gpt-5.1-codex-max — API, Pricing & Context Window | Vivgrid
gpt-5.1-codex-max — API, Pricing & Context Window
gpt-5.1-codex-max on Vivgrid: an extended-effort Codex coding model on the Responses API with a 400K context window and geo-distributed acceleration.
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
| Provider | OpenAI |
| Model ID | gpt-5.1-codex-max |
| Best for | Coding |
| Context window | 400,000 tokens |
| Max output | 128,000 tokens |
| Modalities | Text, Image |
| Tool / function calling | Yes |
| Knowledge cutoff | 2024-09 |
| Acceleration | ⚡ Geo-Distributed — AMER, EMEA |
Pricing
Pricing in USD per 1M tokens, matching the provider's rates.
| Input | Cached input | Output |
|---|---|---|
| $1.25 | $0.125 | $10.00 |
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
[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.](/content/docs/models/gpt-5.2-codex/index.html) [gpt-5.1-codex \
gpt-5.1-codex on Vivgrid: a Codex-tuned coding model on the Responses API with a 400K context window and three-region geo-distributed acceleration.](/content/docs/models/gpt-5.1-codex/index.html)