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.

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.

API surfaces

The Vivgrid Console catalogs gpt-5.3-codex on one surface, all behind the same API key. The endpoint shown is the one the Console previews for that surface.

Quick start

Get an API key from the Vivgrid Console, then call gpt-5.3-codex directly.

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-6-astra — the gpt-6 generation flagship
• gpt-6.1-sol — the newer, Codex-capable gpt-6 model
• gpt-5.5 — flagship model on the Chat Completions API