GET
/v1/models/together/together-nvidia-nemotron-3-ultra-550b-a55b
Accept:
| rawId | nvidia/nemotron-3-ultra-550b-a55b |
| displayName | NVIDIA Nemotron 3 Ultra 550B A55B NVFP4 |
| id | together-nvidia-nemotron-3-ultra-550b-a55b |
| activity | chat |
| schemaEndpointId | no bound generation route |
| firstSeenAt | 1786755208 — Aug 15, 2026 |
| lastSeenAt | 1795375183 — 15m ago |
| contextWindow | 512288 |
| pricing | {"inputs":{"input_tokens":{"param":"input_tokens","bound":"usage","kind":"number"},"output_tokens":{"param":"output_tokens","bound":"usage","kind":"number"},"cache_read_tokens":{"param":"cache_read_tokens","bound":"usage","kind":"number","default":0}},"tables":{"rate":{"base":{"input_tokens":6e-7,"output_tokens":0.0000036000000000000003,"cache_read_tokens":2.0000000000000002e-7}}},"price":{"+":[{"if":[{">":[{"var":"input_tokens"},0]},{"*":[{"var":"input_tokens"},{"lookup":{"table":"rate","keys":["base","input_tokens"]}}]},0]},{"if":[{">":[{"var":"output_tokens"},0]},{"*":[{"var":"output_tokens"},{"lookup":{"table":"rate","keys":["base","output_tokens"]}}]},0]},{"if":[{">":[{"var":"cache_read_tokens"},0]},{"*":[{"var":"cache_read_tokens"},{"lookup":{"table":"rate","keys":["base","cache_read_tokens"]}}]},0]}]},"examples":[],"source":{"url":"https://api.together.xyz/v1/models","hash":"9fe2f188bd293aecee0e8439d5999fc00cc626a34934aeeeb1dd793544a3a89b","extractedAt":"2026-10-07T23:13:26.624Z"}} |
| capabilities | {"max_tokens":true,"stop":true,"temperature":true,"top_p":true,"top_k":true,"presence_penalty":true,"frequency_penalty":true,"seed":true,"response_format":true,"tools":true,"tool_choice":true,"structured_outputs":true} |
| maxOutput · modalities | not published by this provider’s list endpoint |
Endpoints & schemas
GET /v1/schemas/together →| endpoint | activity | schemas |
|---|---|---|
| audio/speech | audio | requestinput responseoutput |
| audio/transcriptions | audio | requestinput responseoutput |
| audio/translations | audio | requestinput responseoutput |
| v1/audio/speech | audio | requestinput responseoutput |
| v1/audio/transcriptions | audio | requestinput responseoutput |
| v1/audio/translations | audio | requestinput responseoutput |
| chat/completions | chat | requestinput responseoutput |
| completions | chat | requestinput responseoutput |
| v1/chat/completions | chat | requestinput responseoutput |
| v1/completions | chat | requestinput responseoutput |
| embeddings | embeddings | requestinput responseoutput |
| v1/embeddings | embeddings | requestinput responseoutput |
| images/generations | image | requestinput responseoutput |
| v1/images/generations | image | requestinput responseoutput |
| v2/videos | video | requestinput responseoutput |
| videos | video | requestinput responseoutput |
Use it
shell
$ curl https://modelschemas.com/v1/schemas/together/audio/audio%2Fspeech # request schema
$ curl -X POST https://modelschemas.com/v1/validate -d '{"provider":"together","endpointId":"audio/speech","payload":{…}}'