Motif 3

Motif-technologiesMCP Tool CallReasoning
motif-technologies/motif-3Open Weights

Motif 3 is a large-scale, decoder-only Mixture-of-Experts (MoE) language model with 314 billion total parameters and 13.2 billion parameters activated per token.

Benchmark Pricing$0.50 / 1M in$2.00 / 1M out$0.20 cache read
Context: 262,144 tokens•Max Output: 262,144 tokens•Released: 2026-08-07

TECHNICAL SPECIFICATIONS

Context Window262,144262.1K tokens
Max Output262,144262.1K tokens
LicenseMITSelf-hostable
Input Modalities
Text
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Motif 3 natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 262,144 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

API CALL INVOCATION EXAMPLE

// Example: Calling Motif 3 via OpenAI SDK
import OpenAI from "openai";

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

const response = await client.chat.completions.create({
  model: "motif-technologies/motif-3",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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

PRICING BY PROVIDER

1 providers
ai&motif-technologies/motif-3
$0.50 / $2.00$0.20 cache

Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.

Prompt Caching Active

This model supports prompt caching at $0.20 / 1M tokens, saving up to 60% on repetitive MCP tool definitions and system instructions.

MODEL RESOURCES

View Motif-technologies HubHugging Face Weights