Use GPT in OpenClaw.
GPT-5.5 is OpenAI's flagship LLM, available through RunAPI at half the official per-token price. OpenClaw already speaks the OpenAI completions protocol — point it at RunAPI's /v1 base URL and every GPT variant (5.5, 5.4, 5.4-mini, 5.3-codex) works with streaming, function calling, and structured output.
Use RunAPI to call GPT-5.5 through the OpenAI-compatible Chat Completions endpoint.
Requirements:
- Read the API key from RUNAPI_API_KEY.
- Call POST https://runapi.ai/v1/chat/completions
- Set model to "gpt-5.5".
- Include a messages array with at least one user message.
- The response is synchronous — the completion arrives in the same HTTP response.
- For streaming, set "stream": true to receive server-sent events.
- For the Responses API, call POST https://runapi.ai/v1/responses instead.
curl -X POST https://runapi.ai/v1/chat/completions \
-H "Authorization: Bearer $RUNAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5.5",
"messages": [
{"role": "system", "content": "You are a concise coding assistant."},
{"role": "user", "content": "Write a Python function that merges two sorted lists in O(n) time."}
],
"temperature": 0.3,
"max_tokens": 1024
}'
{
"id": "chatcmpl-abc123",
"object": "chat.completion",
"model": "gpt-5.5",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "def merge_sorted(a, b):\n result = []\n i = j = 0\n while i < len(a) and j < len(b):\n if a[i] <= b[j]:\n result.append(a[i]); i += 1\n else:\n result.append(b[j]); j += 1\n result.extend(a[i:])\n result.extend(b[j:])\n return result"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 38,
"completion_tokens": 95,
"total_tokens": 133
}
}
Use GPT in OpenClaw in three steps
Point OpenClaw at RunAPI
If RunAPI is already configured as a provider in OpenClaw, the same key and /v1 base URL work for GPT. OpenClaw uses the openai-completions API mode, so GPT-5.5 is a drop-in model swap — no protocol change needed.
export RUNAPI_API_KEY=runapi_xxx
Select a GPT model
Set the model to gpt-5.5 for the flagship, gpt-5.4 or gpt-5.4-mini for lower cost, or gpt-5.3-codex for code-heavy tasks. The /v1/chat/completions endpoint returns a standard OpenAI response with usage counts and finish_reason.
model: gpt-5.5
Use streaming or function calling
Add "stream" true for token-by-token SSE output. Add a tools array for function calling. Add response_format for structured JSON output. All standard OpenAI parameters work through RunAPI without modification.
"stream": true
GPT Chat Completions parameters
| Parameter | Type | Description |
|---|---|---|
model |
string |
Required. gpt-5.5, gpt-5.4, gpt-5.4-mini, gpt-5.4-nano, gpt-5.3-codex, or gpt-5.2. |
messages |
array |
Required. Array of message objects with role (system, user, assistant) and content fields. |
temperature |
number |
Optional. Sampling temperature between 0 and 2. Lower values produce more deterministic output. Defaults to 1. |
max_tokens |
integer |
Optional. Maximum number of tokens to generate in the completion. |
stream |
boolean |
Optional. When true, returns server-sent events with incremental token deltas. Defaults to false. |
tools |
array |
Optional. Array of tool definitions for function calling. Each tool has a type, function name, description, and parameters schema. |
response_format |
object |
Optional. Set type to "json_object" or "json_schema" for structured JSON output. |
reasoning_effort |
string |
Optional. Controls thinking depth for supported models. Accepted values are low, medium, high. |
What is GPT on OpenClaw?
GPT is OpenAI's flagship LLM family, available through RunAPI at half the official per-token price. OpenClaw already speaks the OpenAI chat completions protocol, so switching to RunAPI is a one-line base URL change -- GPT-5.5 for top-tier reasoning, GPT-5.4 for everyday tasks, GPT-5.4-mini for cheap bulk work, and GPT-5.3-codex for code generation all work with streaming, function calling, and structured JSON output.
GPT use cases
Building chatbots and conversational AI
Run GPT-5.5 chat completions through RunAPI at 50% of OpenAI pricing, using the same SDK and API format your app already uses. No code changes beyond the base URL.
Code generation and agentic coding
Use GPT-5.3-codex for code generation, editing, and debugging tasks at lower per-token cost. It supports the same function calling and structured output as the flagship models.
Data extraction with structured outputs
Set response_format to json_schema and get guaranteed valid JSON from GPT, useful for extracting structured data from documents, parsing invoices, or building RAG pipelines.
GPT + OpenClaw questions
Yes. OpenClaw supports OpenAI-compatible providers. Add RunAPI with base URL https://runapi.ai/v1 and set the model to gpt-5.5. The openai-completions protocol that OpenClaw already uses works without changes.
Chat Completions (/v1/chat/completions) is the standard request-response endpoint that returns a message. The Responses API (/v1/responses) is OpenAI's newer surface that supports built-in web search, file search, and computer use tools. Both are available through RunAPI at the same discounted rate.
GPT-5.5 for complex reasoning and hard problems. GPT-5.4 for everyday tasks at lower cost. GPT-5.4-mini for high-volume cheap work like classification or tagging. GPT-5.3-codex for code generation and editing. All use the same endpoint and parameters.
Set response_format to json_schema with a schema definition in your request. GPT will constrain its output to match your schema exactly. This works for data extraction, form parsing, and any task where you need predictable JSON structure. RunAPI forwards the schema parameter unchanged.
Yes. Pass a tools array for function calling or set response_format to json_schema for structured output. RunAPI forwards these parameters to the GPT model and returns the tool_calls or structured JSON in the standard OpenAI response format.
OpenClaw general setup
Not configured yet? Start with the RunAPI setup guide for OpenClaw.
OpenClaw setup guide →Try GPT-5.5 in OpenClaw today.
Get a free RunAPI key, point OpenClaw at /v1, and call GPT-5.5 at half the official OpenAI token price — streaming, function calling, and structured output included.