Model Rover

API Reference

Exact public endpoints, request contracts, and response behavior for the model gateway.

All inference APIs use the gateway Base URL configured for this deployment: http://127.0.0.1:11113

The gateway normalizes authentication, public model IDs, routing, billing, and request tracing while preserving the response dialect of the endpoint you call.

Use public model IDs

Send the complete model ID shown on the Models page, for example openai/gpt-5.2. Internal providers and upstream model IDs are never part of the public contract.

Start with a protocol

Endpoint catalog

MethodPathModeReference
GET/v1/modelsSynchronousList models
POST/v1/chat/completionsSynchronous or SSEChat Completions
POST/v1/responsesSynchronous or SSEResponses
POST/v1/embeddingsSynchronousEmbeddings
POST/v1/images/generationsSynchronous or SSEImage generation
POST/v1/images/editsSynchronous or SSEImage editing
POST/v1/messagesSynchronous or SSEAnthropic Messages
POST/v1/models/{model}:generateContentSynchronousGemini Generate Content
POST/v1beta/models/{model}:generateContentSynchronousGemini Generate Content
POST/v1/models/{model}:streamGenerateContentSSEGemini Generate Content
POST/v1beta/models/{model}:streamGenerateContentSSEGemini Generate Content
POST/v1beta/interactionsSynchronous, SSE, or asynchronous videoGemini Interactions
POST/v1/videos/generationsAsynchronousxAI video
POST/v1/videos/editsAsynchronousxAI video
POST/v1/videos/extensionsAsynchronousxAI video
POST/v1/models/{model}:predictLongRunningAsynchronousGemini video
POST/v1beta/models/{model}:predictLongRunningAsynchronousGemini video
POST/v1/contents/generations/tasksAsynchronousSeedance video
GET/v1/tasks/{taskId}Task lookupTasks and callbacks
GET/v1/contents/generations/tasks/{taskId}Seedance task lookupTasks and callbacks
DELETE/v1/contents/generations/tasks/{taskId}Seedance cancel or deleteTasks and callbacks

/v1 and /v1beta Gemini model methods use the same gateway behavior. The version segment only matches client SDK conventions; it does not select a different gateway feature set.

Compatibility contract

When the incoming protocol matches an available upstream endpoint, the gateway uses a pass-through path: it rewrites the model ID, applies platform limits, and preserves protocol-specific and newly introduced fields. When protocols differ, the gateway converts the shared text, multimodal input, tool-calling, generation, streaming, and usage fields through a canonical representation.

Fields that have no safe cross-protocol equivalent are omitted and named in the x-dropped-params response header. Use the model's native public protocol when a provider-specific feature must be preserved exactly.

Platform-managed behavior

The platform selects providers, routes, failover candidates, and paid service tiers. Client-supplied provider, routing, or route fields are rejected. Model-call POST requests also reject Idempotency-Key; see Authentication and errors and Tasks and callbacks for safe retry rules.

Help us improve this page

Found something unclear, outdated, or incorrect?

Last updated on