gpt-5.3-codex — API, Pricing & Context Window | Vivgrid

gpt-5.3-codex is OpenAI's Codex-optimized coding model, tuned for agentic software engineering: editing files, running tools, and iterating in a loop. It is served on the Responses API (/responses), the surface that Codex and similar coding CLIs expect.

With a 400K-token context window and geo-distributed acceleration across AMER and EMEA, it delivers low-latency, long-horizon coding sessions on Vivgrid through a single API key.

Specifications

Pricing

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

Quick start

Call gpt-5.3-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-5.3-codex",
    "input": "Refactor this function and explain the change.",
    "stream": true
  }'

Ideal use cases

• Codex CLI and other Responses-API coding agents
• Iterative, tool-driven software engineering tasks
• Repository-scale edits within a 400K-token budget
• Pipelines that benefit from streamed, incremental output

Related models

• gpt-5.2-codex — the prior Codex generation
• gpt-5.1-codex-max — extended-effort Codex variant
• gpt-5.5 — flagship model on the Chat Completions API