Trinity-Large-Preview is a frontier-scale open-weight language model from Arcee, built as a 400B-parameter sparse Mixture-of-Experts with 13B active parameters per token using 4-of-256 expert routing. It excels in creative writing, storyt…
Model details →Arcee AI: Trinity Large Preview (free) vs meta-llama/Llama-3.1-8B-Instruct
Arcee AI: Trinity Large Preview (free) wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...
Model details →Side-by-side comparison
| Capability | Arcee AI: Trinity Large Preview (free) | meta-llama/Llama-3.1-8B-Instruct | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 131K | 131K | 🏆 meta-llama/Llama-3.1-8B-Instruct |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.00 | $0.05 | 🏆 Arcee AI: Trinity Large Preview (free) |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.00 | $0.08 | 🏆 Arcee AI: Trinity Large Preview (free) |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | Yes | Tie |
| Vision input Accepts image inputs alongside text. | — | — | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | — | Tie |
Frequently asked questions
Is Arcee AI: Trinity Large Preview (free) better than meta-llama/Llama-3.1-8B-Instruct?
Arcee AI: Trinity Large Preview (free) wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Arcee AI: Trinity Large Preview (free) and meta-llama/Llama-3.1-8B-Instruct?
Input: $0.00 vs $0.05 per 1M tokens. Output: $0.00 vs $0.08 per 1M tokens.
What context windows do Arcee AI: Trinity Large Preview (free) and meta-llama/Llama-3.1-8B-Instruct support?
Arcee AI: Trinity Large Preview (free) supports up to 131K tokens. meta-llama/Llama-3.1-8B-Instruct supports up to 131K tokens.
Do both Arcee AI: Trinity Large Preview (free) and meta-llama/Llama-3.1-8B-Instruct support tool calling?
Arcee AI: Trinity Large Preview (free): yes. meta-llama/Llama-3.1-8B-Instruct: yes.