Why stepIQ Features Pricing Docs Templates

Now in public beta

Build AI pipelines.
Ship without infrastructure.

Chain models, prompts and logic into multi-step workflows.
Trigger via API, cron, or one click. Model-agnostic, privacy-first, and open source.

Start building free → View documentation

weekly-blog-generator Running

Research claude-sonnet-4

Pick Topic gpt-4o

Write Draft claude-sonnet-4

Quality Review claude-sonnet-4

Works with Anthropic OpenAI Meta Llama Mistral

WHY WE'RE DIFFERENT

Built for teams who need control

Not another black-box wrapper: choose models freely, keep security standards high, and build on open code.

Model-agnostic by default

Use the best model for each step. Mix Anthropic, OpenAI, Meta Llama, and others in one workflow.

See supported models

Privacy-first, security-first

Secrets are encrypted, traffic is protected, and data handling is explicit. Security controls are built into the core platform.

Read privacy & security details

Open source and auditable

The platform code is public so teams can verify behavior, self-host strategy, and integrate transparently.

View source on GitHub

HOW IT WORKS

From YAML to production
in three steps

Define once, trigger from your stack, and ship outputs with production-ready execution flow.

Define

Build your pipeline in the editor or import YAML. Set steps, models, variables, and output format.

Trigger

Run on demand, via API, webhook, or cron (plan-dependent). Track execution live with per-step status and stream updates.

Deliver

Return output via API response or send to outbound webhooks with signing and retries. More delivery targets are rolling out.

PIPELINE AS CODE

Everything you need to
orchestrate AI workflows

pipeline.yaml

name: weekly-blog-generator
version: 1

variables:
  language: "fr"
  tone: "direct, pragmatic"

steps:
  - id: research
    model: claude-sonnet-4
    output_format: json
    retry:
      max_attempts: 2

  - id: write_draft
    model: claude-sonnet-4
    output_format: markdown

Model-agnostic

Route each step to the right model provider with unified retries, auth, and usage tracking.

Variable interpolation

Reference previous outputs, user inputs, secrets, and pipeline metadata with Handlebars-like syntax.

Retries & conditions

Built-in retry with backoff. Conditional branching lets you loop or skip steps based on output quality.

Cron scheduling

Schedule pipelines with cron expressions. Timezone-aware, with distributed locking for reliability.

FEATURES

Built for production

Everything beyond the basics to run AI workflows at scale.

Real-time streaming

Watch each step execute live via SSE. See token counts, costs, and outputs as they stream in.

Encrypted secrets

Store API keys and tokens with AES-256-GCM encryption. Reference them safely in prompts via {{env.xxx}}.

YAML import/export

Define pipelines in YAML or JSON. Import, export, and version control your workflows alongside your code.

Cost tracking

Per-step token counts and costs. Get estimates before running. No surprise bills.

API & webhooks

Trigger pipelines programmatically. Unique webhook URLs per pipeline. Full REST API with scoped keys.

Version history

Every edit creates an immutable snapshot. Roll back to any version. Compare definitions side by side.

PRICING

Upgrade as your usage grows

All accounts start on Free by default. Upgrade anytime for higher limits and advanced features.

Starter

19€ /month

2,000 credits included

10 pipelines
10 steps per pipeline
100 runs/day
All core models
Cron scheduling
API access

Start starter

Pro

49€ /month

8,000 credits included

Unlimited pipelines
20 steps per pipeline
500 runs/day
All models
Cron scheduling
YAML import/export
Webhooks & API access
Priority execution

Start free trial

Enterprise

Custom

Custom credit allocation

Everything in Pro
SSO / SAML
Dedicated workers
SLA guarantee
Custom model endpoints
Priority support

Contact sales

Build AI pipelines.Ship without infrastructure.