gpt-5.1-codex-max — API, Pricing & Context Window | Vivgrid

gpt-5.1-codex-max is the extended-effort variant of OpenAI's Codex 5.1 line, tuned to push harder on difficult, long-horizon coding problems. It runs on the Responses API and is a good fit when you want maximum reasoning depth from the 5.1 Codex generation.

On Vivgrid it offers a 400K-token context window and geo-distributed acceleration across AMER and EMEA, balancing depth with responsive latency.

Specifications

Pricing

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

Quick start

Call gpt-5.1-codex-max 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-5.1-codex-max",
    "input": "Refactor this function and explain the change.",
    "stream": true
  }'

Ideal use cases

• Hard, multi-file engineering tasks needing extra reasoning effort
• Codex agents tackling complex debugging and architecture changes
• Long agent loops where thoroughness matters more than raw speed
• Responses-API tooling that wants the strongest 5.1 Codex option

Related models

• gpt-5.1-codex — the standard-effort 5.1 Codex model
• gpt-5.3-codex — newer Codex generation
• gpt-5.5 — flagship coding model