Back to approved models
Googleactiverelay/request.mjsready to route CONTEXT200K contextprompt window MAX OUTPUT64Kper response INPUT$1.3 / Mtoken price OUTPUT$2.5 / Mtoken price
Approved model profile_
Gemini 2.5 Pro
[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-2.5-proconst completion = await client.chat.completions.create({
model: "gemini-2.5-pro",
messages: [
{ role: "user",
content: "Plan a multi-step task" }
]
});Route configuration_
Use the model through the contract you already have.
PipeLLM resolves provider access, policy, and supported model capabilities without changing the interface your application calls.
https://api.pipellm.ai/openaiOpenAI-compatible routegemini-2.5-proUse this in every requestPROVIDER AVAILABILITY1 route
| Provider | Context | Max output | Input / M | Output / M |
|---|---|---|---|---|
| GCP Vertex | 200K context | 64K | $1.3 / M | $2.5 / M |
SUPPORTED SURFACESactive
input: textinput: imageoutput: texttool usecache controlcomputer use
Relay governs model access with the same routing policy that Lens keeps visible and auditable.
