Question 1

What is Trinity Large Thinking?

Accepted Answer

Trinity Large Thinking is a model from Arcee AI, released on Apr 1, 2026. 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 This model is optimized for agentic workflows and performs best when reasoning is preserved (aka interleaved thinking). Learn how to preserve reasoning in our docs: https://openrouter.ai/docs/guides/best-practices/reasoning-tokens#preserving-reasoning.

Question 2

How much does Trinity Large Thinking cost?

Accepted Answer

On the Respan gateway, input starts at $0.25 per 1M tokens on OpenRouter, and output starts at $0.80 per 1M tokens on OpenRouter, after gateway discounts.

Question 3

Which providers serve Trinity Large Thinking on Respan?

Accepted Answer

Trinity Large Thinking is served by OpenRouter.

Question 4

What is Trinity Large Thinking's context window?

Accepted Answer

Trinity Large Thinking accepts up to 262K tokens of context.

Question 5

How do I use Trinity Large Thinking with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "trinity-large-thinking". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Trinity Large Thinking?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 118 tokens per second, and the lowest response latency was 0.6 seconds on OpenRouter. Speed varies with request size and provider.

Trinity Large Thinking

Providers

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Apps

Certified where it counts.