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. Rows link to the model page, where every provider's deployment is listed side by side.

Snapshot as of 1 October 2026

Novita serves 68 tracked models through 68 endpoints as of 1 October 2026; the highest-ranked is GLM 5.3 (ModelCap Index #11); mean measured uptime is 97.88%.

Models served

On the ModelCap Index

Cheapest output price

$0.05/1M

Language models on Novita (68)

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
#	Model	ModelCap Index	Input $/1M	Output $/1M	Context	Quantization	Uptime (30 min)	Endpoints
1	GLM 5.3Z.ai	#1180.9	$0.783	$2.46	1M	fp8	99.35%	1
2	DeepSeek V4.1 FlashDeepSeek	#1579.3	$0.30	$1.20	1M	fp8	99.85%	1Open weights
3	GLM 5.3 FlashZ.ai	#1778.9	$0.084	$0.28	1M	fp8	98.52%	1Open weights
4	DeepSeek V4 Pro 0813DeepSeek	#2476.4	$0.99	$2.97	1M	fp8	100.0%	1Open weights
5	MiMo-V2.6-FlashXiaomi	#2575.7	$0.14	$0.28	1M	fp8	99.53%	1Open weights
6	Hy4 previewTencent	#2673.8	$0.834	$2.50	1M	fp8	70.97%	1Open weights
7	DeepSeek V4 Flash Vision ExpDeepSeek	#2773.8	$0.44	$1.32	1M	—	—	1Open weights
8	Gemma 4 31BGoogle	#2872.9	$0.14	$0.40	262K	bf16	96.58%	1Open weights
9	Qwen3.8 27BQwen	#3968.9	$0.42	$3.00	1M	—	100.0%	1Open weights
10	MiniMax M3MiniMax	#4068.5	$0.30	$1.20	1M	fp8	99.87%	1
11	Gemma 4 26B A4BGoogle	#4168.4	$0.13	$0.40	262K	bf16	99.73%	1Open weights
12	Qwen3.5 397B A17BQwen	#4368.0	$0.60	$3.60	262K	—	—	1Open weights
13	MiMo-V2.5Xiaomi	#4468.0	$0.168	$0.336	1M	fp8	98.81%	1Open weights
14	Kimi K2.7 CodeMoonshot AI	#4965.9	$0.912	$3.84	262K	int4	100.0%	1
15	Ling 3.0 Flash VLInclusionAI	#5065.9	$0.021	$0.062	262K	bf16	100.0%	1Open weights
16	Kimi K2 ThinkingMoonshot AI	#5265.6	$0.60	$2.50	262K	bf16	100.0%	1
17	Ling 3.0 Flash FinInclusionAI	#5964.3	$0.042	$0.123	262K	—	100.0%	1Open weights
18	Ling 3.0 FlashInclusionAI	#6362.2	$0.021	$0.063	262K	—	100.0%	1Open weights
19	Qwen3 235B A22B Instruct 2507Qwen	#6462.1	$0.09	$0.58	131K	fp8	99.73%	1Open weights
20	R1 0528DeepSeek	#6761.5	$0.70	$2.50	164K	fp8	100.0%	1Open weights
21	Qwen3.5-122B-A10BQwen	#7759.5	$0.40	$3.20	262K	bf16	99.88%	1Open weights
22	Qwen3 VL 235B A22B InstructQwen	#7859.5	$0.30	$1.50	131K	bf16	94.71%	1Open weights
23	Qwen3 235B A22B Thinking 2507Qwen	#9654.8	$0.30	$3.00	131K	fp8	92.33%	1Open weights
24	Qwen3 Next 80B A3B InstructQwen	#9854.7	$0.15	$1.50	131K	bf16	84.09%	1Open weights
25	Qwen3 Coder 30B A3B InstructQwen	#9954.1	$0.07	$0.27	160K	fp8	100.0%	1Open weights
26	Qwen3 VL 235B A22B ThinkingQwen	#10153.8	$0.98	$3.95	131K	bf16	—	1Open weights
27	Qwen3 Coder NextQwen	#11053.3	$0.20	$1.50	262K	fp8	99.75%	1Open weights
28	Step 3.7 FlashStepFun	#11252.8	$0.20	$1.15	262K	fp8	99.02%	1Open weights
29	Qwen3 Coder 480B A35BQwen	#11551.9	$0.38	$1.55	262K	fp8	—	1Open weights
30	GLM 4.6VZ.ai	#12249.0	$0.30	$0.90	131K	bf16	99.67%	1Open weights
31	GLM 4.5 AirZ.ai	#12547.4	$0.13	$0.85	131K	bf16	100.0%	1Open weights
32	gpt-oss-120bOpenAI	#13244.6	$0.05	$0.25	131K	fp4	99.93%	1Open weights
