Agentic Index
Helicone vs Portkey (2026)
Helicone last verified ·Portkey last verified
Choose Helicone for an open source LLM observability gateway with self serve pricing. That verdict is the Agentic Index coverage score, graded from each vendor's own published materials.
Choose Portkey for a fuller production control plane spanning routing, guardrails, governance, and an MCP gateway. Helicone runs from $79 a month with a free tier of 10,000 requests a month plus an open source core, while Portkey offers a free Developer plan and Production at $49 a month with 100,000 recorded logs. Helicone is now in maintenance mode, which still brings security patches, support for new models and bug fixes.
On the Agentic Index agent infrastructure ranking, Portkey clears the bar and Helicone does not. Portkey documents all five production contract capabilities in full; Helicone does not document testing, debugging and optimization in full. 33 of the 186 vendors in the lane clear it. See the agent infrastructure ranking
This comparison is published by Agentic Index, an independent agentic AI vendor research platform. Helicone and Portkey are each graded against the same 14 capability Agentic Index taxonomy, from the vendor's own public materials under the Agentic Index verification standard, alongside 1,165 researched vendors. No vendor pays for placement and no vendor has reviewed this page. How this evidence is graded
Choose Helicone if
- You want logging, caching, and cost tracking through one endpoint with minimal ceremony
- Choosing where request logs live, EU or US cloud or your own infrastructure, is a requirement
- Your gateway needs are observability first rather than governance first
Choose Portkey if
- Guardrails, RBAC, and budget governance across teams are day one requirements
- An MCP gateway alongside LLM routing consolidates your agent traffic control
- Security platform integration under Palo Alto Networks is an asset for your buyers
| Feature | H Helicone |
P Portkey |
|---|---|---|
| Action & orchestration | ||
|
Integrations & Tool Calling Ability to connect agents to real systems through native integrations, OAuth-authenticated actions, custom tools, APIs, webhooks, or MCP-compatible tools. |
||
|
HeliconeIntegrations & Tool Calling Model providers connect through the gateway. Helicone also works with frameworks such as the Vercel AI SDK, LiteLLM, OpenRouter and CrewAI, sends webhooks out, and offers a Zapier app that runs chat completions through the gateway. These route model traffic and send events. None of them connects an agent to a real system to take actions. SourceHelicone, docs.helicone.ai/llms.txt (integrations, webhooks, Zapier, web search)read 2026-09-21 |
||
|
PortkeyIntegrations & Tool Calling Agents authenticate once to Portkey's MCP Gateway, which sits between them and MCP servers. For each tool call, the gateway checks that user's access to the server and tool, then injects the upstream credentials (OAuth, API keys or custom headers, with external identity providers such as Okta and Auth0). Servers and individual tools are provisioned per workspace and user. Through the gateway, agents take authenticated action in outside systems. Sourcedocs.portkey.ai/docs/product/mcp-gatewayread 2026-09-22 |
||
|
Workflow Orchestration Ability to sequence, branch, retry, route, and combine deterministic workflow nodes with autonomous agent steps. |
||
|
HeliconeWorkflow Orchestration Per request, the gateway routes and falls back between providers, and prompts are assembled from versioned templates at call time. There are no workflows that sequence, branch or retry agent steps, or that combine deterministic nodes with agent steps. SourceHelicone, docs.helicone.ai/llms.txt (provider routing, prompt assembly)read 2026-09-21 |
||
|
PortkeyWorkflow Orchestration The Agent Gateway is a proxy between agent clients and the customer's own agent servers. It handles authentication, access control and observability for registered A2A agents, and the agents and their steps run on the customer's servers. Portkey has no workflow definitions and runs no agents of its own, so nothing in it sequences or branches agent steps. Sourcedocs.portkey.ai/docs/product/agent-gatewayread 2026-09-22 |
||
|
Triggers & Channel Coverage How agents wake up and where they work: schedules, webhooks, message events, CRM events, inbox events, chat, email, voice, and collaboration tools. |
||
|
HeliconeTriggers & Channel Coverage Alerts fire when an application crosses error thresholds or cost limits. Automated weekly reports deliver usage, cost and performance summaries to email or Slack, and webhooks send request events to the customer's endpoints. SourceHelicone, docs.helicone.ai/llms.txt (alerts, reports, webhooks) and helicone.ai/pricingread 2026-09-21 |
