Does Portkey scale?
Does Portkey impose timeouts on requests?
Does Portkey impose timeouts on requests?
Does Portkey impose timeouts on requests?
Do you support SSO?
Do you support SSO?
Do you support SSO?
How can I get help?
How can I get help?
How can I get help?
What happens if I exceed my plan’s request limits?
What happens if I exceed my plan’s request limits?
What happens if I exceed my plan’s request limits?
Can we self-host Portkey?
Can we self-host Portkey?
Can we self-host Portkey?

Products

Solutions

Developers

Resources

...
...