Compare Trinity Large Preview from arcee-ai and GPT-5.2-Codex from OpenAI on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.
| Attribute | Trinity Large Preview | GPT-5.2-Codex |
|---|---|---|
| Input price | Pricing varies by provider | $1.75/M tokens |
| Output price | Pricing varies by provider | $14/M tokens |
| Context window | 131,000 tokens | 400,000 tokens |
| Intelligence Index | Not available | Not available |
| Coding Index | Not available | Not available |
| Agentic Index | Not available | Not available |
| Latency (p50) | Not available | 2.04 s |
| Throughput (p50) | Not available | 42.0 tok/s |
| Provided by | arcee-ai | OpenAI |
| Model page | Trinity Large Preview model details, providers and pricing | GPT-5.2-Codex model details, providers and pricing |
Benchmark data updated
GPT-5.2-Codex has the longer context window at 400,000 tokens, compared with 131,000 tokens for Trinity Large Preview.