Trinity Large Thinking with Jev
Trinity Large Thinking is a model from Arcee AI, released 2026-04-01. It costs $0.250 per million input tokens and $0.800 per million output tokens, reads up to 262K tokens of context, and writes up to 80,000 tokens in one reply. Through llm11, set model to arcee-ai/trinity-large-thinking.
- Input price
- $0.250 / 1M
- Output price
- $0.800 / 1M
- Context window
- 262K tokens
- Max output
- 80K tokens
- Cached input
- $0.060 / 1M
- Released
- 2026-04-01
- Accepts
- text
- Intelligence index
- 10.8
Read from the provider's prompt cache
Artificial Analysis, via the catalogue
Read from the live catalogue and refreshed daily. At blended list price, 68% of the 332 priced models we can call cost more.
Using Trinity Large Thinking with Jev
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Trinity Large Thinking does the answering when Jev sends it work, or when you name it yourself. At list price Trinity Large Thinking falls in the llm11-fast band, but no pack routes to it because it does not advertise structured output, which the verification checks rely on. You can still pin it: pass arcee-ai/trinity-large-thinking as model and routing steps aside while verification still runs.
Jev is new, so we have not published results for Trinity Large Thinking with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.
What a request costs
List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.
| Request | Tokens in / out | One | A thousand |
|---|---|---|---|
| Short chat turn | 500 / 200 | $0.00028 | $0.285 |
| Question over retrieved documents | 4,000 / 500 | $0.00140 | $1.40 |
| Long document summary | 30,000 / 1,000 | $0.00830 | $8.30 |
Cheaper models to try
Nearest in price and below Trinity Large Thinking, each within a few points of it on the intelligence index.
| Model | Input / 1M | Output / 1M | Context | Index | Released |
|---|---|---|---|---|---|
| Qwen Qwen3.6 35B A3B | $0.150 | $1.00 | 262K | 18.2 | |
| Qwen Qwen3 Coder Next | $0.120 | $0.800 | 262K | 9.2 | |
| Mistral Mistral Small 4 | $0.150 | $0.600 | 262K | 11.3 | |
| OpenAI GPT-6 Luna | $0.100 | $0.500 | 1.05M | 37.3 |
Call it
Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.
python
from openai import OpenAI
client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")
res = client.chat.completions.create(
model="arcee-ai/trinity-large-thinking",
messages=[{"role": "user", "content": "Hello"}],
)Questions
- What is Trinity Large Thinking with Jev?
- Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Trinity Large Thinking does the answering when Jev sends it work, or when you name it yourself. At list price Trinity Large Thinking falls in the llm11-fast band, but no pack routes to it because it does not advertise structured output, which the verification checks rely on. You can still pin it: pass arcee-ai/trinity-large-thinking as model and routing steps aside while verification still runs. Routing decisions are made by Jev, TypeSafe AI's System One model.
- Is Trinity Large Thinking a System One model?
- No. Trinity Large Thinking answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
- How much does Trinity Large Thinking cost?
- $0.250 per million input tokens and $0.800 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00140, so a thousand of them is about $1.40. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the Trinity Large Thinking context window?
- 262,144 tokens, with up to 80,000 tokens in a single reply.
- Does Trinity Large Thinking support tool calling and structured output?
- The catalogue lists tool calling and reasoning controls, but it does not list structured output.
- Can I use Trinity Large Thinking through llm11?
- Yes. Set model to arcee-ai/trinity-large-thinking on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to Trinity Large Thinking?
- Routing decisions are made by Jev, TypeSafe AI's System One model. At list price Trinity Large Thinking falls in the llm11-fast band, but no pack routes to it because it does not advertise structured output, which the verification checks rely on. You can still pin it: pass arcee-ai/trinity-large-thinking as model and routing steps aside while verification still runs.
- What is a cheaper alternative to Trinity Large Thinking?
- Nearest in price and below it: Qwen Qwen3.6 35B A3B at $0.150 in and $1.00 out, Qwen Qwen3 Coder Next at $0.120 in and $0.800 out and Mistral Mistral Small 4 at $0.150 in and $0.600 out. Nearest in price and below Trinity Large Thinking, each within a few points of it on the intelligence index.