Novita AI pricing

32 text models on Novita AI, from $0.07 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.

32 models

Hy3

Tencent262K contextText inputAdded 6 Jul 2026

Input
$0.14
Output
$0.58
Cached
$0.035
Batch
–

GLM 5.2

Z.ai1.05M contextText inputAdded 16 Jun 2026

Input
$0.6496
Output
$2.0416
Cached
$0.1206
Batch
–

Kimi K2.6

Moonshot AI262K contextText and image inputAdded 20 Apr 2026

Input
$0.80
Output
$3.40
Cached
$0.16
Batch
–

GLM 5

Z.ai203K contextText inputAdded 11 Feb 2026

Input
$1.00
Output
$3.20
Cached
$0.20
Batch
–

Kimi K2.5

Moonshot AI262K contextText and image inputAdded 27 Jan 2026

Input
$0.57
Output
$2.85
Cached
$0.095
Batch
–

GLM 4.6V

Z.ai131K contextText and image inputAdded 8 Dec 2025

Input
$0.30
Output
$0.90
Cached
$0.055
Batch
–

Kimi K2 Thinking

Moonshot AI262K contextText inputAdded 6 Nov 2025

Input
$0.60
Output
$2.50
Cached
$0.15
Batch
–

Kimi K2 0905

Moonshot AI262K contextText inputAdded 4 Sept 2025

Input
$0.60
Output
$2.50
Cached
–
Batch
–

GLM 4.5V

Z.ai66K contextText and image inputAdded 11 Aug 2025

Input
$0.60
Output
$1.80
Cached
$0.11
Batch
–

Kimi K2 0711

Moonshot AI131K contextText inputAdded 11 Jul 2025

Input
$0.57
Output
$2.30
Cached
–
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 Novita AI models

Text models

No longer listed

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.