Google · Text

OpenClaw x Gemini

Gemini is Google's flagship multimodal LLM, available in Flash (fast) and Pro (frontier reasoning) variants. Through RunAPI, all Gemini models share the same API shape and billing.

11 variants from $0.10 / 1M tokens Commercial OK
Get API Key View OpenClaw Docs

Prerequisite: npx runapi mcp install

Prompt

Prompt models

Use gemini-2.5-flash when it matches the task: Speed/cost optimized; 1M context; older generation baseline.

You have access to RunAPI chat models for Gemini.

Available Gemini models:
- gemini-2.5-flash: Speed/cost optimized; 1M context; older generation baseline
  chat endpoints: /v1/chat/completions
- gemini-2.5-flash-lite: Gemini 2.5 Flash-Lite; 1M context, thinking off by default; OpenAI-compatible Chat Completions
  chat endpoints: /v1/chat/completions
- gemini-2.5-pro: Best reasoning in 2.5 gen; 1M context
  chat endpoints: /v1/chat/completions
- gemini-3-flash-preview: gemini-3-flash-preview
  chat endpoints: /v1/chat/completions, /v1beta/models/gemini-3-flash-preview:streamGenerateContent
- gemini-3.1-flash-lite: Gemini 3.1 Flash-Lite; 1M context, adjustable thinking; text requests through OpenAI-compatible Chat Completions
  chat endpoints: /v1/chat/completions
- gemini-3.1-pro-preview: gemini-3.1-pro-preview
  chat endpoints: /v1/chat/completions
- gemini-3.5-flash: Fast multimodal streaming for high-volume production workloads
  chat endpoints: /v1/chat/completions, /v1beta/models/gemini-3.5-flash:streamGenerateContent
- gemini-3.5-flash-lite: Lightweight Gemini for text generation through Chat Completions or native content streaming
  chat endpoints: /v1/chat/completions, /v1beta/models/gemini-3.5-flash-lite:streamGenerateContent
- gemini-3.6-flash: Fast multimodal chat, tools, and streaming for production workloads
  chat endpoints: /v1/chat/completions, /v1beta/models/gemini-3.6-flash:streamGenerateContent
- gemini-3.7-flash: Fast streaming chat and native content output with usage reporting
  chat endpoints: /v1/chat/completions, /v1beta/models/gemini-3.7-flash:streamGenerateContent
- gemini-3.8-flash: Text chat with function calling and native content streaming for agent workloads
  chat endpoints: /v1/chat/completions, /v1beta/models/gemini-3.8-flash:streamGenerateContent

Use the model ID and chat endpoint that match the user's request.
Example request: Analyze this codebase and suggest three performance improvements with before/after examples.
Verify the active model with: openclaw models status;openclaw models set runapi/<model-id>

Public Versions and Endpoints

Model ID Endpoints Price Catalog
gemini-2.5-flash
/v1/chat/completions
$0.30 / 1M tokens Model detail
gemini-2.5-flash-lite
/v1/chat/completions
$0.10 / 1M tokens Model detail
gemini-2.5-pro
/v1/chat/completions
$1.25 / 1M tokens Model detail
gemini-3-flash-preview
/v1/chat/completions /v1beta/models/gemini-3-flash-preview:streamGenerateContent
$0.30 / 1M tokens Model detail
gemini-3.1-flash-lite
/v1/chat/completions
$0.25 / 1M tokens Model detail
gemini-3.1-pro-preview
/v1/chat/completions
$1.00 / 1M tokens Model detail
gemini-3.5-flash
/v1/chat/completions /v1beta/models/gemini-3.5-flash:streamGenerateContent
$0.90 / 1M tokens Model detail
gemini-3.5-flash-lite
/v1/chat/completions /v1beta/models/gemini-3.5-flash-lite:streamGenerateContent
$0.15 / 1M tokens Model detail
gemini-3.6-flash
/v1/chat/completions /v1beta/models/gemini-3.6-flash:streamGenerateContent
$0.75 / 1M tokens Model detail
gemini-3.7-flash
/v1/chat/completions /v1beta/models/gemini-3.7-flash:streamGenerateContent
$0.45 / 1M tokens Model detail
gemini-3.8-flash
/v1/chat/completions /v1beta/models/gemini-3.8-flash:streamGenerateContent
$0.45 / 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 + Gemini

  • Multimodal applications

    Send images, PDFs, audio, or video alongside text prompts for Gemini to analyze, describe, or extract structured data in one call.

  • Long document analysis

    Give Gemini large codebases, legal document sets, or research collections in one request for analysis and summarization.

  • Fast agent loops

    Use a Flash version of Gemini for speed-sensitive tool-calling chains where latency matters more than peak reasoning quality.

Why Use Gemini Through RunAPI + OpenClaw

  • 11 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 + Gemini Questions

Can I use Gemini in OpenClaw without a Google Cloud project?

Yes. RunAPI serves Gemini through its OpenAI-compatible endpoint. You only need a RunAPI API key, with no Google Cloud project, service account, or Vertex AI billing.

When should I use Gemini Flash or Pro?

Flash versions are faster and cheaper, which suits agent loops, classification, and tool calling. Pro versions handle complex reasoning and long-context analysis.

Does Gemini through RunAPI support function calling?

Yes. RunAPI passes OpenAI-compatible tools and tool choice to Gemini, and Gemini returns tool calls in the assistant message. OpenClaw handles them like tool calls from other models.

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 Gemini 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