Arcee-ai model
Trinity Large Thinking API cost calculator
Trinity Large Thinking costs $0.25 per 1M input tokens and $0.80 per 1M output tokens on the Arcee-ai API, with a 262K-token context window. A typical request (2K input, 500 output tokens) costs $0.0009 — about $27.00/month at 1,000 requests per day. Use the calculator below to model your exact workload.
Find me a cheaper modelWhat real workloads cost on Trinity Large Thinking
| Workload | Tokens (in / out) | Per request | Per 1K requests |
|---|---|---|---|
| Chatbot message | 500 / 300 | $0.0004 | $0.36 |
| RAG query with context | 4,000 / 500 | $0.0014 | $1.40 |
| Document summarization | 20,000 / 1,000 | $0.0058 | $5.80 |
| Agent coding session | 100,000 / 5,000 | $0.03 | $29.00 |
Frequently asked questions
How much does Trinity Large Thinking cost per 1M tokens?
According to current pricing data, Trinity Large Thinking costs $0.25 per 1M input tokens and $0.80 per 1M output tokens. Processing 1M tokens each way costs $1.05.
What does a typical API request to Trinity Large Thinking cost?
A typical request with 2,000 input tokens and 500 output tokens costs $0.0009. At 1,000 requests per day that is $0.90 daily, or about $27.00 per month.
What is Trinity Large Thinking's context window?
Trinity Large Thinking supports a 262K-token context window (262,144 tokens).
Does Trinity Large Thinking support prompt caching?
Yes. Cached input tokens cost $0.06 per 1M — a 76% discount versus the standard input rate, which matters for agents and chat apps that resend the same system prompt.
What is a cheaper alternative to Trinity Large Thinking?
Granite 4.0 Micro from Ibm-granite is currently the cheapest comparable option at $0.02 per 1M input tokens versus $0.25 for Trinity Large Thinking — roughly 15x cheaper on input.
Compare all current prices on the live model pricing dashboard, see Trinity Large Thinking vs Granite 4.0 Micro pricing, or run Trinity Large Thinking head-to-head against other models in the side-by-side comparison playground.
Pricing data via the OpenRouter models API.