Arcee AI: Trinity Large Thinking: AI model
Trinity Large Thinking is an open reasoning model optimized for agentic workloads from Arcee AI. Reachable from inside Iran through Hormouz.
- Context window:
- 262,144 tokens
- Input:
- $0.25/1M tokens
- Output:
- $0.8/1M tokens
- Type:
- text
- Tools
- Streaming
- Long context
Thinking levels: Always thinks
Trinity Large Thinking is an open-source reasoning model from Arcee AI, built for agentic workloads with a large 256K-token context. It shows strong results on agentic and reasoning tasks and is designed to work best when its reasoning is preserved across turns (interleaved thinking). It supports tool calling, making it a fit for multi-step agents and long analytical sessions.
Trinity Large Thinking is a good fit for agentic reasoning, multi-step tool use and long analytical tasks. It supports tool (function) calling and explicit reasoning. The model works with a context window of about 262K tokens, so it comfortably handles long inputs. It is served through Hormouz behind an OpenAI-compatible API. Just point your base URL at Hormouz and drop in a Hormouz key, and existing OpenAI SDK code runs unchanged.
Pricing is usage-based: $0.25 per million input tokens and $0.8 per million output tokens, billed only for what you use. Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.
Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7...
Quickstart
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "arcee-ai/trinity-large-thinking",
"messages": [{"role": "user", "content": "Hello!"}]
}'Specs
| Vendor | Arcee AI |
|---|---|
| Type | Text |
| Context window | 262,144 tokens |
| Pricing | $0.25/M in · $0.80/M out |
| API | Chat Completions |
| Capabilities | Streaming · Tools |
Benchmarks
Reasoning
Coding
Agentic
Source: Artificial Analysis
Design Arena
How Design Arena works ↗Metrics sourced from Design Arena
Code example
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "arcee-ai/trinity-large-thinking",
"messages": [{"role": "user", "content": "Hello!"}]
}'from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
model="arcee-ai/trinity-large-thinking",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
model: "arcee-ai/trinity-large-thinking",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Buy the Arcee AI: Trinity Large Thinking API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches Arcee AI: Trinity Large Thinking and 600+ other models, and you pay only for what you use.
- No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Use via Hormouz
Connect to this model and 600+ others with one API key, then see usage down to each request.
Request company accessFAQ
- How much does Trinity Large Thinking cost?
- Billing is usage-based: $0.25 per million input tokens and $0.8 per million output tokens. There is no fixed monthly fee. You pay only for what you use.
- How do I access Trinity Large Thinking from inside Iran?
- Create a Hormouz account and generate an API key. Hormouz provides a stable path to the model from inside Iran, with no foreign credit card or circumvention tooling required.
- Is Trinity Large Thinking compatible with OpenAI code?
- Yes. Hormouz exposes an OpenAI-compatible API. Change the base URL to Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.
- What context window and capabilities does Trinity Large Thinking have?
- Trinity Large Thinking works with a context window of about 262K tokens. It also supports tool calling, can produce explicit reasoning. That makes it suitable for agentic reasoning, multi-step tool use and long analytical tasks.
- What is Trinity Large Thinking good for?
- It is best suited to agentic reasoning, multi-step tool use and long analytical tasks.
- Which provider serves Trinity Large Thinking on Hormouz?
- Hormouz is the provider you connect to and bill through. It routes your request to the model and handles access, billing and stable connectivity from inside Iran on your behalf.
Updated 2026-10-13