Helicone vs LangSmith: how to choose
Helicone is an Apache-2.0 request logger and AI gateway that has received only patches and model support since March 2026. For a new deployment, LangSmith is usually the practical choice, since Helicone is not taking new cloud sign-ups; existing Helicone users can keep a self-hosted copy running while they plan a move.[3][4]
What is the difference between Helicone and LangSmith?
The main difference is status: Helicone has been in maintenance mode since March 2026, with new cloud sign-ups disabled, while LangSmith is LangChain's actively developed platform for tracing and evaluating agents. Mintlify acquired Helicone in March 2026, and on 19 October 2026 Helicone said it is no longer part of Mintlify, with no new owner named. For a new deployment, LangSmith is usually the practical choice; existing Helicone users should plan a migration.
At a glance (checked 20 October 2026)
| Decision factor | Helicone | LangSmith |
|---|---|---|
| Status | Maintenance mode since March 2026; new cloud sign-ups disabled | Active development; Engine v2 and Trajectory view shipped September 2026 |
| Ownership | Unclear: says it left Mintlify on 19 October 2026, no new owner named | LangChain, independent; $125M Series B in October 2025 |
| How it captures data | Proxy or AI Gateway in the request path; async SDKs also available | Async SDK or OpenTelemetry, out of the request path; optional gateway |
| Agent tracing | Header-based session grouping, not a span model | Nested runs, threads and a Trajectory view across subagents |
| Evaluation | Not an evaluation framework, by its own docs; Python evaluators turned off October 2026 | Offline and online evals with LLM-as-judge, pairwise and code evaluators |
| Licence and self-hosting | Apache-2.0; free to self-host with Docker or Helm | Proprietary; self-hosting is an Enterprise add-on |
| Pricing | Hobby free, Pro $79 a month, Team $799 a month; new accounts cannot sign up | Developer free for 1 seat; Plus $39 per seat a month |
Helicone vs LangSmith: capabilities side by side
| Capability | Helicone | LangSmith | Prefactor |
|---|---|---|---|
| Observe | |||
| LLM call tracing | ✓ | ✓ | ✓ |
| Multi-step agent tracing (tool calls, nested spans) | Partial | ✓ | ✓ |
| Cost tracking | ✓ | ✓ | ✓ |
| OpenTelemetry support | Partial | ✓ | ✓ |
| Evaluate | |||
| Offline evals (datasets, experiments) | Partial | ✓ | ✓ |
| Online evals on production traffic | Partial | ✓ | ✓ |
| LLM-as-a-judge scoring | Partial | ✓ | ✓ |
| Code-based evaluators | — | ✓ | ✓ |
| Human review and annotation | Partial | ✓ | ✓ |
| Prompt versioning and playground | ✓ | ✓ | — |
| Act on findings | |||
| Runtime controls on live agent actions | Partial | Partial | ✓ |
| Gateway or proxy in the request path | ✓ | — | — |
| Licence and deployment | |||
| Open source | ✓ | Partial | Partial |
| Self-hosting | ✓ | ✓ | Partial |
Helicone's status decides most of this
Helicone is in maintenance mode and closed to new sign-ups, so for a new team LangSmith, or another actively developed platform, is usually the practical choice. Mintlify acquired Helicone on 3 March 2026 and limited work to vulnerability patches, bug fixes and new-model support; on 19 October 2026 Helicone's site said it is no longer part of Mintlify, with no new owner named.
Read more
The last feature entry in its changelog is from November 2025. Fixes still land in the open-source repository: in October 2026 self-hosting was hardened, Python evaluators were turned off and judge calls rate limited. An AWS account lock in May 2026 took the dashboard down for about four days.
Different jobs: a request logger and gateway, or an agent platform
Helicone is a request logger and gateway; LangSmith is an agent tracing and evaluation platform. Helicone's own documentation says it is not an evaluation framework, while LangSmith covers datasets, experiments, online evaluators, annotation queues and Engine.
