[MCP Server] LLM Inference MCP - Multi-model routing, cost optimization

[zhaohongyuziranerran]

LLM Inference MCP Server

Multi-model LLM routing with cost optimization, structured output, and batch inference.

Features

• Smart model routing (8 task profiles)
• Multi-provider support (OpenAI, DeepSeek, Anthropic, vLLM)
• Structured JSON output from any model
• Batch inference (up to 50 parallel prompts)
• Token counting and cost estimation
• Side-by-side model comparison

Tools (7)

list_models, chat_completion, structured_output, batch_inference, count_tokens, estimate_inference_cost, compare_models

GitHub: https://github.com/zhaohongyuziranerran/llm-inference-mcp