PipeLLM logo
Back to approved models

Approved model profile_

Googleactive

Gemini 3 Pro Image Preview

[Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and high-fidelity visual synthesis. The model generates context-rich graphics, from...

gemini-3-pro-image-preview
Open Relay View integration
relay/request.mjsready to route
const completion = await client.chat.completions.create({
  model: "gemini-3-pro-image-preview",
  messages: [
    { role: "user",
      content: "Plan a multi-step task" }
  ]
});
policy checked provider selected
CONTEXT1M contextprompt window
MAX OUTPUT65Kper response
INPUT$2.00 / Mtoken price
OUTPUT$12.00 / Mtoken price

Route configuration_

Call this model through its native API.

Use the documented HTTP endpoint and request body for this model.

ENDPOINThttps://api.pipellm.aiUse the native HTTP request format for this model.

NATIVE API · NO CONVERSION

Native HTTP/v1/chat/completionsDocs Use this native API directly. Protocol conversion is not supported.
MODEL IDgemini-3-pro-image-previewUse this in every request
GOVERNANCEPolicy controlledApprovals and tool rules apply
PROVIDER AVAILABILITY2 routes
ProviderContextMax outputDiscountInput / MOutput / M
GCP Vertex1M context65K—$2.00 / M$12.00 / M
Vertex AIN/AN/A—$2.00 / M$12.00 / M
Displayed pricing is per one million tokens and may vary by provider.
SUPPORTED SURFACESactive
input: textinput: imageoutput: textoutput: image

Relay governs model access with the same routing policy that Lens keeps visible and auditable.