arcee-ai/trinity-mini
Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with robust function...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Clarifaibf16 | $0.045 | $0.150 | 131K | — |
Trinity Mini costs $0.045 per million input tokens and $0.150 per million output tokens via OpenRouter, making it 13th cheapest of 298 paid models.
Trinity Mini generates around 172 tokens per second with 328ms time-to-first-token (p50), the 23rd fastest tracked model.
Trinity Mini supports a 131K-token context window and can output up to 131K tokens. It accepts text input.