Model comparison
Coder Large vs Trinity Large Preview
Compare Coder Large and Trinity Large Preview: input/output $/Mtoken, context window, modalities, and license. OpenRouter-synced pricing.
Arcee Ai
Coder Large
Coder‑Large is a 32 B‑parameter offspring of Qwen 2.5‑Instruct that has been further trained on permissively‑licensed GitHub, CodeSearchNet and synthetic bug‑fix corpora. It suppor
Arcee Ai
Trinity Large Preview
Flagship model for demanding analysis, coding, and production agent workflows
| Metric | Coder Large | Trinity Large Preview |
|---|---|---|
| Provider | Arcee Ai | Arcee Ai |
| Context window | 32,768 | 131,000 |
| Input $/Mtok | $0.500 | $0.250 |
| Output $/Mtok | $0.800 | $1.00 |
| Modalities | text | text |
| License | closed | closed |
Quick take
On input price, Trinity Large Preview is cheaper at $0.250/Mtok. For context window, Trinity Large Preview leads with 131,000 tokens.
Pick based on your workload: high-volume cheap inference vs long-document / agent loops. Enterprise DNA can wire either model into Omni with evals, secrets, and job orchestration.