One endpoint connects applications and agents to approved model deployments with caller identity, routing context, and cost attribution. Fourth of four launches in C1 Launch Week.
SAN FRANCISCO — October 1, 2026 — C1 today announced C1 LLM Gateway as part of Day 4 of its Launch Week. C1 LLM Gateway routes inference requests across supported public, private, and customer-controlled model deployments through a single policy-controlled endpoint, helping enterprises manage provider choice, data-handling requirements, and inference spend.
"Every prompt your teams send is a description of how your company works, and most companies are sending them to a single vendor by default," said Alex Bovee, CEO and co-founder of C1.ai. "That decision belongs to you. Policy should decide which models see which data, and you should know what every one of those calls costs and who made it."
As organizations deploy AI applications and agents across multiple models, each inference request introduces decisions about the provider, deployment, and cost of processing that request. C1 LLM Gateway brings those decisions under configured company policy while retaining caller, route, and usage context.
Applications connect to one C1 endpoint across supported providers and deployments in their configured scope. Teams define eligible routes using provider, model, deployment, region, and data-handling rules. Within those approved options, supported capability, health, latency, and cost signals guide route selection.
C1 LLM Gateway provides:
- Policy-controlled inference routing: Apply configured rules to determine which model endpoints a request can use, including supported public, private, and customer-controlled deployments.
- Provider flexibility: Move approved workloads among supported providers and deployments without changing the application’s gateway integration.
- Accountable usage: Tie requests to the person, application, workload, or agent using the endpoint.
- Cost attribution: Retain identity and workload context to report usage and allocate inference costs to owners, projects, or business units.
- Managed provider credential paths: Reduce the need to embed durable provider secrets in application code through supported managed credential paths.
C1 LLM Gateway uses the same C1 Platform identity and policy foundation as C1 MCP Gateway. LLM Gateway governs inference routing; MCP Gateway governs supported MCP, tool, and API actions. C1 LLM Gateway does not host models: customers retain responsibility for their models and inference deployments.
Learn more about C1 LLM Gateway or request a demonstration.
About C1.ai#
C1.ai is the identity platform for the AI era. Our platform connects humans and agents to enterprise systems with scoped access, enforced policies, human approval, and a record of every action. With C1.ai, the fastest path to AI adoption at scale is the governed path—giving organizations visibility and control without sacrificing security or slowing innovation. Companies such as Ramp, Zscaler, Qualtrics, and DoorDash trust C1.ai to govern identity, secure agents, and empower their teams to put AI to work. Learn more at c1.ai.
Media Contact: press@c1.ai