Claude visitors: new accounts receive $1.00 in bonus API credit within 30 days. One per person; usage credits only.
Use Gemini in WorkBuddy.
Google Gemini is available through RunAPI — Gemini 3.5 Flash for sub-100ms first-token latency, 3.x Pro for complex reasoning, and 2.5 Pro for production workloads with a 1M token context window. WorkBuddy speaks MCP natively, so the same runapi MCP server and RUNAPI_API_KEY that power GPT also call Gemini. No Google Cloud project, no service account, no Vertex AI setup.
Use the runapi MCP server to send a chat request to Gemini.
Requirements:
- Call the RunAPI chat tool exposed by the runapi MCP server
- Set model to "gemini-3.5-flash"
- Ask: "Explain the difference between gRPC and REST in three sentences."
- Set temperature to 0.7 and max_tokens to 256
- 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": "gemini-3.5-flash",
"content": "gRPC uses HTTP/2 and Protocol Buffers for strongly-typed, multiplexed RPC calls with built-in code generation. REST uses JSON payloads and relies on URL paths and HTTP verbs for resource semantics. gRPC is faster for service-to-service calls; REST is simpler to debug and more widely supported by browsers.",
"finish_reason": "stop",
"usage": {
"prompt_tokens": 34,
"completion_tokens": 71,
"total_tokens": 105
}
}
Use Gemini 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. No Google Cloud credentials, no service account JSON — the RunAPI key is all Gemini needs.
export RUNAPI_API_KEY=runapi_xxx
# MCP server: runapi → https://runapi.ai/mcp
Prompt the workbench agent
Type a natural-language request into WorkBuddy and name the model — gemini-3.5-flash for speed, gemini-2.5-pro for long-context reasoning. WorkBuddy fills the model and messages arguments of the RunAPI chat tool and sends the call.
model: gemini-3.5-flash
Read the tool result
The MCP tool returns the reply synchronously with token usage counts. Switch to GPT or Claude in your next prompt without touching the config — every model behind the runapi server shares the same key and tool shape.
usage.total_tokens: 105
Gemini tool parameters on the RunAPI MCP server
| Parameter | Type | Description |
|---|---|---|
model |
string |
Required. gemini-3.5-flash, gemini-2.5-flash, gemini-2.5-pro, gemini-3-flash-preview, or gemini-3.1-pro-preview. |
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. Default varies by model. |
max_tokens |
integer |
Optional. Maximum number of tokens to generate in the response. |
top_p |
number |
Optional. Nucleus sampling threshold between 0 and 1. Alternative to temperature for controlling output randomness. |
tools |
array |
Optional. Tool definitions for function calling. Gemini returns tool_calls in the assistant message, which WorkBuddy processes like any other tool result. |
What is Gemini on WorkBuddy?
Google Gemini is available through RunAPI without a Google Cloud project, service account, or Vertex AI setup. WorkBuddy reaches it through the same runapi MCP server and RUNAPI_API_KEY used for GPT and Claude. Gemini 3.5 Flash gives you sub-100ms first-token latency for real-time agent loops, while Gemini 2.5 Pro handles long-context tasks with its 1M token context window and thinking mode for complex reasoning.
Gemini use cases
Multimodal analysis from the workbench
Send images, PDFs, audio files, or video frames alongside text prompts for Gemini to analyze, describe, or extract structured data — all handled natively through one tool call.
Long document analysis with 1M token context
Feed entire codebases, legal document sets, or research paper collections into Gemini 2.5 Pro's 1M token context window for analysis and summarization without chunking or retrieval pipelines.
Real-time agent loops with Flash
Use Gemini 3.5 Flash for speed-sensitive tool-calling chains where sub-100ms first-token latency matters more than peak reasoning quality. Cost per million tokens is among the lowest in the catalog.
Gemini + WorkBuddy questions
Yes. RunAPI provides Gemini access through its MCP server. You only need a RUNAPI_API_KEY — no Google Cloud project, no service account JSON, no Vertex AI billing setup.
Flash (gemini-3.5-flash) is fastest and cheapest — best for real-time agent loops, classification, and tool-calling chains. Pro (gemini-2.5-pro) handles complex reasoning, long-context analysis, and multi-step tasks where accuracy matters more than speed.
Pay-per-token with no monthly subscription or minimum spend. Input and output tokens are metered separately, and Gemini Flash rates are among the lowest in the RunAPI catalog. Check the RunAPI pricing page for current rates.
Yes. Both go through the same runapi MCP server and API key. Name a different model in your next prompt — gemini-3.5-flash, gpt-5.5, or any other catalog model — and WorkBuddy changes only the model argument of the tool call.
Yes. Define tools in the request and Gemini returns tool_calls in the assistant message. WorkBuddy processes these the same way it handles tool calls from GPT or Claude.
WorkBuddy general setup
Not connected yet? Start with the RunAPI MCP setup guide for WorkBuddy.
WorkBuddy setup guide →Try Gemini in WorkBuddy today.
Get a free RunAPI key, register the MCP server, and start chatting with Gemini 3.5 Flash — no Google Cloud project required.