Provider: Google Vertex AI

Use Respan Gateway to call Google Vertex AI models (gemini-3.5-flash, gemini-3-pro, Anthropic Claude on Vertex, and the rest) while keeping unified observability (logs, cost, latency, reliability) in Respan.

Quick setup

Send your first request

Pick the integration that matches your stack. The base URL is https://api.respan.ai/api and the only key needed is your RESPAN_API_KEY.

1
import { createOpenAI } from "@ai-sdk/openai";
2
import { generateText } from "ai";
3
4
const respan = createOpenAI({
5
  apiKey: process.env.RESPAN_API_KEY!,
6
  baseURL: "https://api.respan.ai/api",
7
});
8
9
const result = await generateText({
10
  model: respan("vertex_ai/gemini-3.5-flash"),
11
  prompt: "Hello, Gemini on Vertex!",
12
});
13
console.log(result.text);

More integrations

Vertex AI models work with every Respan gateway integration:

• OpenAI SDK
• LangChain
• LangGraph
• LlamaIndex
• Pydantic AI
• Respan native (OTel)

Switch models

Change the model parameter to call any supported model through the same client. Use the vertex_ai/ prefix to disambiguate when routing across providers. Browse the full list on the Models page.

1
client.chat.completions.create(model="vertex_ai/gemini-3.5-flash", messages=messages)
2
client.chat.completions.create(model="vertex_ai/gemini-3-pro", messages=messages)
3
client.chat.completions.create(model="vertex_ai/claude-sonnet-4-5@20250929", messages=messages)
4
client.chat.completions.create(model="openai/gpt-5.5", messages=messages)
5
client.chat.completions.create(model="anthropic/claude-sonnet-4-5-20250929", messages=messages)

Use your own Google Vertex AI key (BYOK)

Credits are the default path. If you’d rather bill Google Cloud directly, attach your own service-account credentials.

Override credentials per model (Optional)

Use credential_override when one model on a request should use a different Vertex project than the default.

1
{
2
  "customer_credentials": {
3
    "google_vertex_ai": {
4
      "vertex_ai_project": "your-project",
5
      "vertex_ai_location": "us-central1",
6
      "vertex_ai_credentials": {
7
        "type": "service_account",
8
        "project_id": "your-project"
9
      }
10
    }
11
  },
12
  "credential_override": {
13
    "vertex_ai/gemini-3.5-flash": {
14
      "vertex_ai_project": "ANOTHER_VERTEX_AI_PROJECT",
15
      "vertex_ai_location": "ANOTHER_VERTEX_AI_LOCATION",
16
      "vertex_ai_credentials": {
17
        "type": "service_account",
18
        "project_id": "another-project"
19
      }
20
    }
21
  }
22
}

Log without proxying (Optional)

Already calling Vertex AI directly? Send logs to Respan asynchronously to track cost, latency, and performance for those external calls.

1
import requests
2
3
requests.post(
4
    "https://api.respan.ai/api/request-logs/create/",
5
    headers={
6
        "Authorization": "Bearer YOUR_RESPAN_API_KEY",
7
        "Content-Type": "application/json",
8
    },
9
    json={
10
        "model": "vertex_ai/gemini-3.5-flash",
11
        "prompt_messages": [{"role": "user", "content": "Hello, how are you?"}],
12
        "completion_message": {"role": "assistant", "content": "Hello from Vertex AI through Respan."},
13
        "cost": 0.001,
14
        "generation_time": 1.2,
15
        "customer_params": {"customer_identifier": "user_123"},
16
    },
17
)

See the logging guide for the full setup.