Cloud Auto-Model Selection & Tier Aliases

Model Tiers & Pareto-Optimal Routing

To simplify model selection across hundreds of available LLMs, CBorg provides four curated cloud tier aliases representing distinct points along the cost-vs-intelligence Pareto-optimal frontier (based on published industry benchmarks from Artificial Analysis). The cloud-auto smart router automatically selects among cloud-budget, cloud-standard, and cloud-advanced; cloud-max is available for explicit requests when maximum reasoning capability is required:

Tier AliasFrontier Position & ProfilePrimary Use Case
cloud-budgetMaximum Cost-Efficiency: Lowest token cost with rapid response latency.Basic Q&A, lightweight text formatting, data transformation, high-volume classification.
cloud-standardBalanced Everyday Utility: Solid intelligence with moderate cost.General multi-turn chat, standard code generation, document drafting, summarization.
cloud-advancedHigh Performance & Technical Depth: Strong reasoning at competitive speed.Complex scriptwriting, multi-step code synthesis, data analysis, math problem-solving.
cloud-maxFrontier Intelligence: Deep reasoning and maximum analytical capability.Architecture design, difficult debugging, formal mathematical proofs, complex logic puzzles.

Info

Dynamic Frontier Updates: As new models are released, benchmarks evolve on Artificial Analysis, and pricing structures change across providers, we will periodically update the underlying model mappings for these aliases. By pointing your applications to cloud-* aliases, your workloads automatically benefit from ongoing frontier improvements without requiring code changes.

All tier aliases are automatically paired with Headroom Context Compression (headroom-compressed) to compress conversational and tool-call history, maximizing usable context and reducing prompt latency.

Automated Selection: cloud-auto

If you prefer not to manage tier selection manually per request, CBorg offers the cloud-auto smart router.

cloud-auto dynamically analyzes each incoming prompt in real-time using LiteLLM’s complexity classification engine. It evaluates prompt characteristics—including input token count, structural complexity, reasoning cues, and coding keywords—and automatically dispatches the query to one of three Pareto tiers:

  • Simple prompts route to cloud-budget.
  • Standard conversational queries route to cloud-standard (the default fallback).
  • Technical analysis and coding tasks route to cloud-advanced.

cloud-max is not selected automatically by cloud-auto. Request cloud-max directly for deep reasoning challenges that require its maximum analytical capability.

Usage Examples

Using cURL with cloud-auto

curl https://api.cborg.lbl.gov/v1/chat/completions \
  -H "Authorization: Bearer $CBORG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "cloud-auto",
    "messages": [
      {
        "role": "user",
        "content": "Write a Python script that parses server access logs, computes p95 response times, and outputs a formatted markdown report."
      }
    ]
  }'

Using Python (OpenAI SDK) with a Specific Tier Alias

from openai import OpenAI
import os

client = OpenAI(
    api_key=os.environ.get("CBORG_API_KEY"),
    base_url="https://api.cborg.lbl.gov/v1",
)

# You can request the smart router 'cloud-auto' or a specific tier alias
response = client.chat.completions.create(
    model="cloud-advanced",
    messages=[
        {"role": "system", "content": "You are a scientific computing assistant."},
        {"role": "user", "content": "Explain how Monte Carlo simulations can estimate pi, with sample code."},
    ],
)

# The response identifies the concrete model selected behind the alias.
print(f"Underlying model: {response.model}")
print(response.choices[0].message.content)