APIs · head to head
Convoy vs Seldon

Convoy
APIs
Open source webhooks gateway you self-host, handling both sending and receiving
- From
- Free
- Free plan
- Yes

Seldon
Machine Learning
Kubernetes model serving whose current version is licensed under the Business Source Licence
- From
- Free
- Free plan
- Yes
The short version
- Seldon is free; Convoy starts at $999/mo.
- Only Convoy lists inbound and outbound; only Seldon lists kubernetes custom resources.
- Where Convoy falls short: the hosted cloud trial is capped at one project and 100 events a day, which is too small to properly evaluate the service before committing.
- Prices and features on this page were last checked on 20 November 2026.
How do Convoy and Seldon differ?
Convoy and Seldon differ on pricing model, platforms and category (APIs against Machine Learning). Only the attributes on which Convoy and Seldon actually diverge.
Identical on both: starting price (Free), free tier (Yes).
Not yet recorded: founded for Convoy.
Which features does each one have?
They share no listed features; 8 appear only for Convoy and 8 only for Seldon. Drawn from each product's published feature list. An absence here means we hold no record of it - not that the product lacks it.
Only in Convoy
- Inbound and outbound
- Broker-driven ingestion
- Payload transformation
- Portal links
- Circuit breaking
- Retry policies
- OpenTelemetry export
- Role-based access control
Only in Seldon
- Kubernetes custom resources
- Inference graphs
- Traffic strategies
- Open Inference Protocol
- Alibi Explain
- Alibi Detect
- Kafka-backed pipelines in v2
- Commercial control plane
What is each one used for?
The jobs each tool is most often brought in to do.
Convoy
- A fintech that cannot route customer webhook traffic through a third-party SaaS for compliance reasonsnot Seldon
- A high-volume platform for which per-message webhook pricing costs more than the flat premium licencenot Seldon
- A team that also receives webhooks from many providers and wants ingestion, verification and deduplication in the same gatewaynot Seldon
- An engineering group that wants webhook delivery driven directly from an existing Kafka or SQS topicnot Seldon
Seldon
- Serving an ensemble or a multi-stage inference path as one versioned deployment rather than as a chain of separate servicesnot Convoy
- Running genuine production experiments where a share of live traffic goes to a candidate model and the results are comparednot Convoy
- Regulated environments needing explanations and drift monitoring attached to the served model rather than bolted on laternot Convoy
- Organisations with an established Kubernetes platform team who want serving expressed as manifests under existing deployment controlsnot Convoy
Where do Convoy and Seldon fall short?
Documented limitations, not opinions. Every one is a constraint you would hit in normal use.
Convoy
- The default deployment is self-hosted, so you operate Convoy plus Postgres and Redis and carry the on-call burden for the system that delivers your customers' events
- Frain Technologies is a small startup, and putting customer-facing delivery infrastructure on it means accepting real vendor continuity risk on a component that is hard to swap out quickly
- The premium tier at a flat 999 US dollars a month is poor value below substantial volume, while the community edition omits the portal, transformations and RBAC that most production deployments end up wanting
- The hosted cloud trial is capped at one project and 100 events a day, which is too small to properly evaluate the service before committing
- Documentation and the third-party ecosystem are thinner than the established webhook services, so unusual configurations often mean reading the Go source
Seldon
- Seldon Core v2 is under the Business Source Licence rather than Apache 2.0, so production use requires a commercial agreement, and a team that evaluated it believing it was open source discovers the licence is the blocker exactly when the project is ready to ship
- Core v1 remains Apache 2.0 but is in maintenance, so taking the free route means running software that receives no new development while the architecture it belongs to moves on without it
- Version 2 is a different system rather than a newer release, with different custom resources, a scheduler component and a Kafka-based pipeline model, so migrating from v1 is a re-implementation of every deployment manifest rather than an upgrade
- Kafka is a dependency for v2 pipelines, so an organisation that does not already operate it takes on a distributed log with its own storage, retention, rebalancing and failure modes purely in order to serve models
- Everything assumes Kubernetes fluency and the failure modes are Kubernetes failure modes, custom resource version mismatches, an operator that will not reconcile, admission webhooks and resource limits terminating an inference pod mid-request, so it needs a platform engineer rather than a data scientist
How much do Convoy and Seldon cost?
Convoy has a free plan, with paid plans from $999/mo; Seldon is free to use. Plan by plan below, from each vendor's own pricing page.
Convoy
Free- CommunityFree
- Self-hosted open source gateway
- Inbound and outbound webhooks
- Automatic retries and message broker support
- Premium$999/mo
- Flat rate irrespective of message volume
- Portal links and payload transformation
- RBAC, circuit breaking and white labelling
- EnterpriseOn request
- SAML SSO
- Dedicated support with SLA
- On-premises deployment assistance
- CloudOn request
- Hosted by Convoy
- 14 day trial limited to one project and 100 events a day
- Usage-based tiers above the trial
Seldon
Free- Seldon CoreFree
- Open source
- Kubernetes deployment
- Model serving
- Seldon DeployFree
- Enterprise features
- GUI
- Monitoring
Which should you pick?
Choose Convoy if
- You need inbound and outbound.
- You want to start without paying.
- You work on Linux, Self-hosted, Web.
- You also want broker-driven ingestion.
Choose Seldon if
- You need kubernetes custom resources.
- You want to start without paying.
- You work on Linux.
- You also want inference graphs.
