Skip to content
ModelCap

Inference provider

Novita: AI models and API pricing

Every tracked model Novita serves through OpenRouter, with Novita's own input and output price per 1M tokens, the context window it serves, disclosed quantization and measured endpoint uptime. Models with a position on a ModelCap board link to their model page, where every provider's deployment is listed side by side.

Snapshot as of 19 November 2026

Novita serves 34 tracked models through 34 endpoints as of 19 November 2026; the highest-ranked is GLM 5.3 (ModelCap Index #19); mean measured uptime is 93.44%.

Models served
34
On the ModelCap Index
15
Cheapest output price
$0.063/1M

Language models on Novita (34)

Ranked models first, in ModelCap Index order. Prices are the lowest Novita lists for the model; the endpoint count shows how many deployments carry it.

Language models served by Novita, with price, context, quantization and uptime
#ModelModelCap IndexInput $/1MOutput $/1MContextQuantizationUptime (30 min)Endpoints
1GLM 5.3Z.ai#1978.5$0.63$1.981Mfp8100.0%1
2GLM 5.3 FlashZ.ai#2676.4$0.084$0.281Mfp8100.0%1Open weights
3DeepSeek V4 Pro 0813DeepSeek#3473.0$0.99$2.971Mfp8100.0%1Open weights
4Gemma 4 31BGoogle#4270.7$0.14$0.40262Kbf16100.0%1Open weights
5Hy4 previewTencent#4569.5$0.834$2.501Mfp8—1Open weights
6Qwen3.5 397B A17BQwen#5267.2$0.60$3.60262K——1Open weights
7Gemma 4 26B A4BGoogle#6065.9$0.13$0.40262Kbf160.00%1Open weights
8Qwen3.8 27BQwen#6863.1$0.42$3.001M—100.0%1Open weights
9Kimi K2 ThinkingMoonshot AI#7162.3$0.60$2.50262Kbf16100.0%1
10DeepSeek V4.1 Flash 1017DeepSeek#9258.5$0.12$0.481Mfp8100.0%1Open weights
11Qwen3.5-122B-A10BQwen#9956.7$0.40$3.20262Kbf16100.0%1Open weights
12Step 3.7 FlashStepFun#12851.6$0.20$1.15262Kfp8100.0%1Open weights
13GLM 4.6VZ.ai#15146.1$0.30$0.90131Kbf16100.0%1Open weights
14GLM 4.5 AirZ.ai#15445.1$0.13$0.85131Kbf16100.0%1Open weights
15Qwen3 VL 30B A3B InstructQwen#18438.7$0.20$0.70131Kbf16100.0%1Open weights
16Kimi K2.7 CodeMoonshot AI—$0.912$3.84262Kint4100.0%1
17DeepSeek V4 Flash 0731DeepSeek—$0.409$1.231Mfp8100.0%1Open weights
18DeepSeek V4 Pro 0423DeepSeek—$1.28$2.561Mfp8100.0%1Open weights
19DeepSeek V4.1 FlashDeepSeek—$0.12$0.481Mfp8100.0%1Open weights
20GLM 4.5VZ.ai—$0.60$1.8066Kfp8100.0%1Open weights
21GLM 4.6Z.ai—$0.55$2.20205Kbf16100.0%1Open weights
22GLM 4.7Z.ai—$0.60$2.20205Kfp8100.0%1Open weights
23GLM 4.7 FlashZ.ai—$0.07$0.40200Kbf163.33%1Open weights
24GLM 5Z.ai—$1.00$3.20203Kfp8—1Open weights
25GLM 5.1Z.ai—$1.38$4.40205Kfp8100.0%1Open weights
26GLM 5.2Z.ai—$0.65$2.041Mfp8100.0%1Open weights
27Hy3Tencent—$0.14$0.58262K—100.0%1Open weights
28Kimi K2 0711Moonshot AI—$0.57$2.30131Kfp8100.0%1
29Kimi K2 0905Moonshot AI—$0.60$2.50262Kfp8100.0%1
30Kimi K2.5Moonshot AI—$0.57$2.85262K—100.0%1
31Kimi K2.6Moonshot AI—$0.80$3.40262K——1
32Ling 3.0 FlashInclusionAI—$0.021$0.063262K—100.0%1Open weights
33Ling 3.1 FlashInclusionAI—$0.045$0.1351M—100.0%1Open weights
34Qwen3.5-27BQwen—$0.30$2.40262Kbf16100.0%1Open weights

Novita on ModelCap: common questions

How many AI models does Novita serve?

34 tracked models as of 19 November 2026: 34 language models (15 with a public ModelCap Index position), across 34 live endpoints observed through OpenRouter.

What is the best model available on Novita?

GLM 5.3 from Z.ai is the highest-ranked language model Novita serves, at ModelCap Index position #19 and $1.98 per 1M output tokens on Novita. The table lists every model in Index order.

What is the cheapest model on Novita?

Ling 3.0 Flash at $0.063 per 1M output tokens ($0.021 per 1M input), the lowest positive language-token price Novita lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.

Which Novita model has the largest context window?

GLM 5.3, served with a 1M-token context window on Novita. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.

How reliable is Novita?

Mean measured uptime across Novita endpoints is 93.44% over the last 30 minutes, as reported by OpenRouter at the time of the snapshot. Per-model uptime is in the table; it is a live operational signal, not a service-level guarantee.

Where do the Novita prices come from?

From the OpenRouter catalogue entry for each Novita endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where Novita exposes several deployments of one model at different prices, the table shows the lowest and notes the count; the model page lists each deployment.

How current is this page?

This page uses the published ModelCap snapshot dated 19 November 2026. Publication and page updates happen separately. Offers retained from a failed refresh are marked stale in the data and are not counted here.

Explore further