OpenAI
GPT language models and GPT Image generation — OpenAI's reasoning and creative AI suite.
OpenAI provides the GPT family of language models for chat, code, and reasoning, alongside GPT Image and GPT Image 2 for text-to-image generation with near-perfect multilingual text rendering.
- Single API key shared across providers
- Per-call billing, no commitment
- Les générations échouées ne sont pas facturées
- Streaming supported where the model supports it
What stands out
All models from OpenAI
OpenAI's flagship LLM for chat, code generation, and multi-step reasoning tasks.
Text-to-image and image editing powered by OpenAI's image generation models.
Latest OpenAI image generation with near-perfect multilingual text rendering inside images.
Native image generation inside GPT-4o — generate and edit images within the conversation.
Start with any OpenAI model.
Pick a model, install the skill, and start calling from any agent.
# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/gpt -gInstall the GPT skill for me: 1. Clone https://github.com/runapi-ai/gpt 2. Copy the skills/gpt/ directory into your user-level skills directory (e.g. ~/.claude/skills/ for Claude Code, ~/.codex/skills/ for Codex). 3. Verify that SKILL.md is present. 4. Confirm the install path when done.
Every variant from OpenAI
| Model | Variant | Billing | From | |
|---|---|---|---|---|
|
GPT
|
codex-auto-review | 1K tokens | $0.130 | Voir → |
| gpt-5.2 | 1K tokens | $0.130 | Voir → | |
| gpt-5.2-pro | 1K tokens | $1.00 | Voir → | |
| gpt-5.3-codex | 1K tokens | $0.130 | Voir → | |
| gpt-5.3-codex-spark | 1K tokens | $0.050 | Voir → | |
| gpt-5.4 | 1K tokens | $0.130 | Voir → | |
| gpt-5.4-mini | 1K tokens | $0.050 | Voir → | |
| gpt-5.4-nano | 1K tokens | $0.030 | Voir → | |
| gpt-5.4-pro | 1K tokens | $1.25 | Voir → | |
| gpt-5.5 | 1K tokens | $0.250 | Voir → | |
| gpt-5.5-pro | 1K tokens | $1.25 | Voir → |
Frequently asked questions about OpenAI
Is this an official OpenAI integration?
RunAPI exposes a managed API surface with transparent pricing, capability, and error behavior.
Do I need a OpenAI account?
No. Your RunAPI key is enough for managed access.
How is pricing billed?
Per-call or per-unit metered, with failed generations not charged.