||
|
PortkeyTriggers & Channel Coverage Work reaches agents through Portkey only when a client sends a request. Model, MCP and A2A calls are all made by the caller, and the Agent Gateway proxies them to the customer's agent servers. Portkey names no schedule, event, webhook or inbound queue that starts an agent run. The gateway waits for callers and does not wake an agent on its own. Sourcedocs.portkey.ai/docs/product/agent-gatewayread 2026-09-22 |
||
| Knowledge & context | ||
|
Knowledge Grounding & RAG Ability to ground agent behavior in company data through document ingestion, retrieval, external knowledge APIs, semantic search, or RAG layers. |
||
|
HeliconeKnowledge Grounding & RAG Model traffic is routed and logged, web search can be added to Anthropic models through the gateway, and datasets hold logged requests for evaluation and fine tuning. There is no document ingestion, index, retrieval layer or knowledge API that grounds an agent in company data. SourceHelicone, docs.helicone.ai/llms.txt (web search, datasets)read 2026-09-21 |
||
|
PortkeyKnowledge Grounding & RAG Embedding and file requests route through Portkey to providers, and responses are cached. Portkey maintains no retrieval structure over the customer's documents, and routing embedding calls builds none. Sourceportkey.ai/pricingread 2026-09-22 |
||
|
Memory & State Persistence Ability to persist context across a run, conversation, workflow, user, team, or longer-term memory layer. |
||
|
HeliconeMemory & State Persistence Logged requests, sessions and prompt versions persist, and the gateway can automatically clear old tool uses and thinking blocks from long running agent sessions. Agents get no session, workflow or long term memory to read and write. SourceHelicone, docs.helicone.ai/llms.txt (sessions, context editing)read 2026-09-21 |
||
|
PortkeyMemory & State Persistence Features cover routing, caching, observability, guardrails, prompt management and the MCP and agent gateways. None of them is a memory layer that keeps an agent's state or a user's context across sessions. The response cache holds model responses. Sourceportkey.ai/pricingread 2026-09-22 |
||
| Control & trust | ||
|
Human Oversight & Guardrails Approval steps, consent checkpoints, escalation rules, structured guardrails, policy constraints, and pause/resume controls. |
||
|
HeliconeHuman Oversight & Guardrails With LLM Security enabled, Helicone screens each user message with Meta's Prompt Guard, and optionally Llama Guard across 14 threat categories. It blocks detected threats with an error response before the request is processed. Moderation filters harmful content, and custom rate limits cap requests by count or cost. SourceHelicone, docs.helicone.ai/features/advanced-usage/llm-security and llms.txt (moderations, custom rate limits); docs.helicone.ai/features/advanced-usage/llm-security.mdread 2026-09-21 |
||
|
PortkeyHuman Oversight & Guardrails Inputs and outputs pass through Portkey Guardrails, which act on the verdict automatically by denying the request, flagging it and letting it through, retrying or falling back. The MCP Gateway applies content filters per server, per user tool provisioning and rate limits on tool calls. Org and workspace admins can enforce guardrails, budgets and rate limits, so the customer sets these limits on what an agent may do. Portkey describes no step where a person reviews, approves or must validate an agent action before it commits. Sourcedocs.portkey.ai/docs/product/guardrailsread 2026-09-22 |
||
|
Security, Identity & Governance RBAC, SSO, auditability, encryption, least-privilege tool access, compliance posture, and data handling policy. |
||
|
HeliconeSecurity, Identity & Governance SAML SSO comes on the Enterprise plan, with identity integration through the customer's own provider, and each plan sets its organizations and seats. SOC 2 Type II and HIPAA compliance come from the Team plan up, with InfoSec reviews and customized MSAs on Enterprise. Provider keys are encrypted, data sits in EU or US regions, and retention is configurable. Helicone names no roles or permissions inside an organization. SourceHelicone, helicone.ai/pricing and docs.helicone.ai/references/data-autonomyread 2026-10-01 |
||
|
