GET
/v1/models/baseten/baseten-nvidia-nvidia-nemotron-3-ultra-550b-a55b
Accept:
| rawId | nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B |
| displayName | Nemotron 3 Ultra |
| id | baseten-nvidia-nvidia-nemotron-3-ultra-550b-a55b |
| activity | chat |
| schemaEndpointId | v1/chat/completions |
| releasedAt | 1780594202 — Jun 4, 2026 |
| firstSeenAt | 1780531200 — Jun 4, 2026 |
| lastSeenAt | 1795367775 — 9m ago |
| pricing | $0.6 / 1M input · $2.4 / 1M output → open calculator input_tokens (usage) · output_tokens (usage) · cache_read_tokens (usage) |
| contextWindow | 202800 |
| maxOutput | 202800 |
| modalities | {"input":["text"],"output":["text"]} |
| capabilities | {"frequency_penalty":true,"max_tokens":true,"presence_penalty":true,"response_format":true,"seed":true,"stop":true,"temperature":true,"top_p":true,"tools":true,"tool_choice":true,"top_k":true,"reasoning":true,"reasoning_effort":true,"structured_outputs":true} |
| knowledgeCutoff · openWeights · weightsUrl · requestMap · providerMetadata | not published by this provider’s list endpoint |
Endpoints & schemas
GET /v1/schemas/baseten →| endpoint | activity |
|---|---|
| v1/chat/completions | chat |
endpoints matching this model — the provider has more, see /v1/schemas/baseten
Use it
shell
$ curl https://modelschemas.com/v1/schemas/baseten/chat/v1/chat/completions # request schema
$ curl -X POST https://modelschemas.com/v1/validate -d '{"provider":"baseten","endpointId":"v1/chat/completions","payload":{…}}'
$ curl -X POST https://modelschemas.com/v1/estimate -d '{"provider":"baseten","model":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","usage":{"input_tokens":1200,"output_tokens":400}}'