Skip to content

Compare model prices

Input, output, cached and batch prices, every route and a month of tokens, side by side.

Nemotron 3 Nano 30B A3BNemotron 3.5 Lightning

A month of tokens

  • Nemotron 3 Nano 30B A3B$9.00
  • Nemotron 3.5 Lightning$10.10

100M input and 20M output tokens, list price. Use your own numbers.

Side by side

Nemotron 3 Nano 30B A3BNemotron 3.5 Lightning
Input per 1M$0.05$0.065
Output per 1M$0.2$0.18
Cached input$0.03n/a
Batch in / outn/an/a
Blended (3:1)$0.088$0.094
Context262K1M
Routes45
ReleasedDec 14, 2025Aug 11, 2026
Leadersboard scoren/an/a

On the price map

$0.03$0.1$0.3$1$3$10$30$100$0.03$0.1$0.3$1$3$10$30$100$300Input $ per 1M tokensOutput $ per 1M tokensxxZZDMOOOOOOOOOOOOOOOOZDGMMDMGDQMGGMMZGGDDGGGGGGGGMOOOZQAQQAQQNQAAAQAQxQQAQQAQAAAAQQQQxxxOOOOOOOOOOOOOOOOOAAOMNMQQQMGGMNQQQQQQQMNMMMMMQQQQQQQMQQQQxMMCZZZZZZZAPAAOAOOOOPOOOCDDDDDMDDMGGNZMOQQQMOOZZQMMQQQQQGGGMMMMMMOOOMPPQCAOCCOOOOOOMPQGGGZMDMMGMMQQQ
Size: context window, 8K to 2MEqual blended cost (3:1) 254 models, lower left is cheaper

Every route

Nemotron 3 Nano 30B A3B

Way to buyIn / out per 1M
Crusoe
fp8 · cached $0.03
$0.05 / $0.2Same as list
DeepInfra
fp4 · cached $0.025
$0.05 / $0.2Same as list
Novita AI
fp4
$0.05 / $0.2Same as list
Nebius
fp8
$0.06 / $0.24+20% vs list

Nemotron 3.5 Lightning

Way to buyIn / out per 1M
Darkbloom
int4
$0.065 / $0.18Same as list
Io Net
Default region · cached $0.033
$0.067 / $0.19+4% vs list
CoreWeave
bf16 · cached $0.04
$0.07 / $0.2+9% vs list
Phala
Default region · cached $0.04
$0.07 / $0.2+9% vs list
DeepInfra
bf16 · cached $0.04
$0.08 / $0.2+17% vs list

Price changes by email

Thursdays, only in weeks when an LLM API list price changed.

Double opt-in. Unsubscribe any time.