Next for Seldon: from LLM calls to specialized programs. Explore our upcoming direction and help shape it.
Read the thesis →Combine AI with proven software techniques.
Make production AI faster, more efficient and more reliable.
Start with an existing LLM-powered function. Compare implementations against quality, cost and latency requirements, then explicitly activate a qualified replacement.
Get started
Open beta and Seldon for Startups
Seldon for Startups
$3,000
Up to $3,000 in credits over 90 days for a 25-company cohort. Startups and enterprises are welcome. Application-based after signup.
Apply for $3,000 in credits →Apply in minutes · reviewed after signup · card only if accepted
Why Seldon
Too many production LLM calls are just expensive data work. Seldon helps you identify recurring work and investigate specialized programs.
Cost management.
Evaluate opportunities to reduce LLM spend, with quality, coverage, and latency measured alongside cost.
Effortless productionization.
Evaluate a function before integrating its hosted alias into your application.
Reliability and auditability.
Inspect versioned execution plans and their evidence. Specialized programs can combine ordinary code with learned judgments that still need evaluation.
Observability.
Get clarity on how your LLM workflows are driving your business processes and application logic.
Turn repeated LLM calls into production data pipelines.
See how it works →Drop-in router
Point your base_url at Seldon.
Route LLM calls through an OpenAI-compatible endpoint with cost, latency, and fallback controls. No SDK changes — swap the base URL and keep shipping.
Seldon base URL
SELDON_BASE_URL=https://api.seldon-ai.com/v1Use this as the base URL in any OpenAI-compatible SDK. It already includes /v1.
Explicit functions
Start with one existing LLM request.
Paste a request or short workflow into Functions. Review its inferred contract and authorize a bounded optimization run before changing your application.
Program synthesis
Evaluate a replacement before integrating it.
Functions compares eligible implementations against quality, cost and latency requirements. Inspect the generated-example evidence, try new inputs and explicitly activate a qualified revision.
FAQ
Questions from teams with real LLM traffic.
The short version: start with an existing request, evaluate alternatives, and only promote compiled paths when the evidence is strong enough.
What is Seldon?
Seldon optimizes explicit LLM-powered functions and hosts qualified replacements. Its OpenAI-compatible gateway remains available; traffic discovery and new Audit analysis are retired.
How is Seldon different from a normal AI gateway?
Alongside model routing, Seldon lets you evaluate implementations for a function you identify. Explicit activation makes a replacement callable; it does not automatically intercept your agent traffic.
What's the long-term vision?
We are exploring an AI compiler and runtime around existing application functions. A typed intermediate representation would connect the intended behavior to candidate implementations using ordinary code, specialist models, and LLMs. The thesis sets out the proposal and the questions we still need to answer.
Why combine AI with proven software techniques?
An LLM call can combine semantic judgment with extraction, lookup, and arithmetic. Making those operations explicit can reveal alternative implementations. Each alternative still needs evaluation against the behavior the application requires.
How do I start using it?
Open Functions, save an existing request, review its preview and optimize under your chosen budget. Try a qualified result, activate it and use its function alias through the hosted endpoint.
What happened to Live Audit?
New Audit and discovery work is retired. Historical reports and existing legacy-path controls remain available. Use Functions to optimize an operation you identify.
How does optimization actually roll out?
Activate a qualified Function, then update the intended application call to use its hosted alias. Evaluation on generated examples measures reference agreement or rubric pass rate, not established quality on your production traffic. Existing fallback and input limits still apply.
What data does Seldon retain?
Seldon retains API data needed for billing, reliability, debugging, audits, cache visibility, and compiled-path analysis. Trace payload capture redacts sensitive headers and secret-like values before storage.
Do you train models on customer data?
No. Seldon does not use customer prompts, outputs, traces, or cached responses to train generalized AI models.
Can we try Seldon safely in staging first?
Yes. Try a qualified Function with representative inputs, then integrate its alias in staging. Inspect its results and usage before changing production.