codex-auto-review vs gpt-6.1-terra
| codex-auto-review | gpt-6.1-terra | |
|---|---|---|
| Providers | OpenAI | OpenAI |
| Input $/M | $0.10 | $0.25 |
| Output $/M | $0.60 | $1.25 |
| Output multiplier | ×6.00 | ×5.00 |
| Context window | 1.05M tokens | 1.05M tokens |
| Intelligence index | — | — |
| Coding index | — | — |
What the numbers mean
codex-auto-review is roughly 2.5× cheaper on input than gpt-6.1-terra. If your workload passes the quality bar on the cheaper model, that gap compounds across every request; route to gpt-6.1-terra deliberately rather than by default.
Tags: codex-auto-review — Chat, Vision, Reasoning, Coding, 工具调用, Long context · gpt-6.1-terra — Chat, Vision, Reasoning, Coding, 工具调用, Long context
Code
from openai import OpenAI
client = OpenAI(base_url="https://starseaapi.com/v1", api_key="sk-...")
# codex-auto-review
client.chat.completions.create(model="codex-auto-review", messages=[{"role":"user","content":"Hi"}])
# gpt-6.1-terra
client.chat.completions.create(model="gpt-6.1-terra", messages=[{"role": "user", "content": "Hi"}])