arcee-ai/trinity-large-thinkingOpen WeightsReasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use
TECHNICAL SPECIFICATIONS
MODEL CONTEXT PROTOCOL (MCP) READINESS
✓ Trinity Large Thinking 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 524,288 tokens, this model can handle extremely large MCP resource manifests, complete database schemas, and multiple active server tool definitions simultaneously without degradation.
API CALL INVOCATION EXAMPLE
// Example: Calling Trinity Large Thinking via OpenAI SDK
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.ARCEE-AI_API_KEY,
});
const response = await client.chat.completions.create({
model: "arcee-ai/trinity-large-thinking",
messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});
console.log(response.choices[0].message.content);PRICING BY PROVIDER
Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.
This model supports prompt caching at $0.13 / 1M tokens, saving up to 50% on repetitive MCP tool definitions and system instructions.
MODEL RESOURCES
More Models by Arcee-ai
Alternative and family models from the same lab
Lightly post-trained 398B MoE chat model for creative work, long-context prompts, and tool-using agents
Reasoning-tuned 26B MoE model with 3B active parameters for agents, tools, and multi-step workloads
Experimental chat-tuned 6B MoE model with 1B active parameters for low-resource chat and instruction following