Current comparison · website snapshot 2026-10-09T11:30:13+00:00

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B

Listed provider prices for this tracked model. Blended combines each offer’s input and output into one comparison number, not a prediction of your bill. Lower price does not imply identical revisions, service, speed or terms.

DeepInfra

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B

$0.50 input · $2.20 output · $0.93 blended USD per 1M tokens

See evidence

Saved listing evidence

This is the record used for this comparison, not a fresh price check. Collection is not independent verification.

Provider
DeepInfra
Exact listing ID
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
Input · USD per 1M tokens
0.5
Output · USD per 1M tokens
2.2
Collected
2026-10-09T11:30:04+00:00
Evidence verified
Not independently verified
Source state
live

Saved pricing fields

Only this listing, as collected. Field names and units are the provider’s; the rates above are normalized to USD per million tokens.

discount
Not stated
discount_ends_at
Not stated
short
Not stated
full
Not stated
table
Not stated
type
tokens
cents_per_input_token
5e-05
cents_per_output_token
0.00022
rate_per_input_token_cached
0.2
rate_per_input_token_cache_write
Not stated
rate_per_service_tier_priority
1.5
rate_per_service_tier_flex
0.8
rate_per_explicit_cache_write_token
{"5m": 1.25, "1h": 2.0}
explicit_cache_granularity_tokens
8192

View provider pricing ↗

Provider pages show current terms, which may have changed since this record was collected.

Open provider listing ↗

Verification date unknown · Collected 2026-10-09T11:30:04+00:00.

  • context: 262144
  • identity status: normalized_name
  • freshness: live

Price history

No archived price history is available for this comparison yet. This does not mean the model is new.