WizardLM 2 8x22B

Microsoft

microsoft/wizardlm-2-8x22bOpen Weights

Microsoft WizardLM instruction-tuned Mixtral MoE for multilingual dialogue and complex tasks

Benchmark Pricing$0.49 / 1M in$0.49 / 1M out$0.25 cache read

Context: 65,536 tokens•Max Output: 8,000 tokens•Released: 2024-04-15

TECHNICAL SPECIFICATIONS

Context Window65,53665.5K tokens

Max Output8,0008K tokens

LicenseApache-2.0Self-hostable

Input Modalities

Text

Function / Tool CallingNot Supported

Structured OutputsPrompt Based

MODEL CONTEXT PROTOCOL (MCP) READINESS

⚠ WizardLM 2 8x22B does not natively advertise tool-calling capabilities. When connecting to MCP servers, function calling must be handled via structured prompt injection.

MCP Context Window Recommendations

With a context capacity of 65,536 tokens, this model can handle compact tool sets. Consider keeping MCP server tool manifests minimal to preserve headroom.

API CALL INVOCATION EXAMPLE

// Example: Calling WizardLM 2 8x22B via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.MICROSOFT_API_KEY,
});

const response = await client.chat.completions.create({
  model: "microsoft/wizardlm-2-8x22b",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);