Focus on your agents. We handle the rest.
From your first prototype to millions of AI agents.
Define AI agents, add tools, and deploy through Git. Connic handles execution and scaling and connects agents to existing systems.
€20 welcome credit · No credit card required
Build
Models
Connect an existing provider key or use EU-hosted connic/* models with Project credits.
Replaces
Guardrails
Evaluate untrusted input and final output with block, warn, redact, or custom Python checks.
Replaces
Retrieval
Sync documents and source systems, then return scoped passages with stable citations.
Replaces
Deploy
Managed Runtime
Ship versioned agents with deploy gates, keyed concurrency, retries, sessions, and rollback.
Replaces
Ship
AI Governance
Register AI systems, track controls and incidents, and export hash-verifiable evidence.
Replaces
Any model. Any system. One platform.
Choose EU-hosted connic/* models or connect an existing provider. Connect agents to existing infrastructure.
Models
- Connic Models
- OpenAI
- Anthropic
- Google Gemini
- Azure OpenAI
- AWS Bedrock
- Vertex AI
- OpenRouter
Connectors
- Webhooks
- Cron
- Kafka
- SQS
- PostgreSQL
- WebSocket
- MCP
- S3
- Stripe
Start for free. Scale when ready.
Start with €20 in free credit. Choose monthly Project credit to match your usage as you grow.
Basic
€0/ month
Try Connic with real agents
- €20 one-off welcome credit
- Top up as needed · no monthly fee
- 3 active connectors
- 1 environment
Developer
From €40/ month
Ship a first production agent
- From €40 in monthly Project credit
- 25 active connectors · 3 environments
- 15 min run timeout
- 90 day log retention
Most Popular
Pro
From €200/ month
For teams running agents in production
- From €200 in monthly Project credit
- 50 active connectors · 5 environments
- 60 min run timeout
- 365 day log retention · priority support
- PR testing · custom domains
Starting prices shown for monthly billing, excluding VAT. Prepay 1 year and save 10%, or 2 years and save 25%. Your monthly credit stays the same.
Compare all plans in detailEnterprise: custom pricing, limits and compliance support. Talk to us
From the blog
Tutorials, product updates, and insights into how we build Connic.
Mistral Large 4: Europe's 1T Model, Benchmarks, Pricing & Setup
Mistral Large 4 is a 1T-parameter multimodal model trained in Europe; this guide covers its benchmarks, pricing, weights timeline, and setup for AI agents.
13 min read
Aleph Alpha Kolibri-1: EU Open-Weight Model, Benchmarks & Setup
Aleph Alpha's Kolibri-1 is a 78B open-weight German-English model trained in Europe; this guide covers its benchmarks, hardware, license, and agent setup.
15 min read
What We Shipped in September 2026
September added Connic Voice, phone and messaging connectors such as Twilio and Telnyx, the Playground, browser tools, human input, and lower run prices.
8 min read
Frequently Asked Questions
What Connic is, how it works, and what it costs.
Connic runs production AI agents. Teams define an agent in YAML, write its tools as Python functions, and push to Git. We handle deployment, scaling, monitoring, and the connectors that wire agents into existing stacks.
None. YAML and Python are enough to ship a production agent on Connic. The platform handles builds, deployments, scaling, and monitoring, so there is no Docker, Kubernetes, or CI/CD pipeline to maintain.
Connectors wire agents into the rest of an existing stack. Inbound connectors trigger an agent from a webhook, cron schedule, inbox, message queue (Kafka, SQS), or Postgres event. Outbound connectors push results back to APIs, services, or S3. Sync connectors handle real-time request/response over WebSocket. Configuration happens in the dashboard, while Connic runs the integration layer. Read why pre-built connectors beat custom connector work.
Teams can choose an EU-hosted connic/* model with Project credits or connect an existing key for OpenAI, Anthropic, Google, Mistral, AWS Bedrock, Azure OpenAI, and custom OpenAI-compatible endpoints. Swapping models requires one line in the agent YAML.
Basic includes a one-time €20 Project credit; Developer and Pro include monthly credit. Runtime, storage, retrieval, and connic/* model tokens use the same balance. Standard Projects can add prepaid credit manually or use auto-refill with a hard monthly cap. Enterprise Projects have custom pricing and commercial terms. There are no per-seat fees. See Connic model prices.
Yes. Documents can be uploaded to the built-in Retrieval, pasted as text, or written through the API. Agents query the data with semantic search. No separate vector database, embedding pipeline, or chunking strategy is required.
Every run is captured: full execution trace, tool calls, LLM prompts and responses, tokens, latency, and outcome. Each run can be inspected step by step in the dashboard. Nothing requires separate instrumentation; observability is on by default.
Yes. Basic has no monthly fee and includes a one-time €20 credit, three active connectors, and the full SDK and dashboard. Basic supports manual credit top-ups; Developer and Pro include monthly credit, while Enterprise provides custom limits, pricing, and commercial terms. No credit card is required to start.