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

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

Pricing

Pricing in USD per 1M tokens, matching the provider's rates.

Quick start

Call gpt-5.2-codex through Vivgrid's unified, OpenAI-compatible endpoint. Get an API key from the Vivgrid Console.

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-5.3-codex — the newer Codex generation
• gpt-5.1-codex — earlier Codex variant
• gpt-5.4 — general coding model on Chat Completions