NVIDIA: Nemotron 3 SuperReasoning

nvidia
$0.4output / 1M tokens

Best price — Output ($/1M tokens)

Markets

One row per access path (venue → underlying provider). Prices are each venue's published list price; performance is measured by Artificial Analysis. Your actual bill may vary by routing settings, fallbacks, region / ZDR, long-context tiers, and request features (JSON mode, tools, vision).

#ProviderClassInput $/MOutput $/MCache ($/M Read)vs consensusTTFTThroughputUptime 24hRequests 24h
1
deepinfra
Direct host$0.09
$0.4
—-33.3% vs consensus
—
———
2
coreweave
Direct host$0.2
$0.8
—+33.3% vs consensus
994ms
reasoning 998ms
142.5 tps——
3
nebius
Direct host$0.3
$0.9
—+50.0% vs consensus
1.8s
reasoning 1.8s
252.1 tps——
4
openrouter → nebius
Reseller$0.3
$0.9
—+50.0% vs consensus
—
———
5
openrouter → deepinfra
Disabled by openrouter · disabled · bf16
Reseller$0.09
$0.4
—-33.3% vs consensus
—
———
6
openrouter → dekallm
Disabled by openrouter · disabled · fp8
Reseller$0.08
$0.45
—-25.0% vs consensus
—
———
7
openrouter → digitalocean
Disabled by openrouter · disabled · unknown
Reseller$0.21
$0.46
$0.06-24.2% vs consensus
—
———
8
baseten
Disabled by baseten · stale
Direct host$0.3
$0.75
$0.06+25.0% vs consensus
290ms
386.5 tps——
Source ecosystem
Loading…