Trinity Large Thinking API: toman pricing and code
arcee-ai/trinity-large-thinking
toolsreasoningYou are billed for the usage the request actually reported. Prices follow the market. Cached input: 17,408 toman / 1M.Pricing and top-ups
Trinity Large Thinking example: a multi-step problem with reasoning
The example is picked from this model's own capabilities. Drop in your key and it runs as is.
from openai import OpenAI
client = OpenAI(base_url="https://api.uttapen.ir/v1", api_key="sk-up-…")
resp = client.chat.completions.create(
model="arcee-ai/trinity-large-thinking",
messages=[{"role": "user", "content": (
"A shop has 3 warehouses. A ships 120 orders a day, B ships 85 and C ships 40. "
"If C closes and its load is split between A and B in proportion to their capacity, how many does each ship a day? "
"Work through it step by step and give just the two numbers at the end."
)}],
reasoning_effort="medium", # low | medium | high
)
print(resp.choices[0].message.content)
# reasoning tokens count as output tokens too:
print(resp.usage.completion_tokens_details)curl https://api.uttapen.ir/v1/chat/completions \
-H "Authorization: Bearer sk-up-…" \
-H "Content-Type: application/json" \
-d '{
"model": "arcee-ai/trinity-large-thinking",
"messages": [{"role": "user", "content": "120 and 85 daily orders split across two warehouses; work through it step by step."}],
"reasoning": {"effort": "medium"}
}'import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.uttapen.ir/v1", apiKey: "sk-up-…" });
const resp = await client.chat.completions.create({
model: "arcee-ai/trinity-large-thinking",
messages: [{ role: "user", content: "120 and 85 daily orders are split between two warehouses; work through it step by step and give just the two numbers at the end." }],
reasoning_effort: "medium",
});
console.log(resp.choices[0].message.content);
console.log(resp.usage.completion_tokens_details);What is Trinity Large Thinking good for?
Arcee publishes this model; we expose it under the id "arcee-ai/trinity-large-thinking". Its context window is 262,144 tokens, roughly 197k English words in one request. A single response can run to 80,000 tokens. On price it sits in the "cheap" band — cheaper than 120 and dearer than 286 of the other paid models in the catalogue.
What you get on top of text in, text out: it supports tool calling, so it can invoke your own functions with valid arguments; it has a reasoning mode that pays off on multi-step problems, maths and debugging. All of it works through the standard parameters of the official OpenAI SDK — no custom client, no wrapper. Keep in mind that reasoning tokens are output tokens and do appear on the bill.
Input runs at 72,531 toman per 1M tokens and output at 232,100 — output costs 3.2× input, so trimming the answer saves more than trimming the prompt. It supports cached input: repeated context is billed at 17,408 toman per 1M, which matters a lot if your system prompt is long. You are always charged for the usage the request actually reported, never for the estimate, and a failed request costs nothing.
The closest alternative with the same capabilities from a different provider is Qwen3 Coder Next: Trinity Large Thinking works out roughly 1.1× more expensive, and its context window is the same size. Both run on the same key and the same code, so trying the other one is a single string change.
To make the figure concrete: 100,000 toman of credit buys roughly 253 thousand-word requests on Trinity Large Thinking, and every 1,000 toman is about 2,525 words of round trip. A job with one million input tokens and one million output tokens comes to 304,631 toman in total. Filling this model's 262,144-token window costs 19,014 toman on the input side alone, which is the real reason to keep conversation history short.
Among the less common parameters it accepts top_k — all through the standard request body. It does not support response_format, seed, structured_outputs, which most models here do, so test before switching if your code relies on them. By context size the nearest option from another provider is Seed 1.6 at 262,144 tokens.
Where it makes sense: high-volume work such as classification, tagging and bulk summarising, logic puzzles and code review, agents that reach out to APIs and databases, analysing a long document or codebase in one request.
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...
Three real jobs, priced on this model
Each figure is derived from the prices above and moves when they do.
| Job | Tokens | Cost |
|---|---|---|
| One chat turn with a medium history | 1,500 in + 400 out | 202 toman |
| Summarising a ten-page document | 4,000 in + 600 out | 429 toman |
| Classifying a thousand short rows | 120,000 in + 20,000 out | 13,346 toman |
Frequently asked
- How do I call Trinity Large Thinking from Iran?
- Sign up with your mobile number, top the wallet up in toman, create an API key, then in the official OpenAI SDK point base_url at https://api.uttapen.ir/v1 and set model to "arcee-ai/trinity-large-thinking". Nothing else in your code changes.
- What does Trinity Large Thinking cost in toman?
- 72,531 toman per 1M input tokens and 232,100 toman per 1M output tokens; a 1,000-word request is around 396 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
- How much input does Trinity Large Thinking take?
- Up to 262,144 tokens per request, roughly 197k words. A single answer can reach 80,000 tokens.
- Does Trinity Large Thinking support streaming and tool calling?
- Streaming (stream=true) works on every model here. This one supports tool calling in the standard OpenAI shape.