Prueba de incorporación de key proveedor

NVIDIA | verificar key inventory fit

NVIDIA verificar key inventory fit decides whether a key can move from identification into inventory, pricing, routing, and launch. TestKey starts with 11 covered models, ruta global, sample models Llama 3.1 Nemotron 70B Instruct · Llama 3.1 Nemotron Ultra 253B v1 · Llama 3.3 Nemotron Super 49B V1.5, then verifies with read-only probes.

Proveedor

NVIDIA

ruta global

Cobertura de modelos

Llama 3.1 Nemotron 70B Instruct · Llama 3.1 Nemotron Ultra 253B v1 · Llama 3.3 Nemotron Super 49B V1.5

Dimensión de prueba

verificar key inventory fit

inventory-fit

Señal de onboarding

11 models can become inventory candidates

nvidia

Read-only probes

current_key

Sample metrics

key_valid / requests_total / runtime_model / runtime_model_allowed

Ten capabilities

operational actions / model permission matrix / limit matrix

Resumen de onboarding proveedor

Proveedor

NVIDIA

Dimensión de prueba

inventory-fit

Cobertura de modelos

Solo lectura. Datos eliminados tras 5 minutos.

Por qué importa esta prueba

Proveedor: NVIDIA
Cobertura de modelos: 11
Dimensión de prueba: verificar key inventory fit

Cómo probarlo

Solo lectura. Datos eliminados tras 5 minutos.

Identify the real provider first, then verify verificar key inventory fit; do not treat OpenAI-compatible as real OpenAI by default.
Use 11 covered models as candidates, then read /models, balance, error bodies, and limit headers.
11 models can become inventory candidates

Siguiente acción

NVIDIA verificar key inventory fit should become an action: add provider config, fill pricing, import inventory, set route, add monitoring, or send to human review.

Solo lectura. Datos eliminados tras 5 minutos.
Señal de onboarding: 11 models can become inventory candidates
Cobertura de modelos: Llama 3.1 Nemotron 70B Instruct · Llama 3.1 Nemotron Ultra 253B v1 · Llama 3.3 Nemotron Super 49B V1.5

Diez capacidades de key

NVIDIA has 1 read-only account probes configured, currently supporting operational actions / model permission matrix / limit matrix / continuous monitoring / key identity / capability matrix. These anchors feed the real TestKey detection path, not just admin display.

Read-only probes: current_key, used to prove provider identity, models, balance, or subscription state.
Sampleable metrics: key_valid / requests_total / runtime_model / runtime_model_allowed / tokens_limit / bucket_start / token_role / token_scopes.
Ten-capability anchors: operational actions / model permission matrix / limit matrix / continuous monitoring / key identity.

Abrir checker

Solo lectura. Datos eliminados tras 5 minutos.

Abrir proveedores

NVIDIA

Abrir modelos

Llama 3.1 Nemotron 70B Instruct · Llama 3.1 Nemotron Ultra 253B v1 · Llama 3.3 Nemotron Super 49B V1.5