Read more
Helicone sits in the request path, with exact per-request cost across over 300 models, caching, failover, rate limits, a prompt registry; its prompt-injection blocking works with OpenAI models only. LangSmith traces outside the request path as nested runs and threads, and calculates cost for most OpenAI, Anthropic and Gemini models. Its optional LLM Gateway, in public beta since 30 July 2026, adds spend caps, model access policies and redaction to model calls but not tool calls.
If you run Helicone today
Nothing forces an immediate move: the main repository is Apache-2.0 and the cloud still runs for existing accounts. Self-hosted Docker no longer proxies LLM traffic on its own; the separate GPL-3.0 AI Gateway, last updated in November 2025, has to run beside it.
Read more
To move tracing, repoint Helicone's OpenLLMetry-based async logging at LangSmith's OTLP endpoint, which maps OpenLLMetry and Traceloop attributes, or add LangSmith's OpenAI and Anthropic wrappers. LangSmith's gateway also switches on with a base URL change but is in beta and lists no caching or failover. Export prompts and datasets first; nothing migrates them automatically.
Pricing shape
Helicone's prices only matter to existing accounts, since new customers cannot sign up for any tier. As of 20 October 2026 it lists Hobby free with 10K requests, 1 GB, one seat and 7-day retention, Pro at $79 a month with unlimited seats and one month of retention, and Team at $799 a month.
Read more
LangSmith's Developer tier is free for one seat and 5k base traces a month, and Plus is $39 per seat a month with 10k base traces; the per-trace overage rate is not published. See Helicone's pricing and LangSmith's pricing.
Where Prefactor fits
We sell the layer this section describes. Read it with that in mind.
Stated plainly, since Prefactor publishes this page: Prefactor is an agent evaluation platform that scores each step of a run and acts on what it finds through runtime policies on tool calls and data access, approval holds for risky actions, and a kill switch for a run, an agent or a team. Helicone can block prompt injection for OpenAI models and LangSmith's gateway can cap spend and redact model calls, but neither holds a tool action for a person. If you are leaving Helicone, Prefactor accepts OpenTelemetry traces. It has no gateway, no prompt playground or prompt registry, and it is hosted. See the full comparison of 15 platforms.
Which one fits
Stay on Helicone for now if
- You already run it, ideally self-hosted, and it does what you need.
- You mainly need request logging and per-request cost, not evaluation.
- You have a migration plan and a date, rather than an open-ended wait.
- An Apache-2.0 codebase you can maintain yourself is acceptable.
Pick LangSmith if
- You are starting a new deployment and need a product that takes sign-ups.
- You need offline and online evals, annotation queues and datasets.
- You build on LangChain, LangGraph or Deep Agents.
- You want an actively developed vendor with a named owner.
How we reviewed this comparison
Reviewed against public product and documentation pages on October 20, 2026. If a vendor has changed a feature, product name, or positioning since then, send a correction and we will update it. Numbered source links in the page body point to the ordered sources below.
Sources reviewed
- Helicone pricingChecked 2026-10-20.
- Helicone documentation
- Helicone ownership and status
- LangSmith pricingChecked 2026-10-20.
- LangSmith documentation
- LangSmith website
- Prefactor platform
Methodology
- Reviewed public product, documentation, and launch material visible at the time of writing.
- Mapped each page to the primary buyer, control layer, and runtime capabilities each vendor describes publicly.
- Prefer direct product and documentation pages over analyst summaries or reseller material.
What is the difference between Helicone and LangSmith?
How does Prefactor compare with Helicone and LangSmith?
Can I still sign up for Helicone?
How do I migrate from Helicone to LangSmith?
Does LangSmith replace Helicone's gateway?
What happened to Helicone in October 2026?
Who owns Helicone?
Is Helicone open source?
How much does Helicone cost?
Can Helicone block or hold a live agent action?
Who owns LangSmith?
Is LangSmith open source?
How much does LangSmith cost?
Can LangSmith block or hold a live agent action?
Is Prefactor open source?
How much does Prefactor cost?
Can Prefactor block or hold a live agent action?
Score the run, then act on it
Prefactor scores each step of every agent run and can hold or stop an action when a score says it should not happen. Start on the free tier: 5,000 spans a month, no credit card required.
Unified performance platform for agents, authentication, and risk management