# gpt-5.2-codex — API, Pricing & Context Window | Vivgrid

> Source: https://vivgrid.com/docs/models/gpt-5.2-codex

gpt-5.2-codex on Vivgrid: a Codex-tuned coding model on the Responses API with a 400K context window, function calling, and regional acceleration.

`gpt-5.2-codex` is a Codex-tuned member of the GPT-5 family, built for agentic coding on OpenAI's **Responses API**. It is a dependable choice for software-engineering agents that read, edit, and test code in a loop.

Vivgrid serves `gpt-5.2-codex` with geo-distributed acceleration across **AMER and EMEA** and a **400K-token context window**, so it can hold substantial project context within a single session.

## Specifications

| Field | Value |
| --- | --- |
| Provider | OpenAI |
| Model ID | `gpt-5.2-codex` |
| Best for | Coding |
| Available on | Vibe coding |
| Context window | 400,000 tokens |
| Max output | 128,000 tokens |
| Modalities | Text, Image |
| Tool / function calling | Yes |
| Knowledge cutoff | 2025-08 |
| Acceleration | Geo-distributed — AMER, EMEA |

## Pricing

Pricing in USD per 1M tokens.

| Input | Cached input | Output |
| --- | --- | --- |
| $1.75 | $0.175 | $14.00 |

### What one request costs

The rates above applied to a 20K-token prompt with a 2K-token reply — a typical single agent turn, small enough that every request is billed at the base rate.

| Request | Cost |
| --- | --- |
| Cold prompt, nothing cached | $0.0630 |
| Warm prompt, 90% of the input served from cache | $0.0347 |


## API surfaces

The Vivgrid Console catalogs `gpt-5.2-codex` on one surface, all behind the same API key. The endpoint shown is the one the Console previews for that surface.

| Surface | Primary endpoint | Use it for |
| --- | --- | --- |
| Vibe coding | `/responses` | Coding CLIs and IDE agents that drive the model themselves — point the tool at Vivgrid and keep your own loop. |

## Quick start

Get an API key from the Vivgrid Console (https://console.vivgrid.com), then call `gpt-5.2-codex` directly.

```bash
curl https://api.vivgrid.com/v1/responses \
  -H "Authorization: Bearer $VIVGRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.2-codex",
    "input": "Refactor this function and explain the change.",
    "stream": true
  }'
```


## Ideal use cases

- Codex and Responses-API coding assistants
- Automated refactoring, test generation, and bug fixing
- Tool-calling agents that orchestrate shell and editor actions
- Cost-aware coding workloads that don't need the latest Codex release

## Related models

- [gpt-6-astra](/docs/models/gpt-6-astra) — the gpt-6 generation flagship
- [gpt-5.3-codex](/docs/models/gpt-5.3-codex) — the newer Codex generation
- [gpt-6.1-sol](/docs/models/gpt-6.1-sol) — the balanced gpt-6 coding model