PortkeySecurity, Identity & Governance Enterprise plans get SSO through OIDC. Portkey also has fine grained role based access control, encrypted storage of provider keys, TLS 1.2+ in transit and AES-256 at rest. It claims compliance with SOC 2, ISO 27001, GDPR and HIPAA, with regular third party audits and penetration tests, and its Trust Center is at trust.portkey.ai. Enterprise includes SOC 2 Type 2 and custom BAAs. SCIM works with Okta and Microsoft Entra, and Portkey supports audit logs, JWT authentication and API key rotation. Sourcedocs.portkey.ai/docs/product/enterprise-offering/security-portkeyread 2026-09-22 |
||
|
Observability & Auditability Traces, logs, execution histories, metrics, audit events, and debugging detail for production agent behavior. |
||
|
HeliconeObservability & Auditability Every request through the gateway or SDK is logged with prompt, completion, tokens, cost, latency and errors. Helicone groups them into sessions for agents and pipelines, adds user analytics and custom properties, and lets teams query analytics directly with HQL, a SQL interface with row level security. Data export is available. Retention runs 7 days on Hobby, 1 month on Pro, 3 months on Team and indefinitely on Enterprise, where it is also configurable. SourceHelicone, docs.helicone.ai/llms.txt (sessions, HQL, data export) and helicone.ai/pricingread 2026-09-21 |
||
|
PortkeyObservability & Auditability Every tool call through the MCP Gateway is logged with the user, parameters and response, and the log can be filtered by server, user or time range. Model requests carry logs, traces, feedback, custom metadata, filters and alerts on every plan, with retention set per plan. Enterprise adds audit logs, logs export and OpenTelemetry export. Sourcedocs.portkey.ai/docs/product/mcp-gatewayread 2026-09-22 |
||
|
Deployment & Data Residency Deployment modes and options, including SaaS, dedicated cloud, VPC, on-prem, hybrid, local runtime, and self-hosting. |
||
|
HeliconeDeployment & Data Residency Customers choose an EU or US region for data residency on Helicone Cloud. The open source platform self hosts with Docker or Kubernetes and Helm, and the Enterprise plan includes on premises deployment. SourceHelicone, docs.helicone.ai/references/data-autonomy and llms.txt (self-hosting, Docker, Kubernetes), and helicone.ai/pricing; docs.helicone.ai/references/data-autonomy.mdread 2026-09-21 |
||
|
PortkeyDeployment & Data Residency Enterprise offers private cloud deployment, VPC hosting and data isolation, and the open source gateway can be hosted by the customer. Hybrid deployments run on the customer's AWS (EKS, ECS, Marketplace), GCP and Azure (AKS, ACA), and air gapped deployment is available. A Gateway URLs setting points the dashboard at the customer's own self hosted AI and MCP gateways. Some of these options are Enterprise only. Sourceportkey.ai/pricingread 2026-09-22 |
||
| Solution readiness | ||
|
Prebuilt Agents, Templates & Packs Ready-made workflows, packaged employees, templates, blueprints, industry solutions, and role-specific agents that reduce time-to-value. |
||
|
HeliconePrebuilt Agents, Templates & Packs A model registry and pricing data cover the models the gateway reaches, and cookbooks explain how to build agents. There are no ready made agents, templates or packaged workflows a customer adopts. SourceHelicone, docs.helicone.ai/llms.txt (model registry, cookbooks)read 2026-09-21 |
||
|
PortkeyPrebuilt Agents, Templates & Packs No ready made agents, workflows, templates or role specific agents ship with Portkey. The Prompt Library holds the customer's own templates, and the Skills Registry shares skills the team writes. The prebuilt assets are guardrail checks and partner guardrail integrations, which constrain what agents do. Sourcedocs.portkey.ai/docs/product/guardrailsread 2026-09-22 |
||
| Platform extensibility | ||
|
Model Flexibility & Routing Ability to work across multiple foundation models, route tasks to different models, or let buyers bring their own providers and keys. |
||
|
HeliconeModel Flexibility & Routing The Helicone AI Gateway gives one OpenAI compatible API across more than 100 providers, with automatic provider routing, fallbacks, caching and custom rate limits by request count or cost. Provider keys are stored encrypted in a vault, so customers bring their own keys or use gateway credits. SourceHelicone, docs.helicone.ai/llms.txt (AI Gateway overview, provider routing, error handling and fallback, custom rate limits) and docs.helicone.ai/references/data-autonomyread 2026-09-21 |
||
|
PortkeyModel Flexibility & Routing Model choice sits with the customer. Portkey's Universal API puts many model providers behind one interface. Routing configs the customer writes set providers, model overrides, fallbacks, load balancing weights, retries, conditional routing and circuit breakers. Private model deployments on AWS, GCP and Azure are supported too. Sourceportkey.ai/pricingread 2026-09-22 |
