OpenAI: GPT-5.2 Codex
Code-specialist GPT for repository edits, reviews, and long-running software agents
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| tokenstatopenai/gpt-5.2-codex | OpenAI | $1.75 | $14 | $0.175 | 400K |
| models.devcheapestgpt-5.2-codex | QiHang | $0.14 | $1.14 | $0 | 400K |
| models.devopenai/gpt-5.2-codex | Poe | $1.60 | $13 | $0.16 | 400K |
| models.devopenai/gpt-5.2-codex | Impossibl | $1.75 | $14 | $0.175 | 400K |
| models.devopenai/gpt-5.2-codex | Kilo Gateway | $1.75 | $14 | $0.175 | 400K |
| models.devopenai/gpt-5.2-codex | NanoGPT | $1.75 | $14 | $0.175 | 400K |
| models.devopenai/gpt-5.2-codex | Ofox | $1.75 | $14 | $0.18 | 400K |
| OpenRouteropenai/gpt-5.2-codex | OpenRouter | $1.75 | $14 | $0.175 | 400K |
| models.devopenai/gpt-5.2-codex | OrcaRouter | $1.75 | $14 | $0.175 | 400K |
| models.devopenai/gpt-5.2-codex | Vercel AI Gateway | $1.75 | $14 | $0.175 | 400K |
| models.devopenai/gpt-5.2-codex | ZenMux | $1.75 | $14 | $0.175 | 400K |
| models.devgpt-5.2-codex | Abacus | $1.75 | $14 | $0.175 | 400K |
| models.devgpt-5.2-codex | AIHubMix | $1.75 | $14 | $0.175 | 400K |
| models.devgpt-5.2-codex | Azure | $1.75 | $14 | $0.175 | 400K |
| models.devgpt-5.2-codex | Azure | $1.75 | $14 | $0.175 | 400K |
| models.devazure/gpt-5.2-codex | Eden AI | $1.75 | $14 | $0.175 | 272K |
| models.devgpt-5.2-codex | Jiekou.AI | $1.75 | $14 | $0.175 | 400K |
| models.devazure/gpt-5.2-codex | LLM Gateway | $1.75 | $14 | $0.175 | 400K |
| models.devgpt-5.2-codex | DevPass (LLM Gateway) | $1.75 | $14 | $0.175 | 400K |
| models.devgpt-5.2-codex | OpenCode | $1.75 | $14 | $0.175 | 400K |
| models.devgpt-5.2-codex | Vivgrid | $1.75 | $14 | $0.175 | 400K |
| LiteLLMopenai/gpt-5.2-codex | N/A | $1.75 | $14 | $0.175 | N/A |
| LiteLLMgpt-5.2-codex | N/A | $1.75 | $14 | $0.175 | N/A |
| LiteLLMazure/eu/gpt-5.2-codex | N/A | $1.93 | $15.40 | $0.1925 | N/A |
| LiteLLMeu/gpt-5.2-codex | N/A | $1.93 | $15.40 | $0.1925 | N/A |
| LiteLLMus/gpt-5.2-codex | N/A | $1.93 | $15.40 | $0.1925 | N/A |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- In: text
- In: image
- In: pdf
- Out: text
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
- AA intelligence28.5i
- AA coding0i
- AA agentic0i
- Terminal-Bench 2.064i
- SWE-Bench Pro56.4i
- OSWorld-Verified38.2i
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.