Back to approved models
Googleactiverelay/request.mjsready to route CONTEXT100K contextprompt window MAX OUTPUT100Kper response INPUT$2.00 / Mtoken price OUTPUT$10.00 / Mtoken price
Approved model profile_
Gemini 4 Argon
Gemini 4 Argon is Google's premier reasoning model, engineered to handle advanced analytical challenges. It is specifically designed for sophisticated software engineering workflows as well as demanding scientific and mathematical problem-solving tasks. Built to support autonomous multi-step...
gemini-4-argonPOST https://api.pipellm.aigenerateContent
Authorization: Bearer $PIPELLM_API_KEY
Content-Type: application/json
Model: gemini-4-argon
See the provider documentation for request parameters.Route configuration_
Call this model through its native API.
Use the documented HTTP endpoint and request body for this model.
https://api.pipellm.aiUse the native HTTP request format for this model.NATIVE API · NO CONVERSION
Native HTTPgenerateContentDocs Use this native API directly. Protocol conversion is not supported.gemini-4-argonUse this in every requestPROVIDER AVAILABILITY1 route
| Provider | Context | Max output | Discount | Input / M | Output / M |
|---|---|---|---|---|---|
| Vertex AI | 100K context | 100K | — | $2.00 / M | $10.00 / M |
SUPPORTED SURFACESactive
input: textoutput: texttool usecache controlcomputer use
Relay governs model access with the same routing policy that Lens keeps visible and auditable.
