Search need
Codex API Access API access, flat pricing, active model availability, and endpoint-fit questions.
Model
Codex API access for coding agents and copilots.
Run Codex workloads through an OpenAI-compatible package with predictable spend instead of metered per-token bills.
- GPT-5.5 XHigh in Weekly and standard Monthly; GPT-5.6 Sol in Sol Weekly and Sol Monthly
- Built for agents, copilots, and CI workflows
- Unlimited token consumption with 4 concurrent connections
Quick answer
Codex access packages: XHigh $19/week or $59→$69/month; Sol $69→$89/week or $179→$199/month. One welcome price applies to the first paid order per account.
Last updated 2026-07-23
What this page answers
Page-specific proof
Codex API Access: OpenAI-Compatible ties model selection to pricing, manual delivery, 4 concurrent connections, and delivered model-ID verification.
Verification path
Use the delivered setup email and authenticated GET /v1/models to confirm the exact model ID, then send one endpoint-specific smoke request before longer agent work.
Decision summary
Best fit
Codex builders comparing GPT-5.5 XHigh at $19/week or an eligible $59 first month followed by $69/month with GPT-5.6 Sol at an eligible $69 first week followed by $89/week, or a $179 first month followed by $199/month.
Not a fit
Not ideal when you need instant key delivery, first-party OpenAI enterprise terms, or production traffic beyond 4 concurrent connections.
Next step
Compare model families on /pricing, then use the setup email and authenticated GET /v1/models to select the exact delivered Codex model ID before a smoke test.
Setup steps
Step 1
Choose the matching package
On /pricing, choose GPT-5.5 XHigh at $19/week or an eligible $59 first month followed by $69/month, or GPT-5.6 Sol at an eligible $69 first week followed by $89/week, or a $179 first month followed by $199/month.
Step 2
Use delivered model IDs
Copy the exact Codex model ID from the setup email and authenticated GET /v1/models response before configuring your client.
Step 3
Monitor concurrency
Plan agent workloads around the 4 concurrent connection limit and review usage signals in the dashboard.
Citation bundle
Use this guide with the public LLM indexes, AI search index, official references, and answer sources when citing setup, model, pricing, delivery, and 4-connection facts.
FAQ
Which Codex versions are included?
Weekly and standard Monthly map to GPT-5.5 XHigh; Sol Weekly and Sol Monthly map to GPT-5.6 Sol. Confirm the exact delivered Codex model IDs in the setup email and authenticated /v1/models response.
Is Codex good for Cursor or CI agents?
It can fit coding agents, copilots, refactors, and automated test generation when the client supports a custom OpenAI-compatible base URL and the workload stays within the 4-connection limit. Verify one small request after delivery before longer runs.