# LiteLLM vs Portkey vs Helicone for production traffic > Source: https://agentsindex.ai/blog/litellm-vs-portkey-vs-helicone-ai-gateway Comparison [Agent tools and integrations](https://agentsindex.ai/categories/agent-tools-and-integrations) LiteLLM, Portkey and Helicone AI Gateway compared on license terms, real cost at volume and maintenance, now that Palo Alto Networks owns Portkey. [Team AgentsIndex](https://agentsindex.ai/authors/agentsindex) Published 22 Sep 2026 Checked 13 Nov 2026 [How we check](https://agentsindex.ai/methodology) 7 min read [Editorial policy](https://agentsindex.ai/editorial-policy) ![LiteLLM vs Helicone.](https://agentsindex.ai/img/1024/heroes/litellm-vs-portkey-vs-helicone-ai-gateway/b618f192d1d5/list-16x9-800.webp) ## The short answer For most teams, [LiteLLM](https://agentsindex.ai/litellm) is the default: free, self-hosted, MIT-licensed at its core, and still the most active of the three by a wide margin. Reach for [Helicone](https://agentsindex.ai/helicone)’s AI Gateway instead if you want a purpose-built, low-latency Rust proxy and can live with GPL-3.0 on that specific component. Evaluate Portkey only with the understanding that you are no longer buying from an independent routing startup: you’re buying into Palo Alto Networks’ Prisma AIRS security platform, and the product, the pricing, and the roadmap now answer to that. That last point is the one thing in this comparison that changed the calculus, so it’s worth establishing before anything else. ## Portkey isn’t a startup anymore: it’s a Palo Alto Networks product line Palo Alto Networks announced its intent to acquire Portkey on 30 April 2026 and closed the deal on 29 May 2026, folding it into Prisma AIRS, its AI security platform, as “the control plane to monitor, orchestrate, and govern autonomous agents at scale.” ([Palo Alto Networks press release](https://www.paloaltonetworks.com/company/press/2026/palo-alto-networks-completes-acquisition-of-portkey-to-secure-ai-agents)) Portkey’s own marketing site confirms the rebrand isn’t cosmetic: the “Portkey vs LiteLLM” comparison page routes every “Talk to Us” and “Schedule a call” button to `paloaltonetworks.com/ai-security/ai-gateway`, tagged `utm_campaign=prisma_airs` ([portkey.ai/pricing](https://portkey.ai/pricing)). Portkey’s own pricing page now literally states “Portkey is now PRISMA AIRS AI Gateway.” The plans themselves are unchanged for now: Developer (free forever, 10k logged requests/month, 3-day log retention), Production ($49/month, 100k logged requests then $9 per additional 100k, 30-day retention), and Enterprise (custom, SOC 2 Type 2, HIPAA, private cloud). But the sales motion for anything beyond self-serve now leads to a cybersecurity vendor’s enterprise team, not a small routing company. If what you actually want is a lightweight open-source proxy you fully control, that’s a different vendor relationship than what Portkey is becoming. If what you want is agent governance backed by a company that also sells network security to the Fortune 500, Prisma AIRS is a legitimate answer to a question most indie gateways can’t address. It’s just not the same product category anymore. One nuance worth keeping straight: Portkey’s underlying open-source gateway code (`Portkey-AI/gateway`, MIT-licensed, 13,054 GitHub stars as of today) is still maintained and still merging PRs: the most recent merge landed 25 May 2026, the day the acquisition closed ([github.com/Portkey-AI/gateway](https://github.com/Portkey-AI/gateway)). It’s the hosted product and its commercial direction that changed, not the open-source repo’s licensing. ## The license terms are not identical, and that matters at production All three call themselves open source somewhere on their site. Only one of them is unqualified about it. **LiteLLM** ([BerriAI/litellm](https://github.com/BerriAI/litellm)) is 59,363 GitHub stars as of today and the top-level repository is MIT: genuinely permissive, no strings. But the `enterprise/` subdirectory carries its own separate license file, and it is not MIT: the BerriAI Enterprise License states plainly that code under that directory “may only be used in production” if you hold a paid subscription or other agreement with BerriAI, and forbids copying, merging, publishing, distributing, sublicensing or selling it otherwise ([raw license text, verified today](https://raw.githubusercontent.com/BerriAI/litellm/main/enterprise/LICENSE.md)). Enterprise features (SSO/SCIM, OIDC/JWT auth, RBAC by key/team/org, air-gapped deployment, 24/7 SLA-backed support) sit behind that carve-out ([litellm.ai/enterprise](https://www.litellm.ai/enterprise)). The core gateway (routing, virtual keys, budgets, provider fallback) is fully MIT and