AI Control Plane

Model Management

Provider-agnostic model routing with intelligent fallbacks. Define logical models, configure provider accounts, and set up routing policies that keep your AI pipelines resilient and cost-effective.

Logical Models

Abstract model definitions that decouple your pipelines from specific providers. Instead of hardcoding "gpt-4o" or "claude-sonnet" into your steps, you define a logical model with the capabilities and defaults you need, then map it to one or more provider targets.

Define Capabilities

Declare what your model supports: streaming responses, tool/function calling, vision inputs, and structured JSON mode output. Pipelines automatically respect these capabilities.

Set Defaults

Configure default parameters like temperature, max tokens, top-p, and stop sequences. Steps inherit these unless they specify their own overrides.

Map to Provider Targets

Each logical model maps to one or more concrete provider models. A single logical model like "primary-llm" can target OpenAI GPT-4o as its primary and Anthropic Claude as its fallback, all without your pipeline knowing the difference.

Provider Accounts

Configure API credentials for model providers. Each provider account encapsulates authentication, usage limits, and health state so that your routing layer always knows where to send requests.

OpenAI
Anthropic
Google
Azure
Cohere
Mistral

Rate Limits

Set requests-per-minute and tokens-per-minute limits per account. The router respects these limits and shifts traffic to alternative providers when thresholds are reached.

Monthly Budgets

Assign dollar-amount budgets to each provider account. Track spend in real time and get alerts before you hit the ceiling.

Health Monitoring

Continuous health checks track latency, error rates, and availability for each provider. Unhealthy accounts are automatically deprioritized.

Router Policies

Coming Soon

Intelligent routing rules that match incoming requests to the right model based on step type and purpose. Policies are evaluated in priority order, and each one can define fallback behavior, circuit breakers, and match criteria.

Priority-Based Routing

Assign numeric priorities to each policy. The router evaluates policies from highest to lowest priority, using the first match. This gives you fine-grained control over which model handles which workload.

Automatic Fallback

When the primary model is unavailable or returns errors, the router automatically falls back to secondary models defined in the policy. Requests keep flowing without any changes to your pipelines.

Circuit Breaker

Built-in circuit breaker pattern with configurable failure thresholds and recovery windows. When a model exceeds its error threshold, the circuit opens and traffic is redirected to healthy alternatives until the recovery period elapses.

Match Criteria

Policies match requests based on step type (inference, tool call, extraction) and purpose (chat, summarization, classification). This lets you route different workloads to the most suitable and cost-effective model.

Real-Time Stats

Every policy tracks live metrics: total match count, success rate, and error rate. Use these stats to tune priorities, adjust fallback chains, and identify underperforming models.

Why This Matters

Model management is the foundation of a resilient, cost-efficient AI platform. Here is what it unlocks for your team.

Swap Providers Without Changing Pipelines

Logical models abstract the provider away. Move from OpenAI to Anthropic (or any other provider) by updating a single mapping, not every step in every pipeline.

Set Up Fallbacks for Reliability

Automatic fallback chains and circuit breakers ensure your AI keeps running even when a provider has an outage or hits rate limits.

Monitor Costs with Per-Provider Budgets

Assign monthly budgets to each provider account and track spend in real time. Get alerts before costs spiral and route cheaper workloads to cheaper models.

Route Workloads to Optimal Models

Use match criteria on step type and purpose to send complex reasoning to powerful models and simple classification to fast, inexpensive ones.