Skip to main content
Watch: I Built an AI App Without Leaving Databricks

API compatibility - 5 documented limits

Google Gemini API API compatibility

Google Gemini API documents an OpenAI-compatible API at https://generativelanguage.googleapis.com/v1beta/openai/ (chat/completions, embeddings, images/generations, videos, batches and models). Its docs do not mention an Anthropic-compatible endpoint. The docs list 5 limitations: 5 for the OpenAI-compatible layer.

Verified against Google Gemini API's own documentation. Not documented means the docs read that day do not say; it never means No.

Compare every provider in the API compatibility matrix.

OpenAI-compatible API

Supported
Base URL
https://generativelanguage.googleapis.com/v1beta/openai/
Endpoints
  • chat/completions
  • embeddings
  • images/generations
  • videos
  • batches
  • models
Auth
Authorization: Bearer $GEMINI_API_KEY
Notes
Docs say the OpenAI library support is still in beta. reasoning_effort maps to Gemini thinking_level/thinking_budget; Gemini-only features go through extra_body (cached_content, thinking_config, etc.). service_tier supports flex and priority. Docs recommend calling the Gemini API directly if you are not already on the OpenAI libraries.

From the docs

Gemini models are accessible using the OpenAI libraries (Python and TypeScript / Javascript) along with the REST API, by updating three lines of code and using your Gemini API key.
ai.google.dev/gemini-api/docs/openai

Anthropic-compatible API

Not documented
Notes
The Gemini API docs read today document an OpenAI compatibility layer only; they do not mention an Anthropic-compatible endpoint.

Checked: ai.google.dev/gemini-api/docs/openai

Documented limitations

Parameters, content types and features Google Gemini API's docs say its compatibility layers ignore, reject or change, each with the line it comes from. A layer with nothing listed may still differ in ways the docs do not spell out.

OpenAI-compatible layer5

  • OpenAI library support is in beta

    Support for the OpenAI libraries is still in beta while we extend feature support.
    ai.google.dev/gemini-api/docs/openai

  • reasoning cannot be turned off for Gemini 2.5 Pro or Gemini 3 models

    If you want to disable thinking, you can set reasoning_effort to "none" for 2.5 models. Reasoning cannot be turned off for Gemini 2.5 Pro or 3 models.
    ai.google.dev/gemini-api/docs/openai

  • reasoning_effort and thinking_level/thinking_budget cannot be combined

    Note that reasoning_effort and thinking_level/thinking_budget overlap functionality, so they can't be used at the same time.
    ai.google.dev/gemini-api/docs/openai

  • images: unlisted parameters silently ignored

    Supported parameters include prompt, model, n, size, and response_format. Any other parameters not listed here or in the extra_body section will be silently ignored by the compatibility layer.
    ai.google.dev/gemini-api/docs/openai

  • batch: file upload/download not supported through OpenAI compat

    Compatibility for upload and download is currently not supported.
    ai.google.dev/gemini-api/docs/openai

Example from Google Gemini API's docs

Copied verbatim from the provider's documentation, placeholders included.

Provider example
from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

response = client.chat.completions.create(
    model="gemini-3.8-flash",
    messages=[
        {   "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "Explain to me how AI works"
        }
    ]
)

More on Google Gemini API

Use Google Gemini API in a coding tool

Newsletter

Know when a provider changes its API

One email per week. New models, new endpoints and the compatibility changes that break a base URL, and what they mean for your stack.