free to self-host indefinitely; you only hit the enterprise license if you need the governance layer a larger org typically wants. **Helicone’s AI Gateway** is a separate repository from Helicone’s main observability platform, and the two are licensed differently. The main Helicone app (`Helicone/helicone`) is Apache-2.0, 6,170 stars. The AI Gateway (`Helicone/ai-gateway`), the Rust-based proxy that actually routes and load-balances your LLM traffic, is GPL-3.0, and that’s a recent, deliberate change: the repo’s commit history shows it moved from Apache-2.0 to GPL-3.0 on 21 November 2025, with the commit message “Replace Apache License 2.0 with GNU General Public License v3.0” ([commit on GitHub](https://github.com/Helicone/ai-gateway/commits/main)). GPL-3.0 is copyleft: if you distribute a modified version of the gateway, you’re obligated to release your modifications under GPL-3.0 too. Running it unmodified as an internal service doesn’t trigger that obligation (GPL-3.0 doesn’t have AGPL’s network-use clause), but it’s a materially different commitment than the MIT core of LiteLLM or the Apache-2.0 of Helicone’s own observability platform, and worth flagging to legal before you fork it. **Portkey**’s hosted product has no GitHub link in our records because there isn’t a self-hostable equivalent of the product you’d actually be evaluating. The open-source `Portkey-AI/gateway` repo is MIT, but it’s the routing engine, not the observability/governance dashboard Portkey sells. If open licensing across the whole stack is the requirement, Portkey was never really in this race; LiteLLM and Helicone’s Gateway are. ## What each one actually costs to run Self-hosting removes the license fee but not the engineering cost of running a proxy in production; hosted removes the ops burden but adds a metered bill. Here’s what each vendor actually publishes, checked today: - **LiteLLM**: the gateway itself is $0 whether self-hosted or not. There’s no metered request pricing. Enterprise support and governance features are “Get In Touch” custom pricing, not published. - **Portkey**: Free up to 10k logged requests/month. Production is $49/month for 100k logged requests, then $9 per additional 100k. At 2 million requests/month that’s $49 + (19 × $9) = **$220/month**, on top of whatever compute you’re already paying the model providers. - **Helicone**: Hobby is free for 10,000 requests/month and 1GB storage. Pro is $79/month with “usage-based pricing” beyond the free allotment, priced through a calculator on their site rather than a published flat rate; the vendor doesn’t quote a fixed per-request overage number the way Portkey does ([helicone.ai/pricing](https://www.helicone.ai/pricing)). If the whole reason you’re looking at a gateway is to cut cost and avoid vendor lock-in, paying nothing but your own infrastructure bill for LiteLLM is hard to beat, which is presumably why NVIDIA, AT&T, Netflix, and Okta are cited as users on LiteLLM’s own site ([litellm.ai](https://litellm.ai/)) and why it dwarfs the other two on GitHub activity. ## Which one is actually still being built Stars are a lagging indicator; commit and merge activity tells you who’s still working on it. - **LiteLLM**: last push today (22 September 2026, per GitHub API), 5,196 open issues (a large number, but consistent with a project fielding contributions at scale rather than one going quiet). - **Helicone’s AI Gateway**: last commit 30 July 2025, 13 open issues, 631 stars. That’s over a year without a commit on the gateway repo specifically, worth checking again before you commit if it still matters to you, since a proxy sitting in your request path is not somewhere you want unpatched CVEs piling up quietly. (Helicone’s main observability platform, by contrast, pushed as recently as 25 July 2026, per our records; it’s the Gateway component specifically that looks stalled.) - **Portkey’s open-source gateway**: last merged PR 25 May 2026 (the day the acquisition closed), with 275 open issues on a 13,054-star repo. Still active, just now under different corporate ownership. ## The decision **Default to LiteLLM** if you want a free, actively maintained, self-hosted gateway with a real community behind it, and you’re comfortable that the enterprise governance layer (SSO, RBAC, air-gapped deployment) is a paid add-on rather than free. **Choose Helicone’s AI Gateway** if raw proxy performance is the deciding factor and your legal team is fine with GPL-3.0 on that one component. Its own benchmarks claim sub-5ms P95 latency and ~64MB memory footprint against a “typical setup” baseline of 60–100ms and ~512MB ([helicone.ai/gateway](https://www.helicone.ai/gateway); these are the vendor’s own numbers, not independently verified). Note