gpt

API key required

Call the GPT API (gpt-5.2, gpt-5.4, gpt-5.4-mini, gpt-5.5, gpt-5.3-codex) through RunAPI using the official OpenAI SDK or any OpenAI-compatible client. Use when the user asks for OpenAI / GPT chat, streaming completions, vision input, tool use / function calling, reasoning effort, the Responses API, or Codex coding tasks, or when they want to point an existing OpenAI SDK setup at RunAPI as the base URL.

Install

openclaw skills install runapi-gpt

GPT on RunAPI

Use the official OpenAI SDK (Python, TypeScript, Ruby) — or any OpenAI-compatible HTTP client — and switch the base URL to https://runapi.ai/v1. The endpoints speak the standard OpenAI protocol: Chat Completions (POST /v1/chat/completions) and the Responses API (POST /v1/responses). No client code changes beyond base_url and api_key.

Setup

OPENAI_API_KEY=YOUR_RUNAPI_TOKEN
OPENAI_BASE_URL=https://runapi.ai/v1

Get a RunAPI API Key at https://runapi.ai/api_keys.

Language	Init
Python	`OpenAI(api_key=..., base_url="https://runapi.ai/v1")`
TypeScript	`new OpenAI({ apiKey: ..., baseURL: "https://runapi.ai/v1" })`
Ruby	`OpenAI::Client.new(access_token: ..., uri_base: "https://runapi.ai/v1")`
curl	`POST https://runapi.ai/v1/chat/completions` (or `/v1/responses`)

Pick the right endpoint

Model	Endpoint to use
`gpt-5.2`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.4-nano`, `gpt-5.5`, `gpt-5.3-codex`, `gpt-5.3-codex-spark`	Chat Completions or Responses
`gpt-5.2-pro`, `gpt-5.4-pro`, `gpt-5.5-pro`	Responses only (per OpenAI)

Core recipe — Chat Completions

from openai import OpenAI

client = OpenAI(api_key="YOUR_RUNAPI_TOKEN", base_url="https://runapi.ai/v1")

response = client.chat.completions.create(
    model="gpt-5.4",
    messages=[{"role": "user", "content": "Explain quantum computing simply."}],
    reasoning_effort="high",
)
print(response.choices[0].message.content)
print(response.usage)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_RUNAPI_TOKEN",
  baseURL: "https://runapi.ai/v1",
});

const response = await client.chat.completions.create({
  model: "gpt-5.4",
  messages: [{ role: "user", content: "Explain quantum computing simply." }],
});

Core recipe — Responses API

import httpx

response = httpx.post(
    "https://runapi.ai/v1/responses",
    headers={"x-api-key": "YOUR_RUNAPI_TOKEN"},
    json={
        "model": "gpt-5.4",
        "input": "Explain the theory of relativity.",
        "reasoning": {"effort": "medium"},
    },
)
print(response.json())

The Responses API takes input (string or structured), reasoning.effort ("low" / "medium" / "high"), and optional include for thinking blocks.

Streaming

stream = client.chat.completions.create(
    model="gpt-5.4",
    messages=[{"role": "user", "content": "Write a haiku about coding."}],
    stream=True,
)
for chunk in stream:
    delta = chunk.choices[0].delta.content
    if delta:
        print(delta, end="", flush=True)

const stream = await client.chat.completions.create({
  model: "gpt-5.4",
  messages: [{ role: "user", content: "Write a haiku about coding." }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0].delta.content ?? "");
}

Streaming runs through a regional edge proxy so the request does not hold a Rails/Puma thread. Long generations should always stream.

Vision / multimodal

{
  "model": "gpt-5.4",
  "messages": [
    {
      "role": "user",
      "content": [
        { "type": "text", "text": "What is in this image?" },
        { "type": "image_url", "image_url": { "url": "https://example.com/img.jpg" } }
      ]
    }
  ]
}

Standard OpenAI multimodal block — works on both Chat Completions and Responses (Responses also accepts structured input items).

Tool use / function calling / web search

{
  "model": "gpt-5.4",
  "messages": [
    { "role": "user", "content": "Find the latest news on RunAPI." }
  ],
  "tools": [
    { "type": "function", "function": { "name": "web_search" } }
  ]
}

web_search is supported across the GPT models above. Custom function tools use the standard OpenAI tools schema.

List models

curl https://runapi.ai/v1/models -H "Authorization: Bearer YOUR_RUNAPI_TOKEN"

Returns OpenAI-compatible model objects. If the API Key has allowed_models restrictions, only permitted models are returned.

Supported models

Model ID	API	Use when
`gpt-5.5`	Chat, Responses	Latest general model
`gpt-5.5-pro`	Responses only	Reasoning-heavy
`gpt-5.4`	Chat, Responses	Production default
`gpt-5.4-mini`	Chat, Responses	Cost-optimized
`gpt-5.4-nano`	Chat, Responses	Smallest, fastest
`gpt-5.4-pro`	Responses only	Reasoning
`gpt-5.3-codex`	Chat, Responses	Code generation
`gpt-5.3-codex-spark`	Chat, Responses	Faster Codex variant
`gpt-5.2`	Chat, Responses	Cost-effective
`gpt-5.2-pro`	Responses only	Reasoning

Connect Codex CLI itself

export OPENAI_BASE_URL=https://runapi.ai/v1
export OPENAI_API_KEY=YOUR_RUNAPI_TOKEN
codex

Agent rules

Pro models (gpt-5.*-pro) reject Chat Completions — always use Responses for them. Other models accept either endpoint.
Use streaming for any response longer than a few hundred tokens. Do not hold the agent on a long blocking request.
reasoning_effort is supported on every GPT model above; default is usually "high" for non-Pro models.
Pricing, rate limits, quotas — link to https://runapi.ai/models/gpt.md, not this skill file.

Routing

Model page: https://runapi.ai/models/gpt.md
Provider page: https://runapi.ai/providers/openai.md
Catalog: https://runapi.ai/models.md

gpt