Cydonia 24B V4.1

Thedrummer

thedrummer/cydonia-24b-v4.1Open Weights

Open-weight instruction model for adaptable chat and self-hosted production workloads

Benchmark Pricing$0.41 / 1M in$0.69 / 1M out$0.21 cache read

Context: 131,072 tokens•Max Output: 117,964 tokens•Knowledge: 2024-04-30•Released: 2025-09-27

TECHNICAL SPECIFICATIONS

Context Window131,072131.1K tokens

Max Output117,964118K tokens

LicenseOpen SourceSelf-hostable

Input Modalities

Text

Function / Tool CallingNot Supported

Structured OutputsPrompt Based

MODEL CONTEXT PROTOCOL (MCP) READINESS

⚠ Cydonia 24B V4.1 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 131,072 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

API CALL INVOCATION EXAMPLE

// Example: Calling Cydonia 24B V4.1 via OpenAI SDK
import OpenAI from "openai";

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

const response = await client.chat.completions.create({
  model: "thedrummer/cydonia-24b-v4.1",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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