Claude visitors: new accounts receive $1.00 in bonus API credit within 30 days. One per person; usage credits only.
Use GPT in WorkBuddy.
GPT-5.5 is OpenAI's flagship LLM, available through RunAPI at half the official per-token price. WorkBuddy speaks MCP natively — register RunAPI as an MCP server once and every GPT variant (5.5, 5.4, 5.4-mini) becomes a callable tool inside the workbench, with function calling and structured output intact.
Use the runapi MCP server to send a chat request to GPT.
Requirements:
- Call the RunAPI chat tool exposed by the runapi MCP server
- Set model to "gpt-5.5"
- Ask: "Write a Python function that merges two sorted lists in O(n) time."
- Set temperature to 0.3 and max_tokens to 1024
- Show me the assistant reply and the token usage counts
{
"mcpServers": {
"runapi": {
"url": "https://runapi.ai/mcp",
"transport": "streamable_http",
"headers": {
"Authorization": "Bearer $RUNAPI_API_KEY"
}
}
}
}
{
"model": "gpt-5.5",
"content": "def merge_sorted(a, b):\n result = []\n i = j = 0\n while i < len(a) and j < len(b):\n ...",
"finish_reason": "stop",
"usage": {
"prompt_tokens": 38,
"completion_tokens": 95,
"total_tokens": 133
}
}
Use GPT in WorkBuddy in three steps
Register the RunAPI MCP server
Set RUNAPI_API_KEY in the environment that launches WorkBuddy, then add an MCP server named runapi pointing at https://runapi.ai/mcp over streamable HTTP. If RunAPI is already connected for other models, GPT is included — no additional setup.
export RUNAPI_API_KEY=runapi_xxx
# MCP server: runapi → https://runapi.ai/mcp
Pick a GPT model in your prompt
Name the variant in your workbench request — gpt-5.5 for the flagship, or gpt-5.4 or gpt-5.4-mini for lower cost. WorkBuddy fills the model argument of the RunAPI chat tool and sends the call.
model: gpt-5.5
Read the tool result
The MCP tool returns the completion synchronously with usage counts and finish_reason. Ask for tools or structured JSON output in your prompt and WorkBuddy passes the corresponding arguments through — tool_calls and json_schema results come back in the same response.
usage.total_tokens: 133
GPT tool parameters on the RunAPI MCP server
| Parameter | Type | Description |
|---|---|---|
model |
string |
Required. gpt-5.5, gpt-5.4, gpt-5.4-mini, gpt-5.4-nano, or gpt-5.2. |
messages |
array |
Required. Array of message objects with role (system, user, assistant) and content fields. WorkBuddy builds this from your prompt. |
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. |
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. |
What is GPT on WorkBuddy?
GPT is OpenAI's flagship LLM family, available through RunAPI at half the official per-token price. WorkBuddy reaches every variant through the single runapi MCP server — GPT-5.5 for top-tier reasoning, GPT-5.4 for everyday tasks, and GPT-5.4-mini for cheap bulk work — all with function calling and structured JSON output, using the same RUNAPI_API_KEY that covers Claude, Gemini, and the media models.
GPT use cases
Office documents and long-form drafting
Draft reports, summaries, and slides inside WorkBuddy and let GPT-5.5 handle the heavy reasoning — the MCP tool returns polished long-form output straight into the workbench.
Agentic reasoning and multi-step tasks
Use GPT-5.5 for complex, multi-step reasoning tasks through the same MCP tool, with function calling and structured output support.
Data extraction with structured outputs
Ask for json_schema output and get guaranteed valid JSON from GPT — useful for extracting structured data from documents, parsing invoices, or feeding downstream automations.
GPT + WorkBuddy questions
Yes. WorkBuddy speaks MCP natively. Register RunAPI as an MCP server pointing at https://runapi.ai/mcp with your RUNAPI_API_KEY, and GPT appears as a callable chat tool. The same server covers chat, image, video, and music models.
RunAPI charges 50% of OpenAI's official per-token rate for all GPT models. The discount applies to both input and output tokens, with no subscription or volume commitment. Check the RunAPI pricing page for exact per-million-token rates.
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. All go through the same MCP tool — only the model argument changes.
Yes. Ask for it in your prompt — WorkBuddy passes a tools array or a response_format of json_schema through the MCP tool call, and GPT returns tool_calls or schema-constrained JSON in the tool result.
No. After the MCP server is registered, you type a natural-language prompt into the workbench. WorkBuddy selects the RunAPI chat tool, fills in the model and messages, and renders the reply inline — no curl commands or SDK setup.
WorkBuddy general setup
Not connected yet? Start with the RunAPI MCP setup guide for WorkBuddy.
WorkBuddy setup guide →Try GPT-5.5 in WorkBuddy today.
Get a free RunAPI key, register the MCP server, and call GPT-5.5 at half the official OpenAI token price — function calling and structured output included.