docs: Fix AI model list in FAQ - correct supported models

Fixed incorrect information about supported AI models:
Before (Incorrect):
- Listed OpenAI GPT-4 and Claude as directly supported
- These are NOT natively supported
After (Correct):
- DeepSeek (native support, recommended)
- Qwen (native support, Alibaba Cloud)
- Custom OpenAI-compatible APIs (can use OpenAI, Claude via proxy, etc.)
Also updated cost estimates to reflect actual supported models.
Reference: mcp/client.go shows only DeepSeek, Qwen, and Custom providers.
Co-Authored-By: tinkle-community <tinklefund@gmail.com>

docs/guides/faq.en.md

@@ -129,16 +129,17 @@ docker compose up -d
 ## AI & Model Questions
 
 ### Which AI models are supported?
-- DeepSeek (recommended for cost/performance)
-- OpenAI GPT-4
-- Claude (Anthropic)
-- Custom models via API
+- **DeepSeek** (recommended for cost/performance)
+- **Qwen** (Alibaba Cloud Tongyi Qianwen)
+- **Custom OpenAI-compatible APIs** (can be used for OpenAI, Claude via proxy, or other providers)
 
 ### How much do API calls cost?
 Depends on your model and decision frequency:
 - **DeepSeek**: ~$0.10-0.50 per day (1 trader, 5min intervals)
-- **GPT-4**: ~$2-5 per day
-- **Claude**: ~$1-3 per day
+- **Qwen**: ~$0.20-0.80 per day
+- **Custom API** (e.g., OpenAI GPT-4): ~$2-5 per day
+
+*Estimates based on typical usage. Actual costs vary by provider and usage.*
 
 ### Can I use multiple AI models?
 Yes! Each trader can use a different AI model. You can even A/B test different models.

docs/guides/faq.zh-CN.md

@@ -129,16 +129,17 @@ docker compose up -d
 ## AI 与模型问题
 
 ### 支持哪些 AI 模型？
-- DeepSeek（推荐性价比）
-- OpenAI GPT-4
-- Claude（Anthropic）
-- 通过 API 的自定义模型
+- **DeepSeek**（推荐性价比）
+- **Qwen**（阿里云通义千问）
+- **自定义 OpenAI 兼容 API**（可用于 OpenAI、通过代理的 Claude 或其他提供商）
 
 ### API 调用成本是多少？
 取决于您的模型和决策频率：
 - **DeepSeek**：每天约 $0.10-0.50（1 个交易员，5 分钟间隔）
-- **GPT-4**：每天约 $2-5
-- **Claude**：每天约 $1-3
+- **Qwen**：每天约 $0.20-0.80
+- **自定义 API**（例如 OpenAI GPT-4）：每天约 $2-5
+
+*基于典型使用的估算。实际成本因提供商和使用量而异。*
 
 ### 可以使用多个 AI 模型吗？
 可以！每个交易员可以使用不同的 AI 模型。您甚至可以 A/B 测试不同模型。