Skip to navigation
ModelsMore providers

Provider: Google PaLM

Call Google PaLM models through Respan Gateway with unified logs, cost, and latency.
This page is for Respan LLM Gateway users.

Google PaLM is a legacy provider. palm/chat-bison is its only currently live model in the Respan catalog. For new projects, we recommend Gemini. Use Respan Gateway to call Google PaLM models while keeping unified observability (logs, cost, latency, reliability) in Respan.

Google PaLM requires bring your own key (BYOK). Provider usage cannot be paid with Respan credits.

Quick setup

1

Get a Respan API key

Sign up and create a key on the API keys page.

2

Add your Google PaLM credentials

Configure your Google PaLM credentials on the Providers page before using the examples below. See Use your own Google PaLM key.

Send your first request

After configuring your Google PaLM credentials in Respan, pick the integration that matches your stack. The base URL is https://api.respan.ai/api and your application authenticates with RESPAN_API_KEY.

The recommended path. Point the OpenAI SDK at the Respan gateway and call any Google PaLM model.

from openai import OpenAI
client = OpenAI(
    api_key="YOUR_RESPAN_API_KEY",
    base_url="https://api.respan.ai/api",
)
response = client.chat.completions.create(
    model="palm/chat-bison",
    messages=[{"role": "user", "content": "Hello, Google PaLM!"}],
)
print(response.choices[0].message.content)

More integrations

Google PaLM models work with every Respan gateway integration:

Switch models

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

client.chat.completions.create(model="palm/chat-bison", messages=messages)
client.chat.completions.create(model="gemini/gemini-3.8-flash", messages=messages)
client.chat.completions.create(model="openai/gpt-6-sol", messages=messages)

Use your own Google PaLM key (BYOK)

Google PaLM credentials are required. Configure them in Respan or pass them with each request using one of the options below.

1

Open Providers

Go to the Providers page.

2

Add Google PaLM

Select Google PaLM and paste your google_palm.api_key.

3

Load balancing (Optional)

Add multiple credential sets and use Load balancing weight to distribute traffic across them.

Override credentials per model (Optional)

Use credential_override when one model on a request should use a different Google PaLM key than the default.

{
  "customer_credentials": {
    "google_palm": { "api_key": "YOUR_GOOGLE_PALM_API_KEY" }
  },
  "credential_override": {
    "palm/chat-bison": { "api_key": "ANOTHER_GOOGLE_PALM_API_KEY" }
  }
}

Log without proxying (Optional)

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

import requests
requests.post(
    "https://api.respan.ai/api/request-logs/create/",
    headers={
        "Authorization": "Bearer YOUR_RESPAN_API_KEY",
        "Content-Type": "application/json",
    },
    json={
        "model": "palm/chat-bison",
        "prompt_messages": [{"role": "user", "content": "Hello, how are you?"}],
        "completion_message": {"role": "assistant", "content": "Hello from Google PaLM through Respan."},
        "cost": 0.001,
        "generation_time": 1.2,
        "customer_params": {"customer_identifier": "user_123"},
    },
)

See the logging guide for the full setup.