Introducing the Universal Managed Agents API.Read the announcement
Google

Providers/Google

Google

Gemini — natively multimodal frontier models with massive context windows.

Operational
Model LabFrontier

Models on Brainbase

Gemini Flash

2 variants available1 new

gemini-3.5-flashNew
gemini-2.5-flash

Gemini Pro

1 variant available

gemini-2.5-pro

About

Google DeepMind's Gemini models are built multimodal from the ground up — text, images, audio, and video in a single context — with some of the largest context windows available.

On Brainbase, Gemini models are platform-billed and run inside any open harness: OpenCode or Qwen Code. Pick the harness that fits your workflow and point it at a Gemini slug per task.

Available on Brainbase:

  • Gemini Flash: Google's latency-optimized multimodal line with a million-token window, including Gemini 3.5 Flash, Gemini 2.5 Flash
  • Gemini Pro: Google DeepMind's reasoning flagship, including Gemini 2.5 Pro

Run these models in Codex, OpenCode, or Qwen Code — selected per task like any other platform model.

Try it on Brainbase

One API call boots a managed sandbox on the opencode harness pointed at gemini-3.5-flash. Hosting, scaling, and billing are handled for you.

curl -X POST https://api.brainbaselabs.com/v2/agents \
  -H "Authorization: Bearer $BRAINBASE_API_KEY" \
  -d '{
    "title": "my-agent",
    "runtime_kind": "opencode",
    "default_model": "gemini-3.5-flash"
  }'
runtime_kind/opencodemodel/gemini-3.5-flash