Skip to content
ShilpBot
AI Models

Motif Technologies Motif 3: Pricing, Specs and Limits

Motif Technologies Motif 3: mixture-of-experts multilingual model for English and Korean, 262K context, 0.30 in / 1.20 out per 1M tokens. Specs, limits...

By ShilpBot Team · Published · 3 min read

Motif 3 is a mixture-of-experts language model from Motif Technologies with 314 billion total and 13.2 billion active parameters. The listing calls it a general-purpose multilingual model for English and Korean.

If you serve Korean-speaking users, that focus is the main reason to evaluate it. Priced at $0.30 per million input tokens and $1.20 per million output tokens, it is mid-range.

Prices and specifications checked against the public OpenRouter catalogue on 2026-11-16. See the live model page for current limits.

Motif Technologies Motif 3 quick facts

DetailValue
DeveloperMotif Technologies
Model IDmotif-technologies/motif-3
Added to the catalogue2026-11-02
TypeMixture-of-experts multilingual model for English and Korean
Parameters13.2B active / 314B total
Context window262K tokens (262,144)
Maximum output235,929 tokens
Input typestext
Price0.30 in / 1.20 out per 1M tokens (cached input 0.060)

Feature support from the catalogue: Tool calling: listed; JSON / structured output: listed; Reasoning: supported, effort not adjustable.

What Motif Technologies Motif 3 is good for

  • English and Korean tasks, such as bilingual support or translation checks.
  • General-purpose text work at moderate cost.
  • Long outputs, with a 235,929-token cap.

Limits of Motif Technologies Motif 3

  • Text only, with no adjustable reasoning effort.
  • Other languages are not highlighted, so test any you need.
  • 262K context is smaller than the 1M-token models.

How Motif Technologies Motif 3 compares

  • KT Mi:dm K 3.0 Pro: It has a larger context window (262,144 against 261,795 tokens); its output cap is 235,929 tokens against 235,615; it activates 13.2B parameters per token against 12B; it costs 0.30 input and 1.20 output per million tokens against 0.20 and 0.80.
  • Mistral Large 4: It has a smaller context window (262,144 against 1,048,576 tokens); its output cap is 235,929 tokens against 262,144; it does not accept image input; it costs 0.30 input and 1.20 output per million tokens against 0.70 and 2.10.
  • inclusionAI Ling 3.1 Flash: It has a smaller context window (262,144 against 1,000,000 tokens); its output cap is 235,929 tokens against 262,144; it activates 13.2B parameters per token against 25B; it costs 0.30 input and 1.20 output per million tokens against 0.045 and 0.14.

Calling Motif Technologies Motif 3 from code

Use the model ID motif-technologies/motif-3 with any OpenAI-compatible client pointed at OpenRouter:

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "motif-technologies/motif-3", "messages": [{"role": "user", "content": "Explain what you can do in two sentences."}]}'

Prompts that show what Motif Technologies Motif 3 can do

  1. Translate a short business email between Korean and English and have a native speaker check it.
  2. Ask for a summary of a Korean news article in English.
  3. Compare it with Mi:dm K 3.0 Pro on a Korean prompt.

What Motif Technologies Motif 3 costs

The catalogue lists 0.30 per million input tokens and 1.20 per million output tokens, with cached input at 0.060 per million. Sending 1 million input tokens and receiving 100,000 output tokens would cost about 0.42. A single coding-agent step with a 150,000-token prompt and a 10,000-token answer would cost about $0.057 before caching. If your client reuses the same prompt prefix, cached input at 0.060 per million tokens can cut the input side of that bill by about 80 percent. Prices are set by the provider, can change, and may differ between hosting providers, so check the live model page before you budget.

Keep reading

Compare every paid model by price in our AI model pricing roundup, or see the free models roundup. New to terms like mixture-of-experts? Start with how neural networks learn.

Frequently asked questions

Which languages is Motif 3 designed for?

The listing describes it as a general-purpose multilingual model for English and Korean.

What are the cost and limits of Motif Technologies Motif 3?

As of 2026-11-16 the catalogue lists 0.30 per million input tokens and 1.20 per million output tokens. 262K tokens (262,144) context window, up to 235,929 output tokens, model ID motif-technologies/motif-3. Prices can change, so check the live model page.

#Motif Technologies Motif 3#Motif Technologies model#AI model pricing#AI API pricing#AI chat model#multilingual model#OpenRouter