# GPT-5.2 Codex API prices

GPT-5.2 Codex (gpt-codex) — 400k context, 128k max output.
20 metered per-token offers from 20 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| QiHang | $0.14 | $1.14 | — | 400k |
| Ofox | $1.4 | $11.2 | $0.144 | 400k |
| Poe | $1.6 | $13 | $0.16 | 400k |
| Abacus | $1.75 | $14 | $0.175 | 400k |
| AIHubMix | $1.75 | $14 | $0.175 | 400k |
| Azure | $1.75 | $14 | $0.175 | 400k |
| Azure Cognitive Services | $1.75 | $14 | $0.175 | 400k |
| Eden AI | $1.75 | $14 | $0.175 | 272k |
| Impossibl | $1.75 | $14 | $0.175 | 400k |
| Jiekou.AI | $1.75 | $14 | — | 400k |
| Kilo Gateway | $1.75 | $14 | $0.175 | 400k |
| DevPass (LLM Gateway) | $1.75 | $14 | $0.175 | 400k |
| LLM Gateway | $1.75 | $14 | $0.175 | 400k |
| NanoGPT | $1.75 | $14 | $0.175 | 400k |
| OpenCode Zen | $1.75 | $14 | $0.175 | 400k |
| OpenRouter | $1.75 | $14 | $0.175 | 400k |
| OrcaRouter | $1.75 | $14 | $0.175 | 400k |
| Vercel AI Gateway | $1.75 | $14 | $0.175 | 400k |
| Vivgrid | $1.75 | $14 | $0.175 | 400k |
| ZenMux | $1.75 | $14 | $0.17 | 400k |

## Summary

- Cheapest input: $0.14 per 1M tokens (QiHang)
- Cheapest output: $1.14 per 1M tokens (QiHang)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-12-11
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-5.2 Codex API?

As of Oct 4, 2026, QiHang has the lowest GPT-5.2 Codex output price at $1.14 per 1M tokens, and QiHang has the lowest input price at $0.14 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer GPT-5.2 Codex?

20 providers list GPT-5.2 Codex on Sovyron; 20 of them sell it at a metered per-token price.

### Is GPT-5.2 Codex free?

No provider in the Sovyron catalog lists a free tier for GPT-5.2 Codex.

### What is the context window of GPT-5.2 Codex?

GPT-5.2 Codex supports a 400k-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/gpt-5-2-codex/
Full dataset: https://sovyron.com/data/catalog.json