it’s a separate, less actively committed repo than Helicone’s main observability product. **Consider Portkey/Prisma AIRS** only if what you actually need is agent governance under a cybersecurity vendor’s umbrella: SOC 2, HIPAA, VPC hosting, and a sales team that reports up through Palo Alto Networks. If you came looking for an independent, developer-first routing layer, that’s no longer quite what’s on offer. About the author [Team AgentsIndex](https://agentsindex.ai/authors/agentsindex) Editorial team The AgentsIndex research desk publishes source-linked product research and original market analysis. ## Top of agent tools and integrations [The category page](https://agentsindex.ai/categories/agent-tools-and-integrations) - [Base2026](https://agentsindex.ai/base2026) · The team behind Base2026 runs this listing · Free SEO research MCP server, public API and browser SEO checks with original sources attached. · Free Checked 26 Oct · [Visit](https://agentsindex.ai/go/base2026) - MCP server: yes - API: yes - Open source: yes - Self-host: not listed - [ERIUS PHONE](https://agentsindex.ai/eriusphone) · The team behind ERIUS PHONE runs this listing · Isolated cloud Android phones rented by the month that keep an agent's apps and sign-ins between sessions. · From about $44 a month Checked 14 Nov · Free trial · [Visit](https://agentsindex.ai/go/eriusphone) - MCP server: yes - API: yes - Open source: partly - Self-host: no - [Smithery](https://agentsindex.ai/smithery) · Public MCP server registry, now run by Arcade, listing direct vendor MCP URLs after its proxy shut down. · Free Checked 14 Nov · Freemium · [Visit](https://agentsindex.ai/go/smithery) - MCP server: yes - API: no - Open source: partly - Self-host: partly - [UI Discovery](https://agentsindex.ai/uidiscovery) · The team behind UI Discovery runs this listing · A library of real websites, iOS apps and dashboards with each one's palette, fonts and original build prompt. · From $20 a month Checked 13 Nov · [Visit](https://agentsindex.ai/go/uidiscovery) - MCP server: yes - API: yes - Open source: no - Self-host: not listed - [TinyFish](https://agentsindex.ai/tinyfish) · The team behind TinyFish runs this listing · Web search, page fetching, cloud browsers and a web automation agent for AI agents, with search and fetch free. · Free, then $0.002 per minute Checked 14 Nov · ISO 27001 · [Visit](https://agentsindex.ai/go/tinyfish) - MCP server: yes - API: yes - Open source: no - Self-host: partly - [ClineFlow](https://agentsindex.ai/clineflow) · The team behind ClineFlow runs this listing · Git-native project memory and handoffs for coding agents. · Free Checked 13 Nov · [Visit](https://agentsindex.ai/go/clineflow) - MCP server: no - API: no - Open source: yes - Self-host: yes - [AgentMail](https://agentsindex.ai/agentmail) · Email provider where agents send, receive and thread mail, with webhooks and websockets for incoming messages. · Free, then $20 a month Checked 12 Nov · EU-hosted Freemium SOC 2 · [Visit](https://agentsindex.ai/go/agentmail) - MCP server: yes - API: yes - Open source: yes - Self-host: partly - All 95 AI agent tools and integrations · First paid plans from $3 to $650 a month. · [See all 95](https://agentsindex.ai/categories/agent-tools-and-integrations) - 67 free to start - 43 publish a monthly price - 41 open source - Checked 30 July–14 November 2026 [Show the whole category](https://agentsindex.ai/categories/agent-tools-and-integrations) ## More of our research Comparison 16 October 2026 ### [Daytona vs E2B vs Modal: which sandbox for agent code?](https://agentsindex.ai/blog/daytona-vs-e2b-vs-modal) Daytona, E2B and Modal compared on sandbox pricing, concurrency, GPU support and open-source status, plus why Daytona's flagship repo is now archived. Comparison 28 September 2026 ### [Beam AI, Stack AI, Gumloop and more: which can you buy?](https://agentsindex.ai/blog/agent-automation-platforms-which-can-you-actually-buy) We checked all six pricing pages today. Only BuildShip has a real self-serve ladder. The other five gate you behind a sales call or a $500+/month floor. Comparison 25 September 2026 ### [Which browser automation API should you build an agent on?](https://agentsindex.ai/blog/browser-automation-api-comparison) Skyvern, Browserbase, Browser Use, Playwright MCP, Hyperbrowser, and TinyFish compared on credential handling, session isolation, and audits, not speed. Comparison 15 August 2026 ### [Workflow automation for AI agents: where free tiers end](https://agentsindex.ai/blog/workflow-automation-where-each-platform-stops-being-free) Zapier, Make, n8n, Activepieces, Pipedream and Trigger.dev meter in six different units. Which free tier survives real agent work, which runs out first.