CLI Delegation Agents Squads enables multi-LLM support by delegating to native provider CLIs. No SDK integrations needed—just shell out to claude, gemini, codex, grok, etc.
Check Available Providers Provider CLI Status ──────────────────────────────────────── Anthropic claude ✓ ready Google gemini ✓ ready OpenAI codex ✓ ready Mistral vibe ✓ ready xAI grok ✓ ready Aider aider ✓ ready Ollama ollama ✓ ready ✓ All providers ready
Run with Specific Provider # Override provider for this run squads run research/analyst --execute --provider=google # Uses Gemini CLI instead of Claude
Provider Resolution The CLI resolves providers in this order:
Agent file - provider: in frontmatter or ## Provider headerCLI flag - --provider=googleSquad default - providers.default in SQUAD.mdFallback - anthropic
Configuration Squad-Level Providers Configure default providers in SQUAD.md frontmatter:
--- name : intelligence mission : Market research and competitive analysis providers : default : anthropic # CLI: claude vision : openai # CLI: codex (for image analysis) realtime : xai # CLI: grok (for real-time data) cheap : google # CLI: gemini (for high-volume) ---
Agent-Level Override Override the provider for specific agents:
--- provider : xai --- # Social Monitor ## Purpose Real-time X/Twitter trend detection using Grok.
Supported CLIs Provider CLI Install Non-Interactive Flag Anthropic claudenpm i -g @anthropic-ai/claude-code--printGoogle gemininpm i -g @google/gemini-cli--promptOpenAI codexnpm i -g @openai/codexexec subcommandMistral vibecurl -LsSf https://mistral.ai/vibe/install.sh | bash--prompt --auto-approvexAI grokbun add -g @vibe-kit/grok-cli--promptMulti aiderpip install aider-install && aider-install--message --yesLocal ollamabrew install ollamarun <model> "<prompt>"
Environment Variables Each CLI reads its own API keys:
# .env (or shell profile) ANTHROPIC_API_KEY = sk-ant-... # claude GOOGLE_API_KEY = AIza... # gemini (or OAuth) OPENAI_API_KEY = sk-... # codex MISTRAL_API_KEY = ... # vibe XAI_API_KEY = ... # grok
Why Use Multiple LLMs? Different LLMs excel at different tasks. A well-designed agent system can leverage:
Claude - Complex reasoning, nuanced analysis, long contextGPT-4 - General purpose, wide knowledge, tool useGemini - Multimodal, Google ecosystem integrationGrok - Real-time data, X/Twitter integrationLlama/Open models - Privacy, self-hosting, cost control
Provider Comparison Provider Strengths Best For Claude (Anthropic) Reasoning, safety, long context Complex analysis, code review GPT-4 (OpenAI) Versatility, ecosystem General tasks, plugins Gemini (Google) Multimodal, speed Vision tasks, Google integration Grok (xAI) Real-time, humor Social media, current events Llama (Meta) Open source, self-host Privacy-sensitive, offline Mistral European, efficient EU compliance, edge deployment
Model Tiers (Within Providers) Each provider offers different capability tiers:
Anthropic (Claude)
OpenAI
Google
xAI
Model Use Case Cost Claude Opus Complex reasoning $$$ Claude Sonnet Balanced default $$ Claude Haiku Fast, simple tasks $
Model Use Case Cost GPT-4o Multimodal, flagship $$$ GPT-4o-mini Fast, efficient $ o1/o3 Deep reasoning $$$$
Model Use Case Cost Gemini Ultra Most capable $$$ Gemini Pro Balanced $$ Gemini Flash Speed optimized $
Model Use Case Cost Grok-2 Full capability $$$ Grok-2-mini Faster responses $$
Squad Configuration Agent-Level Provider Selection Assign different providers to different agents:
# SQUAD.md - Intelligence Squad ## Agents ### market-researcher **Provider** : Claude Sonnet **Purpose** : Deep market analysis requiring nuanced reasoning ### social-monitor **Provider** : Grok **Purpose** : Real-time X/Twitter monitoring and trend detection ### data-analyst **Provider** : GPT-4o **Purpose** : Spreadsheet analysis with vision capabilities ### summarizer **Provider** : Gemini Flash **Purpose** : Fast summarization of research findings
Environment Configuration Set up API keys for each provider:
# .env ANTHROPIC_API_KEY = sk-ant-... OPENAI_API_KEY = sk-... GOOGLE_API_KEY = AIza... XAI_API_KEY = xai-...
Provider Selection in Code Claude Code
OpenAI
Gemini
Grok
# Agent: Market Researcher **Model** : claude-sonnet-4-20250514 ## Instructions Analyze market trends using deep reasoning...
