✨ Agent-First API

{
  "error": {
    "message": "Model 'gpt5' not found",
    "type": "invalid_request_error",
    "param": "model",
    "code": "model_not_found",
    "did_you_mean": "gpt-4o",
    "suggestions": [
      {"id": "gpt-4o"},
      {"id": "gpt-4o-mini"},
      {"id": "claude-sonnet-4-5"}
    ],
    "hint": "Did you mean 'gpt-4o'? Use GET /v1/models to list all available models."
  }
}

{
  "error": {
    "message": "Insufficient balance: need ~$0.3500 for claude-sonnet-4-5, but balance is $0.1200.",
    "type": "insufficient_balance",
    "code": "insufficient_balance",
    "balance_usd": 0.12,
    "estimated_cost_usd": 0.35,
    "suggestions": [
      {"id": "gpt-4o-mini"},
      {"id": "deepseek-chat"}
    ],
    "hint": "Insufficient balance: need ~$0.3500 for claude-sonnet-4-5, but balance is $0.1200. Try a cheaper model, or top up at https://lemondata.cc/dashboard/billing."
  }
}

{
  "error": {
    "message": "Model claude-opus-4-6 temporarily unavailable",
    "code": "all_channels_failed",
    "retryable": true,
    "retry_after": 30,
    "alternatives": [
      {"id": "claude-sonnet-4-5", "status": "available", "tags": []},
      {"id": "gpt-4o", "status": "available", "tags": []}
    ],
    "hint": "All channels for 'claude-opus-4-6' are temporarily unavailable. Retry in 30s or try an alternative model."
  }
}

{
  "error": {
    "message": "Rate limit: 60 rpm exceeded",
    "type": "rate_limit_error",
    "code": "rate_limit_exceeded",
    "retryable": true,
    "retry_after": 8,
    "hint": "Rate limited. Retry after 8s. Current limit: 60/min for user role."
  }
}

{
  "error": {
    "message": "This model's maximum context length is 128000 tokens...",
    "type": "invalid_request_error",
    "code": "context_length_exceeded",
    "retryable": false,
    "suggestions": [
      {"id": "gemini-2.5-pro"},
      {"id": "claude-sonnet-4-5"}
    ],
    "hint": "Reduce your input or switch to a model with a larger context window."
  }
}

X-LemonData-Hint: This model supports native Anthropic format. Use POST /v1/messages for better performance (no format conversion).
X-LemonData-Native-Endpoint: /v1/messages

{
  "id": "gpt-4o",
  "lemondata": {
    "category": "chat",
    "pricing_unit": "per_token",
    "cache_pricing": {
      "cache_read_per_1m": "1.25",
      "cache_write_per_1m": "2.50",
      "platform_cache_discount": 0.9
    }
  }
}

GET /v1/models?category=chat          # Chat models only
GET /v1/models?category=image         # Image generation models
GET /v1/models?tag=coding&category=chat  # Coding-optimized chat models

GET https://api.lemondata.cc/llms.txt

from openai import OpenAI, BadRequestError

client = OpenAI(
    api_key="sk-your-key",
    base_url="https://api.lemondata.cc/v1"
)

def smart_chat(messages, model="gpt-4o"):
    try:
        return client.chat.completions.create(
            model=model, messages=messages
        )
    except BadRequestError as e:
        error = e.body.get("error", {}) if isinstance(e.body, dict) else {}
        # Use did_you_mean for auto-correction
        if error.get("code") == "model_not_found" and error.get("did_you_mean"):
            return client.chat.completions.create(
                model=error["did_you_mean"], messages=messages
            )
        raise

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-your-key',
  baseURL: 'https://api.lemondata.cc/v1'
});

async function smartChat(messages, model = 'gpt-4o') {
  try {
    return await client.chat.completions.create({ model, messages });
  } catch (error) {
    const err = error?.error;
    if (err?.code === 'model_not_found' && err?.did_you_mean) {
      return client.chat.completions.create({
        model: err.did_you_mean, messages
      });
    }
    throw error;
  }
}