Early access: features, availability, and pricing may change as Kyara Intelligence evolves.

Below baseline Reasoning

Arcee AI: Trinity Large Thinking

Large-scale open-weight MoE for creative writing and immersive roleplay adventures.

Model ID arcee-ai/trinity-large-thinking

Quick start

Drop this model into any OpenAI-compatible client by setting the base URL, your API key, and the model ID below.

curl https://api.kyara-intelligence.com/v1/chat/completions \
  -H "Authorization: Bearer $KYARA_INTELLIGENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "arcee-ai/trinity-large-thinking",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'

See the full API reference

Overview

Amane is powered by Arcee AI's Trinity-Large-Thinking, a large-scale open-weight 400B-parameter sparse MoE with 13B active parameters per token using 4-of-256 expert routing. Excels in creative writing, storytelling, roleplay, and character-driven dialogue with natural conversational flow. Features a 131,000 token context window and reflects Arcee's efficiency-first design philosophy. Perfect for immersive narratives and dynamic character interactions with permissive open-weight licensing.

Specifications

Context / Memory 📚 Standard · 131K tokens

Cost vs baseline Below baseline

Input

0.5x

Output

0.7x

Input

cr / M tokens

Output

15.3M

cr / M tokens

Multiples are relative to the catalog median; bars are scaled to the most expensive model.

Model ID

arcee-ai/trinity-large-thinking

Reasoning

Available

Status

Current

Upstream moderation

All models on Kyara Intelligence are accessed through their original API providers (Mistral, Z.AI/GLM, xAI, DeepSeek, and others). Each provider's content policies and moderation apply to all requests.

Kyara routes API calls without modifying inputs or outputs, and does not log prompt or response content. Users are responsible for complying with the relevant provider's terms of service in addition to Kyara's terms.