DEPRECATED
Retired 2026-08-27 — 34 days ago. Requests to this identifier are expected to fail.
state=dead sunset=2026-08-27 days_remaining=-34 severity=critical sources=litellm,openrouter evidence_tier=catalog confirmed_by_endpoint=false documented_by_provider=false replacement=none corroborated=yes divergent_fields=none checked=2026-09-30 15:40Z
nvidia/nemotron-3-ultra-550b-a55b
Vendor: nvidia. Tracked by 2 of 5 sources.
What each source reports
| Source | ID | Context | Max out | In $/Mtok | Out $/Mtok | Sunset |
|---|---|---|---|---|---|---|
| litellm | openrouter/nvidia/nemotron-3-ultra-550b-a55b | 262,144 | 182,520 | $0.6 | $2.4 | 2026-08-27 |
| openrouter | nvidia/nemotron-3-ultra-550b-a55b | 262,144 | 182,520 | $0.6 | $2.4 | — |
Change history
| Severity | Change | What | Detected |
|---|---|---|---|
| info | deprecated | together_ai/nvidia/nemotron-3-ultra-550b-a55b: deprecation announced for 2026-08-27 (date already passed) | 2026-09-30 |
| low | added | new model together_ai/nvidia/nemotron-3-ultra-550b-a55b (512,288 ctx) | 2026-09-24 |
| medium | removed | [one catalog only — litellm, openrouter still list it] together_ai/nvidia/nemotron-3-ultra-550b-a55b is no longer listed by this source — calls to it are expected to fail | 2026-09-23 |
| low | modified | openrouter/nvidia/nemotron-3-ultra-550b-a55b: max_output_tokens raised 32,768 to 182,520 | 2026-09-19 |
| info | repriced | openrouter/nvidia/nemotron-3-ultra-550b-a55b: input_price_per_mtok $0.62/Mtok to $0.60/Mtok | 2026-09-19 |
| info | repriced | openrouter/nvidia/nemotron-3-ultra-550b-a55b: output_price_per_mtok $3.12/Mtok to $2.40/Mtok | 2026-09-19 |
| info | repriced | openrouter/nvidia/nemotron-3-ultra-550b-a55b: cache_read_price_per_mtok $0.19/Mtok to $0.12/Mtok | 2026-09-19 |
| low | modified | nvidia/nemotron-3-ultra-550b-a55b: max_output_tokens raised 32,768 to 182,520 | 2026-09-19 |
| info | repriced | nvidia/nemotron-3-ultra-550b-a55b: input_price_per_mtok $0.62/Mtok to $0.60/Mtok | 2026-09-19 |
| info | repriced | nvidia/nemotron-3-ultra-550b-a55b: output_price_per_mtok $3.12/Mtok to $2.40/Mtok | 2026-09-19 |
| info | repriced | nvidia/nemotron-3-ultra-550b-a55b: cache_read_price_per_mtok $0.19/Mtok to $0.12/Mtok | 2026-09-19 |
| high | modified | nvidia/nemotron-3-ultra-550b-a55b: max_output_tokens cut 182,520 to 32,768 | 2026-09-17 |
| medium | repriced | nvidia/nemotron-3-ultra-550b-a55b: output_price_per_mtok $2.40/Mtok to $3.12/Mtok | 2026-09-17 |
| medium | repriced | nvidia/nemotron-3-ultra-550b-a55b: cache_read_price_per_mtok $0.12/Mtok to $0.19/Mtok | 2026-09-17 |
| low | repriced | nvidia/nemotron-3-ultra-550b-a55b: input_price_per_mtok $0.60/Mtok to $0.62/Mtok | 2026-09-17 |
| low | modified | nvidia/nemotron-3-ultra-550b-a55b: max_output_tokens raised 32,768 to 182,520 | 2026-09-16 |
