Nebius AI Studio pricing

15 text models on Nebius, from $0.06 to $2.00 per 1M input tokens.

Updated

Running an agent on these models? abracadabra shows which tasks it finishes and where the rest stop.

15 models

Kimi K3.1 Pro

Moonshot AI1.05M contextText and image inputAdded 23 Oct 2026

Input
$2.00
Output
$10.00
Cached
$0.20
Batch
–

GLM 5.3

Z.ai1.05M contextText inputAdded 18 Aug 2026

Input
$1.40
Output
$4.40
Cached
$0.26
Batch
–

Qwen3.8 27B

Qwen1M contextText and image inputAdded 14 Aug 2026

Input
$0.45
Output
$3.00
Cached
$0.10
Batch
–

GLM 5.2

Z.ai1.05M contextText inputAdded 16 Jun 2026

Input
$1.40
Output
$4.40
Cached
$0.14
Batch
–

Nemotron 3 Nano 30B A3B

NVIDIA262K contextText inputAdded 14 Dec 2025

Input
$0.06
Output
$0.24
Cached
$0.012
Batch
–

Qwen3 30B A3B Instruct 2507

Qwen262K contextText inputAdded 29 Jul 2025

Input
$0.10
Output
$0.30
Cached
$0.10
Batch
–

Gemma 3 27B

Google110K contextText and image inputAdded 12 Mar 2025

Input
$0.10
Output
$0.30
Cached
$0.04
Batch
–

Prices in US dollars. Token prices are per 1 million tokens. abracadabra compiles them from each provider’s listing on OpenRouter, the LiteLLM price list and the providers’ own pricing pages, and refreshes them daily. The dataset is free to use: /api/ai-pricing.

All Nebius models

Text models

See which tasks your agent finishes.

A price says what a call costs. abracadabra reads every conversation your agent has and shows the topics people bring, the tasks that get done and the turn where the rest stop.

Free to start, no card. Or open the playground.