OpenClaw LLM Router 🧠

"Chat with GPT-4 for reasoning, switch to Claude for creative writing"

"Compare responses from GPT-4, Claude, and Gemini for the same question"

"Analyze this image with GPT-4o - what objects are in it?"

"Route simple queries to fast/cheap models, complex queries to GPT-4"

"If GPT-4 fails, automatically try Claude, then Gemini"

export AISA_API_KEY="your-key"

POST https://api.aisa.one/v1/chat/completions

curl -X POST "https://api.aisa.one/v1/chat/completions" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4.1",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Explain quantum computing in simple terms."}
    ],
    "temperature": 0.7,
    "max_tokens": 1000
  }'

{
  "role": "user|assistant|system",
  "content": "message text or array for multimodal"
}

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1234567890,
  "model": "gpt-4.1",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Quantum computing uses..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 50,
    "completion_tokens": 200,
    "total_tokens": 250,
    "cost": 0.0025
  }
}

curl -X POST "https://api.aisa.one/v1/chat/completions" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-3-sonnet",
    "messages": [{"role": "user", "content": "Write a poem about AI."}],
    "stream": true
  }'

data: {"id":"chatcmpl-xxx","choices":[{"delta":{"content":"In"}}]}
data: {"id":"chatcmpl-xxx","choices":[{"delta":{"content":" circuits"}}]}
...
data: [DONE]

curl -X POST "https://api.aisa.one/v1/chat/completions" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {
        "role": "user",
        "content": [
          {"type": "text", "text": "What is in this image?"},
          {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}}
        ]
      }
    ]
  }'

curl -X POST "https://api.aisa.one/v1/chat/completions" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4.1",
    "messages": [{"role": "user", "content": "What is the weather in Tokyo?"}],
    "functions": [
      {
        "name": "get_weather",
        "description": "Get current weather for a location",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {"type": "string", "description": "City name"},
            "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}
          },
          "required": ["location"]
        }
      }
    ],
    "function_call": "auto"
  }'

POST https://api.aisa.one/v1/models/{model}:generateContent

curl -X POST "https://api.aisa.one/v1/models/gemini-2.0-flash:generateContent" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [{"text": "Explain machine learning."}]
      }
    ],
    "generationConfig": {
      "temperature": 0.7,
      "maxOutputTokens": 1000
    }
  }'

# Basic completion
python3 {baseDir}/scripts/llm_router_client.py chat --model gpt-4.1 --message "Hello, world!"

# With system prompt
python3 {baseDir}/scripts/llm_router_client.py chat --model claude-3-sonnet --system "You are a poet" --message "Write about the moon"

# Streaming
python3 {baseDir}/scripts/llm_router_client.py chat --model gpt-4o --message "Tell me a story" --stream

# Multi-turn conversation
python3 {baseDir}/scripts/llm_router_client.py chat --model qwen-max --messages '[{"role":"user","content":"Hi"},{"role":"assistant","content":"Hello!"},{"role":"user","content":"How are you?"}]'

# Vision analysis
python3 {baseDir}/scripts/llm_router_client.py vision --model gpt-4o --image "https://example.com/image.jpg" --prompt "Describe this image"

# List supported models
python3 {baseDir}/scripts/llm_router_client.py models

# Compare models
python3 {baseDir}/scripts/llm_router_client.py compare --models "gpt-4.1,claude-3-sonnet,gemini-2.0-flash" --message "What is 2+2?"

from llm_router_client import LLMRouterClient

client = LLMRouterClient()  # Uses AISA_API_KEY env var

# Simple chat
response = client.chat(
    model="gpt-4.1",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response["choices"][0]["message"]["content"])

# With options
response = client.chat(
    model="claude-3-sonnet",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain relativity."}
    ],
    temperature=0.7,
    max_tokens=500
)

# Streaming
for chunk in client.chat_stream(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Write a story."}]
):
    print(chunk, end="", flush=True)

# Vision
response = client.vision(
    model="gpt-4o",
    image_url="https://example.com/image.jpg",
    prompt="What's in this image?"
)

# Compare models
results = client.compare_models(
    models=["gpt-4.1", "claude-3-sonnet", "gemini-2.0-flash"],
    message="Explain quantum computing"
)
for model, result in results.items():
    print(f"{model}: {result['response'][:100]}...")

def smart_route(message: str) -> str:
    # Simple queries -> fast/cheap model
    if len(message) < 50:
        model = "gpt-3.5-turbo"
    # Complex reasoning -> powerful model
    else:
        model = "gpt-4.1"
    
    return client.chat(model=model, messages=[{"role": "user", "content": message}])

def chat_with_fallback(message: str) -> str:
    models = ["gpt-4.1", "claude-3-sonnet", "gemini-2.0-flash"]
    
    for model in models:
        try:
            return client.chat(model=model, messages=[{"role": "user", "content": message}])
        except Exception:
            continue
    
    raise Exception("All models failed")

results = client.compare_models(
    models=["gpt-4.1", "claude-3-opus"],
    message="Analyze this quarterly report..."
)

# Log for analysis
for model, result in results.items():
    log_response(model=model, latency=result["latency"], cost=result["cost"])

MODEL_MAP = {
    "code": "deepseek-coder",
    "creative": "claude-3-opus",
    "fast": "gpt-3.5-turbo",
    "vision": "gpt-4o",
    "chinese": "qwen-max",
    "reasoning": "gpt-4.1"
}

def route_by_task(task_type: str, message: str) -> str:
    model = MODEL_MAP.get(task_type, "gpt-4.1")
    return client.chat(model=model, messages=[{"role": "user", "content": message}])

{
  "error": {
    "code": "model_not_found",
    "message": "Model 'xyz' is not available"
  }
}

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AISA_API_KEY"],
    base_url="https://api.aisa.one/v1"
)

response = client.chat.completions.create(
    model="gpt-4.1",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)