from openai import OpenAI client = OpenAI() response = client.chat.completions.create( model = "gpt-4o" , messages = [{ "role" : "user" , "content" : prompt}] )
import google.generativeai as genai genai.configure( api_key = os.environ[ "GOOGLE_API_KEY" ]) model = genai.GenerativeModel( "gemini-1.5-pro" ) response = model.generate_content(prompt)
from openai import OpenAI # Grok uses OpenAI-compatible API client = OpenAI( api_key = os.environ[ "XAI_API_KEY" ], base_url = "https://api.x.ai/v1" ) response = client.chat.completions.create( model = "grok-2" , messages = [{ "role" : "user" , "content" : prompt}] )
Routing Patterns Task-Based Routing Route tasks to the best provider:
Task Requirement Best Provider Real-time data Grok Image analysis GPT-4o / Gemini Deep reasoning Claude Opus Google integration Gemini General tasks Claude Sonnet / GPT-4o
Cascade Pattern Start cheap, escalate when needed:
Start cheap
Gemini Flash (fastest, cheapest)
If insufficient
Escalate to Claude Sonnet
If still insufficient
Escalate to Claude Opus
Consensus Pattern Use multiple providers for critical decisions:
Critical Decision → Run in parallel across Claude, GPT-4o, and Gemini → Voting/Synthesis → Final Answer
Cost Optimization Price Comparison (approximate per 1M tokens) Provider Input Output Claude Haiku $0.25 $1.25 GPT-4o-mini $0.15 $0.60 Gemini Flash $0.075 $0.30 Claude Sonnet $3.00 $15.00 GPT-4o $2.50 $10.00 Gemini Pro $1.25 $5.00 Claude Opus $15.00 $75.00
Prices change frequently. Check provider pricing pages for current rates.
Cost Strategy ## Budget Allocation Example - 60% → Gemini Flash / GPT-4o-mini (high-volume tasks) - 30% → Claude Sonnet / GPT-4o (standard tasks) - 10% → Claude Opus / o1 (complex reasoning)
Implementation Examples Multi-Provider Squad # .agents/squads/intelligence/SQUAD.md name : Intelligence Squad description : Multi-provider research and analysis agents : - name : trend-scanner provider : grok model : grok-2-mini purpose : Real-time social trend detection - name : deep-researcher provider : anthropic model : claude-sonnet-4-20250514 purpose : In-depth analysis and synthesis - name : data-visualizer provider : openai model : gpt-4o purpose : Chart and image generation - name : fast-summarizer provider : google model : gemini-1.5-flash purpose : Quick summaries and translations
Provider Abstraction Create a unified interface:
// lib/llm.ts type Provider = 'anthropic' | 'openai' | 'google' | 'xai' ; interface LLMConfig { provider : Provider ; model : string ; temperature ?: number ; } async function query ( config : LLMConfig , prompt : string ) { switch ( config . provider ) { case 'anthropic' : return queryAnthropic ( config . model , prompt ); case 'openai' : return queryOpenAI ( config . model , prompt ); case 'google' : return queryGemini ( config . model , prompt ); case 'xai' : return queryGrok ( config . model , prompt ); } }
Best Practices
Match provider strengths to task requirements
Use cheaper models for high-volume, simple tasks
Reserve expensive models for complex reasoning
Implement fallbacks across providers for reliability
Monitor costs per provider weekly
Abstract provider selection for easy switching
Avoid:
Using one provider for everything (miss optimizations)
Ignoring rate limits (each provider has different limits)
Hardcoding provider choice (make it configurable)
Forgetting about latency differences
Token Economics Optimize costs across providers
Agent Parallelization Run multi-provider agents concurrently