Questions people ask
- Is Convoy or Seldon better?
- Neither clearly leads. Convoy starts at Free and Seldon at Free, and user ratings are close enough to be indistinguishable. Choose on capability and platform support.
- Which is cheaper, Convoy or Seldon?
- Convoy starts at Free and Seldon at Free.
- Does Convoy or Seldon run on more platforms?
- Convoy runs on Linux, Self-hosted, Web. Seldon runs on Linux.
- Can I use Convoy for free?
- Both have a free tier, so you can try either at no cost before committing.
- What is Convoy best used for?
- Convoy is most often used for a fintech that cannot route customer webhook traffic through a third-party saas for compliance reasons, a high-volume platform for which per-message webhook pricing costs more than the flat premium licence, a team that also receives webhooks from many providers and wants ingestion, verification and deduplication in the same gateway, an engineering group that wants webhook delivery driven directly from an existing kafka or sqs topic. Of those, a fintech that cannot route customer webhook traffic through a third-party saas for compliance reasons and a high-volume platform for which per-message webhook pricing costs more than the flat premium licence are not what Seldon is typically brought in for.
- What can Convoy do that Seldon cannot?
- Convoy covers Inbound and outbound, Broker-driven ingestion, Payload transformation, Portal links. Seldon covers Kubernetes custom resources, Inference graphs, Traffic strategies, Open Inference Protocol.
Answered from the vendors’ own pages
Convoy: Is Convoy really open source?
Yes, the community edition is open source and self-hostable, covering both inbound and outbound webhooks with retries.
Seldon: Is Seldon open source?
Partly, and this is the thing to check before you build on it. Core v1 is Apache 2.0 but in maintenance. Core v2 was moved to the Business Source Licence in 2024, which allows evaluation but not unlicensed production use. Verify the current licence of each component you intend to run, including MLServer and the Alibi libraries.
Convoy: What does premium cost?
A flat 999 US dollars a month, self-hosted, regardless of message volume.
Seldon: What is the difference between v1 and v2?
Architecture, not just version number. v2 introduces a scheduler, a different set of custom resources and Kafka-backed pipelines. Manifests, mental model and operations all change, so treat a move as a project.
Convoy: Does it receive webhooks as well as send them?
Yes, inbound ingestion with verification and deduplication is a first-class feature, unlike most webhook services.
Seldon: Do I need Kubernetes?
Yes. It is a Kubernetes-native system and there is no meaningful deployment without a cluster and someone competent to run it.
Convoy: Do I have to self-host?
No, there is a hosted cloud, but the trial is capped at 100 events a day and self-hosting is the primary model.
Seldon: What is MLServer?
Seldon's Python inference server implementing the Open Inference Protocol, usable inside Seldon deployments or on its own. Check its current licence alongside Core's, since the company has moved projects onto the Business Source Licence.
Seldon: Do I have to run Kafka?
For v2 pipelines, yes. If you only need single models served, that dependency is a large amount of infrastructure for the benefit, and a simpler serving layer may be the better answer.
Related pages
Other head to heads
- Convoy vs Kong Gateway
- Convoy vs Svix
- Convoy vs Tyk
- Convoy vs Janus Gateway
- Convoy vs Appwrite
- Convoy vs Gravitee
- Convoy vs Spring Cloud Gateway
- Convoy vs Formance
- Convoy vs AWS API Gateway
- Convoy vs IBM API Connect
- Convoy vs Directus
- Convoy vs Bruno
- Convoy vs Fintecture
- Convoy vs KeystoneJS
- Convoy vs LiteLLM
- Convoy vs Moov
- Convoy vs Portkey
- Convoy vs Q2 Digital Banking
- Convoy vs BentoML
- Convoy vs Kubeflow
- Convoy vs AWS SageMaker
- Convoy vs Azure Machine Learning
- Convoy vs Google Vertex AI
- Convoy vs Ray
- Convoy vs Pachyderm
- Convoy vs DataRobot
- Convoy vs MLflow
- Convoy vs DVC
- Convoy vs JupyterHub
- Convoy vs Weights & Biases
- Convoy vs Hugging Face
- Convoy vs SAS
- Convoy vs KNIME
- Convoy vs Pinecone
- Convoy vs Weaviate
- Convoy vs LangChain
- Seldon vs Kong Gateway
- Seldon vs Svix
- Seldon vs Tyk
- Seldon vs Janus Gateway
- Seldon vs Appwrite
- Seldon vs Gravitee
- Seldon vs Spring Cloud Gateway
- Seldon vs Formance
- Seldon vs AWS API Gateway
- Seldon vs IBM API Connect
- Seldon vs Directus
- Seldon vs Bruno
- Seldon vs Fintecture
- Seldon vs KeystoneJS
- Seldon vs LiteLLM
- Seldon vs Moov
- Seldon vs Portkey
- Seldon vs Q2 Digital Banking
- Seldon vs BentoML
- Seldon vs Kubeflow
- Seldon vs AWS SageMaker
- Seldon vs Azure Machine Learning
- Seldon vs Google Vertex AI
- Seldon vs Ray
- Seldon vs Pachyderm
- Seldon vs DataRobot
- Seldon vs MLflow
- Seldon vs DVC
- Seldon vs JupyterHub
- Seldon vs Weights & Biases
- Seldon vs Hugging Face
- Seldon vs SAS
- Seldon vs KNIME
- Seldon vs Pinecone
- Seldon vs Weaviate
- Seldon vs LangChain
