One unified API. A curated, live model list. Automatic task-to-model matching based on capability scoring, tier, and budget constraints.
The models below are the ones the router is serving right now, read live from the API. The set can change without notice.
Fast, cheap inference for high-volume agent tasks: summaries, simple Q&A, structured extraction.
Balanced capability for tool use, coding, and multi-step reasoning at reasonable cost.
Highest-capability tier for complex reasoning, agentic workflows, long-context tasks, and highest-stakes outputs.
Prices are SwarmSync's listed per-model rates per million tokens and may differ from what a provider charges directly. You pay the listed rate plus an 8% SwarmSync fee.
Pass model: "auto" and the router scores your task across 8 capabilities, matches the task profile to each model's strength vector, and picks the best-fit model within your tier.
Every model has a strength vector across coding, reasoning, creative writing, structured output, long context, conversation, tool use, and multilingual. Routing is dot-product similarity.
Set a budget cap on your agent and the router automatically stays within economy or mid tier. Premium models are only selected when the task score exceeds your tier threshold.
Need a specific model? Pin it directly with a model ID exactly as listed by GET /v1/models. The router passes through pinned requests without scoring overhead.
Direct-provider models behind one unified OpenAI-compatible API. The exact set changes over time and is always listed at GET /v1/models. Switch providers without changing your agent code.
Full support for streaming responses and function calling across all compatible models. The router respects tool-use capability flags and never routes tool-use tasks to models that don't support them.
The router classifies every prompt across these dimensions, then finds the model whose strength vector best matches the task profile.
Drop-in OpenAI-compatible. Works with any SDK that targets the OpenAI API.
OpenAI-compatible chat completions with auto-routing
List all available models with tier, pricing, and capabilities
Preview which model would be selected for a given prompt (no LLM call made)
List routing API keys for your account (requires auth)
Usage stats and cost summary for this API key
Use any OpenAI-compatible client. Set model: "auto" to enable intelligent routing.
import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://api.swarmsync.ai/v1',
apiKey: process.env.SWARMSYNC_ROUTING_KEY,
});
const response = await client.chat.completions.create({
model: 'auto', // auto-routes to best model
// model: 'economy', // → economy tier (same as swarmsync/budget)
// model: 'premium', // → premium tier (same as swarmsync/performance)
messages: [{ role: 'user', content: 'Your prompt here' }],
});Get a routing key from your console settings and start calling a curated set of models through a single OpenAI-compatible endpoint.