API ReferenceModels

Retrieve a model

Returns the full per-model schema: pricing rows, parameter table (name, type, default, min/max, allowed values, descriptions, conditional flags), capability flags, and modalities. Same data the docs site and the playground render from. This endpoint is public and returns only tenant-agnostic model metadata.

Path parameters

model_idstringRequired
Canonical model slug.

Response

Full model schema with parameters.
idstringOptional
objectstringOptional
display_namestringOptional
providerstringOptional

Lowercase provider / maker slug.

descriptionstringOptional
aliaseslist of stringsOptional

Alternate model ids the API also accepts for this model, such as legacy dotted versions (“deepseek-v3.2”), provider-prefixed forms (“deepseek/deepseek-v4-pro”), and upstream ids. Requests, billing, and GET /v1/models/{model} all resolve them to the canonical id. Empty for models with no alternate ids.

typeenumOptional
Technical model type.
categoryenumOptional
Catalog grouping the model is filtered under.
native_inferencebooleanOptional

True when EmpirioLabs serves the model on its own managed GPU infrastructure (the Native Inference designation shown in the catalog). Always present. Combine it with category to select native models, for example native text models.

weight_precisionstring or nullOptional

Exact served weight precision, verbatim from the catalog and identical to the value shown on the model’s documentation page (for example “FP8 weights + FP8 KV”). Null when unknown or not applicable. The OpenRouter-format listing (GET /v1/models?format=openrouter) carries a standardized quantization enum derived from this same value.

context_windowinteger or nullOptional
context_lengthinteger or nullOptional

OpenRouter-convention alias of context_window. Same value, surfaced under the field name third-party tools look for.

modalitieslist of stringsOptional
Combined input plus output modality labels.
input_modalitieslist of stringsOptional
output_modalitieslist of stringsOptional
featureslist of stringsOptional

Capability tags such as reasoning, vision, or video_generation.

max_output_tokensinteger or nullOptional
capabilitiesobjectOptional
Boolean capability flags for quick feature checks.
supported_endpointslist of stringsOptional

API routes this model accepts, for example POST /v1/chat/completions.

pricingobject or list of objectsOptional

OpenRouter-style pricing. Single object for flat-rate models, or a 2-item array for context-tiered chat models. All values are USD strings. Per-token fields (prompt, completion, input_cache_read) are per-token, not per-million; flat fields (image, request) are per-event.

For models with three or more context-based tiers the array is a best-effort 2-tier summary (cheapest base + highest-context tier). See pricing_rows for the full tier-by-tier breakdown.

pricing_rowslist of objectsOptional

EmpirioLabs’ display-friendly breakdown including tool fees, per-image/second/minute rates, and full tier ladders. Use this when you need the complete picture.

model_released_atdate or nullOptional
Exact public release date of the underlying model when verified. Null when the date has not been verified yet.
deprecation_datedateOptional

Scheduled retirement date. Present only when a retirement has been scheduled; the model is removed from the catalog and stops routing on this date. Absent means no retirement is planned. Poll this field to migrate before a model you depend on goes away.

deprecatedbooleanOptional

Present and true only alongside deprecation_date. Absent for every model with no scheduled retirement.

is_newbooleanOptional
discountobject or nullOptional

Display discount summary. When present, label uses the Save up to X% format and percent is the maximum advertised savings for the model.

parameterslist of objectsOptional

Errors

404
Not Found Error