GET

/v1/models/nvidia/nvidia-nvidia-llama-3-1-nemotron-70b-instruct

provider nvidiastatus activefirst seen Apr 15, 2025last seen 11m ago
rawIdnvidia/llama-3.1-nemotron-70b-instruct
displayName—
idnvidia-nvidia-llama-3-1-nemotron-70b-instruct
activitychat
schemaEndpointIdno bound generation route
releasedAtno release date reported by the provider
firstSeenAt1744675200 — Apr 15, 2025
lastSeenAt1794561501 — 11m ago
pricingnot published by this provider’s list endpoint
modalities{"input":["text"],"output":["text"]}
requestMap{"thinking":null,"maxTokensField":"max_tokens","developerRole":null,"replayReasoningContent":null,"store":null,"strictTools":null,"sessionAffinity":null,"cacheControl":null,"toolStream":null,"reasoningEffort":null}
contextWindow · maxOutput · capabilities · knowledgeCutoff · openWeights · weightsUrl · providerMetadatanot published by this provider’s list endpoint

Endpoints & schemas

GET /v1/schemas/nvidia →
endpointactivity
nvidia/llama-3.1-nemotron-70b-instruct
input · output
chat

endpoints matching this model — the provider has more, see /v1/schemas/nvidia

Sources

fieldrecorded source
modalitieshttps://build.nvidia.com/nvidia/llama-3_1-nemotron-70b-instruct

docs-derived

modalities

Source trace
cc9a4ae69cb88b2ad362599826d089905f45b730bab6cbaca46e5cf6996c4897
schemaEndpointIdhttps://build.nvidia.com/nvidia/llama-3_1-nemotron-70b-instruct

docs-derived

paths

Source trace
c282c3e90e3ade2a3ed067c91ed64fcd85b121bff5ad12bdcc02d6f16bb058f1
requestMapFields.maxTokensFieldhttps://build.nvidia.com/nvidia/llama-3_1-nemotron-70b-instruct

docs-derived

max_tokens

Source trace
c282c3e90e3ade2a3ed067c91ed64fcd85b121bff5ad12bdcc02d6f16bb058f1
pricinghttps://docs.api.nvidia.com/nim/docs/product

Value unknown (null); not published in the checked source · checked 2026-10-06.

cacheReadhttps://docs.api.nvidia.com/nim/docs/product

Value unknown (null); not published in the checked source · checked 2026-10-06.

activitySource unknown — no source URL recorded.
contextWindowSource unknown — no source URL recorded.
maxOutputSource unknown — no source URL recorded.
capabilitiesSource unknown — no source URL recorded.
reasoningSource unknown — no source URL recorded.
requestMapSource unknown — no source URL recorded.

Use it

shell
$ curl https://modelschemas.com/v1/schemas/nvidia/chat/nvidia/llama-3.1-nemotron-70b-instruct # request schema
$ curl -X POST https://modelschemas.com/v1/validate -d '{"provider":"nvidia","endpointId":"nvidia/llama-3.1-nemotron-70b-instruct","payload":{…}}'
$ curl -X POST https://modelschemas.com/v1/estimate -d '{"provider":"nvidia","model":"nvidia/llama-3.1-nemotron-70b-instruct","usage":{"input_tokens":1200,"output_tokens":400}}'