GPT-5.2 Codex
GPT-5.2 Codex is served by 2 providers that kRouter can route to, with a 400K-token context window and pricing from $5.00 per 1M input tokens. Because more than one provider offers it, the price you pay depends on which one you route to — the same request, the same model, different bills.
Where to get GPT-5.2 Codex
| Provider | Route as |
|---|---|
| GitHub Copilot | gh/gpt-5.2-codex |
| Cursor IDE | cu/gpt-5.2-codex |
What GPT-5.2 Codex is suited for
A 400K window is large enough to hold a substantial part of a codebase in one turn, so it suits whole-repo refactors and long agent sessions where the history keeps growing. It supports extended reasoning, which helps on debugging and multi-step planning but spends output tokens on thinking before the answer appears — worth knowing when you set max_tokens. Tool and function calling are supported, so it can drive an agent loop. Cached input is billed at $2.50 against $5.00 fresh, which is the difference that matters most for agent work — the same context is resent on every turn.
Specs
- Context window
- 400K
- Max output
- 128K
- Input / 1M
- $5.00
- Output / 1M
- $20.00
- Extended reasoning
- Tool / function calling
Cheaper alternatives to GPT-5.2 Codex
Comparable capabilities at a lower rate. With a kRouter combo you can send routine turns to one of these and reserve GPT-5.2 Codex for the work that actually needs it.
- GPT-5.1$4.00 in · $16.00 out per 1M
- GPT 5.3 Codex (Low)$4.00 in · $16.00 out per 1M
- Claude Sonnet 4.6$3.00 in · $15.00 out per 1M
- Claude Sonnet 4.5$3.00 in · $15.00 out per 1M
GPT-5.2 Codex FAQ
How much does GPT-5.2 Codex cost?
GPT-5.2 Codex is $5.00 per 1M input tokens and $20.00 per 1M output tokens. Cached input is $2.50, which matters a lot for agent work that resends the same context each turn.
Which providers serve GPT-5.2 Codex?
2 providers: GitHub Copilot, Cursor IDE. Through kRouter you can switch between them by changing the route prefix, without changing your tool.
What is GPT-5.2 Codex's context window?
400K tokens, with up to 128K tokens of output. kRouter publishes this on /v1/models as context_length, so clients read the real number instead of guessing from the model name.
Is there a cheaper alternative to GPT-5.2 Codex?
Yes — GPT-5.1 ($4.00/1M in), GPT 5.3 Codex (Low) ($4.00/1M in), Claude Sonnet 4.6 ($3.00/1M in), Claude Sonnet 4.5 ($3.00/1M in) are cheaper with comparable capabilities. A kRouter combo can send routine turns to one of those and keep GPT-5.2 Codex for the work that needs it.
Route to GPT-5.2 Codex from any tool
kRouter runs locally and gives Claude Code, Cursor, Codex and the rest one endpoint that reaches every provider above — with automatic failover. Free and MIT-licensed.
Install kRouter