---
title: "通过 RunAPI 在龙虾 (OpenClaw) 中使用 Gemini — 大模型API 指南"
url: "https://runapi.ai/zh-CN/openclaw-gemini.md"
canonical: "https://runapi.ai/zh-CN/openclaw-gemini"
locale: "zh-CN"
model: "gemini"
---

# 在 OpenClaw 中使用 Gemini。

Google Gemini 可通过 RunAPI 的 OpenAI 兼容端点调用 — Gemini 3.5 Flash 实现亚 100 毫秒的首字延迟，3.x Pro 应对复杂推理，2.5 Pro 服务于生产工作负载。OpenClaw 将其视为又一个 OpenAI 兼容模型，因此为 GPT 提供动力的同一套 provider 配置和 RUNAPI_API_KEY 也能调用 Gemini。无需 Google Cloud 项目，无需服务账号，无需 Vertex AI 配置。

## API example

```bash
curl -X POST https://runapi.ai/v1/chat/completions \
  -H "Authorization: Bearer $RUNAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.5-flash",
    "messages": [
      {"role": "system", "content": "You are a concise technical assistant."},
      {"role": "user", "content": "Explain the difference between gRPC and REST in three sentences."}
    ],
    "temperature": 0.7,
    "max_tokens": 256
  }'

```

### Response

```json
{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "model": "gemini-3.5-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "gRPC uses HTTP/2 and Protocol Buffers for strongly-typed, multiplexed RPC calls with built-in code generation. REST uses HTTP/1.1 (or 2) with 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
  }
}

```

## How it works

1. **Configure RunAPI** — Set the RUNAPI_API_KEY environment variable. If you already configured RunAPI as an OpenClaw provider, the same key and baseUrl work for Gemini — just change the model ID. No Google Cloud credentials needed.
2. **Call Gemini via chat completions** — Send a POST request to /v1/chat/completions with model set to gemini-3.5-flash. Pass a messages array with system and user roles. The endpoint accepts the same OpenAI-compatible shape your agent already uses for GPT models.
3. **Read the response** — The response arrives synchronously in OpenAI chat completion format. The assistant reply is in choices[0].message.content, with token usage in the usage object. For streaming, set stream to true and parse SSE events.

## Parameters

| Parameter | Type | Description |
|-----------|------|-------------|
| `model` | `string` | Required. gemini-3.5-flash, gemini-2.5-flash, gemini-2.5-pro, gemini-3-flash-preview, gemini-3-pro-preview, or gemini-3.1-pro-preview. |
| `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. Default varies by model. |
| `max_tokens` | `integer` | Optional. Maximum number of tokens to generate in the response. |
| `stream` | `boolean` | Optional. When true, the response streams as server-sent events. Each event contains a delta with partial content. |
| `top_p` | `number` | Optional. Nucleus sampling threshold between 0 and 1. Alternative to temperature for controlling output randomness. |

## FAQ

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

Yes. RunAPI provides Gemini access through its OpenAI-compatible endpoint. You only need a RUNAPI_API_KEY -- no Google Cloud project, no service account JSON, no Vertex AI billing setup.

### What is the difference between Gemini Flash vs Pro -- when should I use each?

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.

### Is the Gemini API still free through RunAPI?

RunAPI uses pay-per-token billing for Gemini with no free tier. However, Gemini Flash rates are among the lowest in the RunAPI catalog. Input and output tokens are metered separately. Check the RunAPI pricing page for current rates.

### Can I switch between Gemini and GPT in the same OpenClaw session?

Yes. Both use the same RunAPI provider config and API key. Change the model parameter from gemini-3.5-flash to gpt-5.5 (or any other RunAPI model) without reconfiguring the provider. OpenClaw selects models per request.

### Does Gemini through RunAPI support function calling and tool use?

Yes. RunAPI passes the OpenAI-compatible tools and tool_choice parameters to Gemini. Define tools in the request body and Gemini returns tool_calls in the assistant message. OpenClaw processes these the same way it handles tool calls from GPT or Claude.


## Links

- [OpenClaw 配置指南 →](https://runapi.ai/zh-CN/openclaw)
- [Gemini 模型 →](https://runapi.ai/zh-CN/models/gemini)
- [Model catalog](https://runapi.ai/zh-CN/models)
- [API docs](https://runapi.ai/zh-CN/docs)