OpenAI · Text

OpenClaw x GPT

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.

15 variants from $0.06 / 1M tokens Commercial OK
Get API Key View OpenClaw Docs

Prerequisite: npx runapi mcp install

Prompt

Prompt models

Use codex-auto-review when it matches the task: codex-auto-review.

You have access to RunAPI chat models for GPT.

Available GPT models:
- codex-auto-review: codex-auto-review
  chat endpoints: /v1/chat/completions, /v1/responses
- gpt-4o-mini: Fast, affordable GPT-4o model for everyday text tasks
  chat endpoints: /v1/chat/completions, /v1/responses
- gpt-5-pro: GPT-5 Pro for analysis and coding through the Responses API
  chat endpoints: /v1/responses
- gpt-5.2: Professional knowledge work; Thinking mode for deep tasks
  chat endpoints: /v1/responses, /v1/chat/completions
- gpt-5.4: Best coding + agentic workflows; industry-leading code benchmark
  chat endpoints: /v1/responses, /v1/chat/completions
- gpt-5.4-mini: Cost-effective fallback for gpt-5.4; available to Free tier
  chat endpoints: /v1/chat/completions, /v1/responses
- gpt-5.4-nano: gpt-5.4-nano
  chat endpoints: /v1/responses, /v1/chat/completions
- gpt-5.5: Purpose-built for long-horizon agentic tasks; best error recovery
  chat endpoints: /v1/chat/completions, /v1/responses
- gpt-5.6-luna: Fastest, lightest GPT-5.6 tier for summaries, drafts, and everyday automation
  chat endpoints: /v1/responses, /v1/chat/completions
- gpt-5.6-sol: Flagship for the hardest tasks: complex coding, deep research, long-horizon agents
  chat endpoints: /v1/chat/completions, /v1/responses
- gpt-5.6-terra: Balanced workhorse for high-volume tasks; near-flagship quality, cost-efficient
  chat endpoints: /v1/responses, /v1/chat/completions
- gpt-6-astra: Most capable model: frontier reasoning, 1M context, code generation, and agentic tasks
  chat endpoints: /v1/chat/completions, /v1/responses
- gpt-6-luna: Fastest, lightest GPT-6 tier: 1M context for summaries, drafts, and everyday automation
  chat endpoints: /v1/chat/completions, /v1/responses
- gpt-6-sol: Cost-efficient GPT-6 tier: strong reasoning, 1M context, coding, and agentic tasks
  chat endpoints: /v1/chat/completions, /v1/responses
- gpt-6.1-sol: Cost-efficient GPT-6 tier: strong reasoning, 1M context, coding, and agentic tasks
  chat endpoints: /v1/chat/completions, /v1/responses

Use the model ID and chat endpoint that match the user's request.
Example request: Analyze this quarterly revenue data and produce a summary with key trends, anomalies, and three recommendations.
Verify the active model with: openclaw models status;openclaw models set runapi/<model-id>

Public Versions and Endpoints

Model ID Endpoints Price Catalog
codex-auto-review
/v1/chat/completions /v1/responses
$0.20 / 1M tokens Model detail
gpt-4o-mini
/v1/chat/completions /v1/responses
$0.15 / 1M tokens Model detail
gpt-5-pro
/v1/responses
$7.50 / 1M tokens Model detail
gpt-5.2
/v1/responses /v1/chat/completions
$1.75 / 1M tokens Model detail
gpt-5.4
/v1/responses /v1/chat/completions
$2.50 / 1M tokens Model detail
gpt-5.4-mini
/v1/chat/completions /v1/responses
$0.75 / 1M tokens Model detail
gpt-5.4-nano
/v1/responses /v1/chat/completions
$0.20 / 1M tokens Model detail
gpt-5.5
/v1/chat/completions /v1/responses
$5.00 / 1M tokens Model detail
gpt-5.6-luna
/v1/responses /v1/chat/completions
$0.20 / 1M tokens Model detail
gpt-5.6-sol
/v1/chat/completions /v1/responses
$5.00 / 1M tokens Model detail
gpt-5.6-terra
/v1/responses /v1/chat/completions
$2.00 / 1M tokens Model detail
gpt-6-astra
/v1/chat/completions /v1/responses
$5.00 / 1M tokens Model detail
gpt-6-luna
/v1/chat/completions /v1/responses
$0.06 / 1M tokens Model detail
gpt-6-sol
/v1/chat/completions /v1/responses
$1.20 / 1M tokens Model detail
gpt-6.1-sol
/v1/chat/completions /v1/responses
$1.00 / 1M tokens Model detail

Verify

Poll until the task reaches a terminal status

Select <model-id> to generate verification commands.

Configuration

Guide endpoint: <endpoint>

Select <model-id> to generate a request with the endpoint's public input contract.
How it works

Get Started in 3 Steps

  1. Choose a model ID

    Select a public catalog model ID and review its endpoint and current starting price.

  2. Configure RunAPI

    Add the provider configuration for this agent.

  3. Verify the result

    Run the agent status and model-selection commands shown below.

What to Build with OpenClaw + GPT

  • Chatbots and conversational AI

    Run GPT chat completions through RunAPI with the OpenAI SDK and request format your app already uses, changing only the base URL.

  • Agentic reasoning and multi-step tasks

    Use GPT for multi-step reasoning, planning, and tool-using agent loops in OpenClaw.

  • Data extraction with structured outputs

    Request JSON that follows a schema to extract structured data from documents, parse invoices, or feed RAG pipelines.

Why Use GPT Through RunAPI + OpenClaw

  • 15 variants, one API key

    Use one RunAPI connection to choose among the live model variants without changing your integration.

  • Clear usage pricing

    See current catalog pricing before you send a request, with no subscription or minimum spend required.

  • Direct responses

    Synchronous calls return the result in the same response, so your agent can use it immediately without task polling.

OpenClaw + GPT Questions

Can I use GPT in OpenClaw through RunAPI?

Yes. OpenClaw supports OpenAI-compatible providers. Add RunAPI with the configuration shown on this page and pick a GPT version from the versions list.

What is the difference between the Chat Completions API and the Responses API?

Chat Completions is the standard request-response endpoint that returns a message. The Responses API is OpenAI's newer interface with built-in tools. RunAPI supports both for GPT.

Can I use function calling and structured output with GPT on RunAPI?

Yes. Pass tools for function calling or a JSON schema for structured output. RunAPI forwards these parameters and returns tool calls or structured JSON in the standard OpenAI response format.

Which model ID should I use?

Choose a public model ID from the version table. Each ID exposes the endpoints shown for that version.

Does this guide configure a chat model?

Yes. This Model Line supports a client-facing LLM protocol.

Start using GPT with OpenClaw

Get API Key Read Quickstart

Building with a team?

We're here to help with enterprise setup, integrations, and technical questions.

Contact Us