GPT
OpenAI's flagship LLM for chat, code generation, and multi-step reasoning tasks.
# 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.
GPT is OpenAI's flagship large language model series, with the GPT-5 family delivering state-of-the-art performance in chat, code generation, and multi-step reasoning. Available in multiple capability tiers.
- Installable agent skill
- Unified API key
- SDK examples included
- Les générations échouées ne sont pas facturées
Variantes
| Variant | Billing | From | |
|---|---|---|---|
| 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 → |
Use this model from your agent
# User prompt to the agent
"Analyze this quarterly revenue data and produce a summary with key trends, anomalies, and three recommendations."// Code generated by the agent via @runapi.ai/gpt
import { GptClient } from '@runapi.ai/gpt';
const client = new GptClient();
const result = await client.chatCompletion.run({
model: 'codex-auto-review',
prompt: 'Analyze this quarterly revenue data and produce a summary with key trends, anomalies, and three recommendations.',
});How to call this model
Install the skill
Add the model skill to your agent or install the SDK package.
Authenticate once
Use your RunAPI key for every supported model.
Send a request
Use the unified schema for the endpoint you need.
Receive output
Poll by task ID or handle the callback when the generation completes.
SDK quickstart
curl -X POST https://runapi.ai/v1/chat/completions \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "codex-auto-review",
"messages": [
{
"role": "user",
"content": "Analyze this quarterly revenue data and produce a summary with key trends, anomalies, and three recommendations."
}
]
}'import { GptClient } from "@runapi.ai/gpt";
const client = new GptClient();
const result = await client.chatCompletion.run({
model: "codex-auto-review",
messages: [{"role":"user","content":"Analyze this quarterly revenue data and produce a summary with key trends, anomalies, and three recommendations."}],
});require "runapi/gpt"
client = RunApi::Gpt::Client.new
result = client.chat_completion.run(
model: "codex-auto-review",
messages: [{role: "user", content: "Analyze this quarterly revenue data and produce a summary with key trends, anomalies, and three recommendations."}]
)Where GPT fits
GPT is OpenAI's frontier LLM family, spanning standard and mini variants for different cost-performance trade-offs. Through RunAPI, all GPT models share the same API shape and billing.
Why use GPT through RunAPI
One API key
Use the same credentials across models and providers.
Agent-ready
Installable skills include docs and schema for tool calls.
Predictable billing
Usage-based pricing is visible before you call.
Frequently asked questions
How do I call this model?
Use the RunAPI SDK, CLI, or REST endpoint shown on this page.
Do failed generations cost money?
Les générations échouées ne sont pas facturées
Can agents use it directly?
Yes. Install the model skill and your agent gets the docs, schema, and examples.