| info | repriced | nvidia/nemotron-3-ultra-550b-a55b: input_price_per_mtok $0.62/Mtok to $0.60/Mtok | 2026-09-16 |
| info | repriced | nvidia/nemotron-3-ultra-550b-a55b: output_price_per_mtok $3.12/Mtok to $2.40/Mtok | 2026-09-16 |
| info | repriced | nvidia/nemotron-3-ultra-550b-a55b: cache_read_price_per_mtok $0.19/Mtok to $0.12/Mtok | 2026-09-16 |
| high | modified | nvidia/nemotron-3-ultra-550b-a55b: max_output_tokens cut 182,520 to 32,768 | 2026-09-16 |
| medium | repriced | nvidia/nemotron-3-ultra-550b-a55b: output_price_per_mtok $2.40/Mtok to $3.12/Mtok | 2026-09-16 |
| medium | repriced | nvidia/nemotron-3-ultra-550b-a55b: cache_read_price_per_mtok $0.12/Mtok to $0.19/Mtok | 2026-09-16 |
| low | repriced | nvidia/nemotron-3-ultra-550b-a55b: input_price_per_mtok $0.60/Mtok to $0.62/Mtok | 2026-09-16 |
| low | modified | nvidia/nemotron-3-ultra-550b-a55b: max_output_tokens raised 32,768 to 182,520 | 2026-09-14 |
| info | repriced | nvidia/nemotron-3-ultra-550b-a55b: input_price_per_mtok $0.62/Mtok to $0.60/Mtok | 2026-09-14 |
| info | repriced | nvidia/nemotron-3-ultra-550b-a55b: output_price_per_mtok $3.12/Mtok to $2.40/Mtok | 2026-09-14 |
| info | repriced | nvidia/nemotron-3-ultra-550b-a55b: cache_read_price_per_mtok $0.19/Mtok to $0.12/Mtok | 2026-09-14 |
| low | added | new model nebius/nvidia/Nemotron-3-Ultra-550b-a55b (1,048,576 ctx) | 2026-09-06 |
| low | added | new model openrouter/nvidia/nemotron-3-ultra-550b-a55b (262,144 ctx) | 2026-09-06 |
| high | modified | nvidia/nemotron-3-ultra-550b-a55b: max_output_tokens cut 182,520 to 32,768 | 2026-09-04 |
| medium | repriced | nvidia/nemotron-3-ultra-550b-a55b: output_price_per_mtok $2.40/Mtok to $3.12/Mtok | 2026-09-04 |
| medium | repriced | nvidia/nemotron-3-ultra-550b-a55b: cache_read_price_per_mtok $0.12/Mtok to $0.19/Mtok | 2026-09-04 |
| low | repriced | nvidia/nemotron-3-ultra-550b-a55b: input_price_per_mtok $0.60/Mtok to $0.62/Mtok | 2026-09-04 |
| low | modified | nvidia/nemotron-3-ultra-550b-a55b: max_output_tokens raised 32,768 to 182,520 | 2026-09-02 |
| info | repriced | nvidia/nemotron-3-ultra-550b-a55b: input_price_per_mtok $0.62/Mtok to $0.60/Mtok | 2026-09-02 |
| info | repriced | nvidia/nemotron-3-ultra-550b-a55b: output_price_per_mtok $3.12/Mtok to $2.40/Mtok | 2026-09-02 |
| info | repriced | nvidia/nemotron-3-ultra-550b-a55b: cache_read_price_per_mtok $0.19/Mtok to $0.12/Mtok | 2026-09-02 |
| medium | repriced | nvidia/nemotron-3-ultra-550b-a55b: output_price_per_mtok $2.20/Mtok to $3.12/Mtok | 2026-09-02 |
| medium | repriced | nvidia/nemotron-3-ultra-550b-a55b: cache_read_price_per_mtok $0.10/Mtok to $0.19/Mtok | 2026-09-02 |
| low | modified | nvidia/nemotron-3-ultra-550b-a55b: max_output_tokens raised 16,384 to 32,768 | 2026-09-02 |