Built for Cline.
In any IDE.

An OpenAI-compatible LLM service for the Codex family. Drop it into Cline, Cursor, Continue.dev, or any client that speaks /v1/chat/completions. No SDK changes, no migration.

~/projects/your-app — zsh
$ curl -X POST https://clinecodex.com/oai-chatgpt/v1/chat/completions \ -H "Authorization: Bearer ***" \ -H "Content-Type: application/json" \ -d '{ "model": "codex-5.5", "messages": [...] }' → 200 OK · 312ms · finish_reason: tool_calls
Browse models → View API docs
// models

The catalog

Every model routes to the Codex backend. Pick by capability, not by API.

⌕
all
codex
stable
legacy
model capabilities context
codex-5.5
provider: codex · tier: flagship
tools code fast
128k
codex-5.2
provider: codex · tier: codex-tuned
tools code
128k
codex-5
provider: codex · tier: stable
tools code
128k
codex-4
provider: codex · tier: legacy
code
8k
codex-5-codex
provider: codex · tier: codex variant
tools code fast
128k
// who it's for

Built for builders.

Whatever your stack, whatever your IDE — Cline Codex fits in.

EN
Engineers
Refactor, debug, ship.
DS
Data Scientists
Notebooks + pipelines.
RS
Researchers
Read, summarize, prototype.
WR
Writers
Docs that match the code.
ID
Indie devs
Solo velocity.
ST
Students
Pair program. Learn fast.
// api

One base URL. No SDK changes.

Point your existing OpenAI client at clinecodex.com — it just works.

Cline Codex — v1
# configure your client (any OpenAI SDK) base_url = "https://clinecodex.com/oai-chatgpt/v1" api_key = "<your-api-key>" model = "codex-5.5" # or use curl directly $ curl https://clinecodex.com/oai-chatgpt/v1/models | jq '.data[].id' "codex-5.5" "codex-5.2" "codex-5-codex" "codex-5" "codex-4"
// pricing

Token plans.

Simple, transparent pricing. Cancel anytime. No hidden fees.

Plus
$ 20 / month
For solo developers and hobbyists.
  • 200K tokens / day
  • All Codex models
  • 10 requests / minute
  • Standard email support
  • Community Discord access
Most popular
Pro
$ 50 / month
For power users shipping every day.
  • 1M tokens / day
  • All Codex models, priority queue
  • 60 requests / minute
  • Priority email support
  • Usage analytics dashboard
  • Early access to new models
Max
$ 200 / month
For teams and production workloads.
  • Unlimited tokens
  • All Codex models, highest priority
  • 300 requests / minute
  • Dedicated support engineer
  • Up to 10 team seats
  • SSO + audit logs
  • Custom rate limits on request