AI Gateway

Every major AI model for your agent and workflows. No keys, no markup.

Your company agent, workflows and pipelines call models from every major provider through one gateway. There is no API key to manage, each role can use its own model, and calls are billed at each provider’s list price with no markup, shown by model on your Usage page.

Every major model

Models from OpenAI, Anthropic, Google, xAI, Mistral and more, named by model id. Changing a model is a one-line change in your repository.

No API keys

The platform holds the credential. There is no API key to create, store, rotate or leak, and none in your code.

A model per role

The company agent picks its model from the roles of the person it talks to, for example a stronger one for finance.

In workflows and pipelines

A workflow step drafts, classifies or summarises with one call, and pipelines grade records with decision models.

List price, no markup

Model calls are billed at each provider’s list price with no markup, apart from platform usage.

Spend by model

Your Usage and Billing pages show AI spend by model, day by day, next to everything else your workspace uses.

In code

agent/segmentstream.json
{  "models": {    "chat": {      "default": "openai/gpt-6-luna",      "byRole": { "finance": "anthropic/claude-opus-5.5" },      "preview": "google/gemini-2.5-flash-lite"    },    "stt": "spacexai/grok-stt",    "imageDescription": "google/gemini-2.5-flash-lite"  }}
Ontology SDK reference →

Use it, build on it, or have it built

Use it

Ask the agent or run a workflow; the model calls appear on your Usage page by model.

Build it with your agent

Your coding agent names a model id in a workflow step or in the agent’s settings and deploys. There is nothing else to set up.

Have our engineers build it

Our engineers choose the model for each task with you during a pilot.

Replaces An API key for every model provider, A separate AI bill per provider and Markups on model tokens.

Works with

Solutions built with it

Read more

Enterprise pilot

Start a pilot.

Want ai gateway set up for you? Our forward-deployed engineers build it with you in your workspace, as code you own.

  • One solution, on your data, in your own workspace
  • First version live in two weeks
  • Parity proven before anything is switched off
  • Fixed scope and price, credited to your contract if you continue

Not ready for a pilot? Send the form anyway with your question. An engineer will reply, not a sales rep.

How the pilot works

Goes to our founder’s inbox. No sales queue, no newsletter.

Build your company’s own software. Let agents run it.

$ segmentstream workspace create acme --region eu --subdomain acme

▸ Created workspace acme · database, warehouse and a private git repository

$ segmentstream workspace WORKSPACE-ID clone acme && cd acme

▸ your coding agent builds what your team asked for and runs the checks

$ git add -A && git commit -m "First version"

$ segmentstream deploy

▸ app, company agent, API and MCP tools live for your invited members

Start a pilot

Our engineers build the first version on your data in two weeks, at a fixed price.

Or build it yourself with your coding agent:

curl -fsSL https://segmentstream.com/install.sh | sh

We’ll email you product updates, tips and onboarding help. Unsubscribe anytime.