Alphayellowish
Production-ready · India region · Asia/Kolkata

Codex CLI,
built for teams.

Production GPT-5.5 access for engineering teams. Per-employee keys with real-time budget controls, usage dashboards, and a drop-in OpenAI-compatible endpoint.

Already have a key? Sign in

Model lineup

Two frontier models.
One endpoint.

gpt-5.5 Frontier

OpenAI's most capable model. Best for complex reasoning, agentic flows, full-stack code generation, and long-context work.

Context window 1,050K tokens
Output max 128K tokens
Capabilities Vision · Tools · Reasoning
gpt-5.3-codex Codex-tuned

Specialized for code. Lower latency, tighter token economy, and stronger on multi-file refactors and CLI tool use.

Tuned for Codex CLI · IDE agents
Median latency ~1.1s
Best for Code generation & review

Why Alphayellowish

Made for teams
that ship code.

Hard budget caps

Set monthly budgets per employee. We enforce them at the gateway with 429 responses — no surprise overruns.

Real-time dashboards

Every engineer sees their own usage: tokens spent, requests today, hourly activity, cached savings — refreshed every 30 seconds.

Per-employee keys

One key per person. Revoke instantly when a teammate leaves. Audit who used what across your whole organization.

Prompt caching, free

Cached prompt prefixes are billed at $0. Repeated Codex sessions get dramatically cheaper after the first call.

Drop-in OpenAI API

Works with Codex CLI, Cursor, Claude Code, or any OpenAI-compatible client. Swap one URL — no code changes.

Bangalore-hosted

Edge in BLR1. Sub-100ms latency from anywhere in India. ISO-grade infrastructure with daily backups and 5-minute health probes.

What you get

Pick the tier that
matches your team.

All tiers include both gpt-5.5 and gpt-5.3-codex. Limits reset every 5 hours rolling.

Pro

Solo dev

For one developer · daily use

Token budget / 5h2.5M
Tokens / minute400K
Requests / minute300
Modelsgpt-5.5 + codex
Reset5h rolling
Validity30 days
Talk to us

Team

20× · popular

Engineering team

For multiple developers · sustained heavy use

Token budget / 5h10M
Tokens / minute1.6M
Requests / minute1,200
Modelsgpt-5.5 + codex
Reset5h rolling
Validity30 days
Talk to us

Custom pricing for larger teams. Get in touch for a quote.

60-second setup

From key to first call,
in under a minute.

01

Install Codex CLI

One command. Works on macOS, Linux, Windows (via WSL).

npm install -g @openai/codex
02

Point Codex at us

Single config file. Swap the base URL — keep everything else.

mkdir -p ~/.codex && cat > ~/.codex/config.toml <<EOF
model = "gpt-5.5"
model_provider = "alphayellowish"

[model_providers.alphayellowish]
name = "AlphaYellowish"
base_url = "https://app.alphayellowish.com/v1"
env_key = "AY_KEY"
wire_api = "responses"
EOF
03

Set your key and ship

Your key was emailed to you by your admin. Once exported, you're live.

export AY_KEY="sk-•••"
codex "write a hello world in python"

9K

msg/5h capacity

<5s

avg first token

99.9%

uptime target

5min

health probe cycle

Ready when your team is.

Alphayellowish is currently invite-only for select engineering teams. Email us to enroll your team.