Nemotron 3 Ultra pricing across providers
Across tracked provider offerings, input runs $0.500–$0.625 per million tokens and output $2.20–$3.13 per million tokens. The cheapest tracked provider offering for a typical agentic mix (2.5% input, 97% cached input, 0.5% output) is DeepInfra at $0.120 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 3 of 3 offerings publish a cache-read rate; 3 of 3 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to Nemotron 3 Ultra
Is this the right model for your workload? Compare open-weight picks and providers for your use case →
Daily price history
Loading price history…
Daily snapshots are retained for up to 90 days; history begins with the first recorded snapshot.
Provider offerings for Nemotron 3 Ultra
Ranked by effective cost at a typical agentic mix. Quantized and tier variants stay separate rows.
| Provider | Quant | Input $/M | Output $/M | Cache $/M | Blended $/M | Uptime (30m) |
|---|---|---|---|---|---|---|
| DeepInfra | fp4 | $0.500 | $2.20 | $0.100 | $0.120 | 100.00% |
| Baseten | fp4 | $0.600 | $2.40 | $0.120 | $0.143 | 100.00% |
| Venice | fp8 | $0.625 | $3.13 | $0.188 | $0.213 | 100.00% |
Provider-offering pricing refreshed 2026-10-29. Uptime is the 30-minute endpoint metric where a provider publishes it. Verify rates on the provider's official pricing page before committing spend.