Skip to content
Alpha
  • Models
  • Rankings
  • Ori
Talk to sales

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Ori
  • Labs
  • Pricing
  • Business
  • Enterprise

Explore

  • Rankings
  • Models
  • Apps
  • Providers
  • Benchmarks
  • Tools
  • Discover
  • Works With OR

Company

  • About
  • Blog
  • Customers
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
  1. Home
  2. /
  3. Compare

Trinity Large Preview vs GPT-5.2-Codex

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.

Favicon for arcee-ai
Trinity Large Preview
Favicon for openai
GPT-5.2-Codex
Favicon for arcee-ai
Trinity Large Preview
Favicon for openai
GPT-5.2-Codex

Overview

Trinity Large Preview
Author
arcee-ai
GPT-5.2-Codex
Author
OpenAI
Trinity Large Preview
Context length
131Ktokens
GPT-5.2-Codex
Context length
400Ktokens
Trinity Large Preview
Reasoning
GPT-5.2-Codex
Reasoning
Trinity Large Preview
Input modalities
GPT-5.2-Codex
Input modalities
Trinity Large Preview
Output modalities
GPT-5.2-Codex
Output modalities

Analysis

Trinity Large Preview vs GPT-5.2-Codex at a glance

Trinity Large Preview
Input price
Pricing varies by provider
GPT-5.2-Codex
Input price
$1.75/M tokens
Trinity Large Preview
Output price
Pricing varies by provider
GPT-5.2-Codex
Output price
$14/M tokens
Trinity Large Preview
Context window
131,000 tokens
GPT-5.2-Codex
Context window
400,000 tokens
Trinity Large Preview
Intelligence Index
Not available
GPT-5.2-Codex
Intelligence Index
Not available
Trinity Large Preview
Coding Index
Not available
GPT-5.2-Codex
Coding Index
Not available
Trinity Large Preview
Agentic Index
Not available
GPT-5.2-Codex
Agentic Index
Not available
Trinity Large Preview
Latency (p50)
Not available
GPT-5.2-Codex
Latency (p50)
2.04 s
Trinity Large Preview
Throughput (p50)
Not available
GPT-5.2-Codex
Throughput (p50)
42.0 tok/s
Trinity Large Preview
Provided by
arcee-ai
GPT-5.2-Codex
Provided by
OpenAI
Trinity Large Preview
Model page
Trinity Large Preview model details, providers and pricing
GPT-5.2-Codex
Model page
GPT-5.2-Codex model details, providers and pricing
Trinity Large Preview vs GPT-5.2-Codex comparison
AttributeTrinity Large PreviewGPT-5.2-Codex
Input pricePricing varies by provider$1.75/M tokens
Output pricePricing varies by provider$14/M tokens
Context window131,000 tokens400,000 tokens
Intelligence IndexNot availableNot available
Coding IndexNot availableNot available
Agentic IndexNot availableNot available
Latency (p50)Not available2.04 s
Throughput (p50)Not available42.0 tok/s
Provided byarcee-aiOpenAI
Model pageTrinity Large Preview model details, providers and pricingGPT-5.2-Codex model details, providers and pricing

Benchmark data updated Oct 28, 2026

Frequently asked questions

Which has the longer context window, Trinity Large Preview or GPT-5.2-Codex?

GPT-5.2-Codex has the longer context window at 400,000 tokens, compared with 131,000 tokens for Trinity Large Preview.