||
|
APIs, SDKs & MCP Extensibility Composability layer: stable APIs, SDKs, MCP tool consumption/serving, custom tools, and integration into internal systems. |
||
|
HeliconeAPIs, SDKs & MCP Extensibility A REST API covers requests, sessions, scores, evaluations, prompts, webhooks and trace logging. Alongside it sit an OpenAI compatible gateway API, SDK integrations, webhooks, a Zapier app, and a Helicone MCP server that lets MCP compatible assistants query observability data. The codebase is open source. SourceHelicone, docs.helicone.ai/llms.txt (REST reference, MCP server, webhooks, Zapier)read 2026-09-21 |
||
|
PortkeyAPIs, SDKs & MCP Extensibility Developers get Portkey's own API and SDKs. The same feedback call works through the Node and Python SDKs and the REST API, and Portkey publishes an OpenAPI specification. Prompts are served through a Prompt API, and the Agent Gateway acts as a server to downstream agent clients for registered A2A agents. Sourcedocs.portkey.ai/docs/product/observability/feedbackread 2026-09-22 |
||
|
Testing, Debugging & Optimization Testing, debugging, scoring, retries, fallbacks, quality gates, and optimization loops for improving agent workflows before and after deployment. |
||
|
HeliconeTesting, Debugging & Optimization Scores and user feedback on requests and sessions come in through the API. Helicone curates request data into datasets for fine tuning and evaluation, provides a playground and versioned prompts deployed through the gateway, and tracks score distributions over time. Customers cannot run an application against fixtures or datasets before production, and there are no configurable quality gates. SourceHelicone, docs.helicone.ai/llms.txt (eval scores, datasets, prompts, evaluations API) and helicone.ai/pricingread 2026-09-21 |
||
|
PortkeyTesting, Debugging & Optimization Canary testing sends a set share of production traffic to a new model or prompt through a routing config, on every plan. Each request carries guardrail verdicts (pass or fail per check, counted in the log drawer) and weighted feedback scores sent through the Feedback API, which can be analyzed by metadata. Guardrails can deny, retry or fall back on a failed check. Together these let a team compare a change against current traffic. Sourcedocs.portkey.ai/docs/product/ai-gateway/canary-testingread 2026-09-22 |
||
| Specialist automation | ||
|
Browser & Computer Use Browser, desktop, or remote/local computer control for workflows that cannot be handled through stable APIs alone. |
||
|
HeliconeBrowser & Computer Use The product covers observability, the AI Gateway, prompts, datasets, security features and self hosting. No agent controls a browser, desktop or computer. SourceHelicone, docs.helicone.ai/llms.txtread 2026-09-21 |
||
|
PortkeyBrowser & Computer Use The gateway routes model calls, including provider computer use tools, whose actions the customer's own code carries out. Portkey describes no browser, desktop or remote computer session that it runs for an agent, and it wires in no headless fetch or third party browser engine. Sourceportkey.ai/pricingread 2026-09-22 |
||
Pricing snapshot
Sourced from the Index pricing dataset · open each vendor's profile for full detail.
| Pricing | H Helicone |
P Portkey |
|---|---|---|
|
Entry price Lowest public entry point |
From $79/mo · free tier (10k requests/mo) + open source | Free Developer plan · Production $49/mo · open source gateway free to self-host |
|
Pricing confidence How public the numbers are |
Public, exact | Public, exact |
|
Billing Primary billing axis |
Subscription tiers by features and seats, with usage based scaling above included request volume; AI Gateway billed as zero markup provider pass through | usage |
|
Variable cost Workload / overage exposure |
Medium variable cost | Medium variable cost |
|
Free tier / trial Try before you buy |
Free tierTrial
|
Free tier
|
|
Buying motion Self-serve vs sales call |
Mixed | Mixed |
|
Pricing verified When this pricing was last checked |
Product updates
Newest first, each linked to its source.
Mintlify acquired Helicone in March 2026. Palo Alto Networks bought Portkey in 2026 and sells it as Prisma AIRS AI Gateway beside Portkey's own plans.
More comparisons with Helicone or Portkey
Other matchups in agent infrastructure platforms
Not the pairing you were after? These compare a different set of agent infrastructure platforms on the same 14 capabilities.