# OpenAI Codex Preisgestaltung: Was die CLI wirklich kostet 2026

OpenAI Codex CLI is a free, open-source tool — but it sends every prompt to the OpenAI API, which charges per token. One image compression task burned 7,675 tokens: between 3 and 11 cents. The default model, codex-mini-latest, costs $1.50 per million input tokens and $6.00 per million output tokens. Pointing Codex at RunAPI instead cuts those rates by 50%, with no other changes to your workflow.

*Updated June 23, 2026 · RunAPI Editorial*

## Wie viel kostet OpenAI Codex?

The Codex CLI itself is free to download and run. The cost comes from API calls: every prompt, file read, and code generation goes to the OpenAI API. The default model is codex-mini-latest, priced at $1.50/1M input tokens and $6.00/1M output tokens through OpenAI directly. A moderate coding session — roughly 8M input and 2M output tokens per month — runs about $24 with OpenAI. The same usage through RunAPI costs $12. RunAPI is OpenAI-compatible, so you change two environment variables and nothing else. Tip: run /compact during long sessions to free up context and stop burning tokens on conversation history.

- **Codex CLI ist kostenlos**: Die CLI selbst hat keine Abonnementgebühr. Sie zahlen nur für die während jeder Coding-Sitzung verbrauchten API-Tokens.
- **OpenAI direkt — $1,50 / $6,00 pro 1 Mio. Tokens**: codex-mini-latest Eingabe kostet $1,50/1 Mio. Tokens, Ausgabe kostet $6,00/1 Mio. Tokens über die OpenAI-API.
- **RunAPI — $0,75 / $3,00 pro 1 Mio. Tokens**: RunAPI liefert dasselbe Modell zu 50 % Rabatt. Setzen Sie zwei Umgebungsvariablen und Codex routet automatisch über RunAPI.
- **Keine Abonnementbindung**: Zahlen Sie nur für das, was Sie verwenden. Keine monatliche Sitzgebühr. Kein Mindestbetrag. Die Abrechnung stoppt, sobald Sie aufhören zu coden.

## Was wird als Token gezählt?

Every message Codex sends to the API includes your prompt, the full context of files it has read, any tool results, and conversation history. That combined input is tokenized (roughly 750 words per 1,000 tokens). The model's response — edited code, explanations, next steps — counts as output tokens. Both directions are billed separately. Codex caches nothing between sessions, so a fresh session re-reads the same files and bills that context again. One real example from a developer testing image compression — a single 5 MB file task burned 7,675 tokens, or roughly 3 to 11 cents. Not very cheap for one file, but most coding sessions stay well under a dollar each.

## codex-mini-latest Preisgestaltung: OpenAI vs. RunAPI

## Was kostet ein typischer Monat?

## 

1. **Codex CLI installieren** — 
2. **RunAPI-Konto erstellen** — 
3. **Umgebungsvariablen setzen** — 
4. **Codex ausführen** — 
5. **Das Modell überprüfen** — 

## Häufige Fragen zur Codex-Preisgestaltung

### 



### 



### 



### 



### 



### 



### 



###