33	Gemma 3 27BGoogle	#13344.5	$0.119	$0.20	98K	bf16	99.41%	1
34	gpt-oss-20bOpenAI	#16637.8	$0.04	$0.15	131K	fp4	99.83%	1Open weights
35	Llama 4 MaverickMeta	#17434.8	$0.27	$0.85	1M	fp8	100.0%	1
36	Llama 4 ScoutMeta	#17732.9	$0.18	$0.59	131K	bf16	100.0%	1
37	Llama 3.3 70B InstructMeta	#17832.4	$0.135	$0.40	12K	bf16	99.76%	1
38	Nemotron 3 Nano 30B A3BNVIDIA	#17931.8	$0.05	$0.20	262K	fp4	100.0%	1
39	Qwen2.5 72B InstructQwen	#18929.0	$0.38	$0.40	32K	bf16	99.84%	1
40	Llama 3.1 8B InstructMeta	#23313.5	$0.02	$0.05	16K	fp8	97.77%	1
41	Apodex 1.1 MiniApodex	—	Free	Free	262K	bf16	99.80%	1
42	ERNIE 4.5 VL 424B A47BBaidu	—	$0.42	$1.25	123K	fp16	100.0%	1Open weights
43	Ling 3.0 Flash SanteInclusionAI	—	Free	Free	262K	—	100.0%	1
44	Mistral NemoMistral AI	—	$0.04	$0.17	60K	fp8	79.05%	1Open weights
45	Qwen3 VL 30B A3B InstructQwen	—	$0.20	$0.70	131K	bf16	99.89%	1Open weights
46	DeepSeek V4 Flash 0423DeepSeek	—	$0.14	$0.28	1M	fp8	100.0%	1Open weights
47	DeepSeek V4 Flash 0731DeepSeek	—	$0.409	$1.23	1M	fp8	100.0%	1Open weights
48	DeepSeek V4 Pro 0423DeepSeek	—	$1.60	$3.20	1M	fp8	100.0%	1Open weights
49	GLM 4.5VZ.ai	—	$0.60	$1.80	66K	fp8	—	1Open weights
50	GLM 4.6Z.ai	—	$0.55	$2.20	205K	bf16	99.81%	1Open weights
51	GLM 4.7Z.ai	—	$0.54	$1.98	205K	fp8	99.62%	1Open weights
52	GLM 4.7 FlashZ.ai	—	$0.07	$0.40	200K	bf16	70.52%	1Open weights
53	GLM 5Z.ai	—	$1.00	$3.20	203K	fp8	100.0%	1Open weights
54	GLM 5.1Z.ai	—	$1.38	$4.40	205K	fp8	98.51%	1Open weights
55	GLM 5.2Z.ai	—	$0.65	$2.04	1M	fp8	99.86%	1Open weights
56	Hy3Tencent	—	$0.14	$0.58	262K	—	99.04%	1Open weights
57	Kimi K2 0711Moonshot AI	—	$0.57	$2.30	131K	fp8	100.0%	1
58	Kimi K2 0905Moonshot AI	—	$0.60	$2.50	262K	fp8	100.0%	1
59	Kimi K2.5Moonshot AI	—	$0.57	$2.85	262K	—	99.49%	1
60	Kimi K2.6Moonshot AI	—	$0.80	$3.40	262K	—	100.0%	1
61	MiMo-V2.5-ProXiaomi	—	$0.48	$0.96	1M	—	99.01%	1Open weights
62	MiniMax M1MiniMax	—	$0.55	$2.20	1M	bf16	—	1
63	MiniMax M2MiniMax	—	$0.30	$1.20	205K	fp8	—	1
64	MiniMax M2.1MiniMax	—	$0.30	$1.20	205K	fp8	—	1
65	MiniMax M2.5MiniMax	—	$0.30	$1.20	205K	fp8	100.0%	1
66	MiniMax M2.7MiniMax	—	$0.27	$1.08	205K	fp8	99.18%	1
67	Qwen3.5-27BQwen	—	$0.30	$2.40	262K	bf16	100.0%	1Open weights
68	R1DeepSeek	—	$0.70	$2.50	64K	fp8	100.0%	1Open weights

Novita on ModelCap: common questions

How many AI models does Novita serve?

68 tracked models as of 1 October 2026: 68 language models (40 with a public ModelCap Index position), across 68 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 #11 and $2.46 per 1M output tokens on Novita. The table lists every model in Index order.

What is the cheapest model on Novita?

Llama 3.1 8B Instruct at $0.05 per 1M output tokens ($0.02 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 97.88% 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 1 October 2026. Publication and page updates happen separately. Offers retained from a failed refresh are marked stale in the data and are not counted here.