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 11 August 2026

Novita serves 46 tracked models through 46 endpoints as of 11 August 2026; the highest-ranked is GLM 5.2 (ModelCap Index #13); mean measured uptime is 97.18%.

Models served

On the ModelCap Index

Cheapest output price

$0.03/1M

Language models on Novita (46)

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 5.2Z.ai	#1370.5	$0.938	$2.95	1M	fp8	99.87%	1Open weights
2	Hy3Tencent	#1864.9	$0.14	$0.58	262K	—	100.0%	1Open weights
3	Gemma 4 31BGoogle	#2062.8	$0.14	$0.40	262K	bf16	94.32%	1Open weights
4	Qwen3.5 397B A17BQwen	#2261.6	$0.60	$3.60	262K	—	—	1Open weights
5	MiniMax M3MiniMax	#2361.3	$0.30	$1.20	1M	fp8	99.66%	1
6	Gemma 4 26B A4BGoogle	#2559.2	$0.13	$0.40	262K	bf16	99.86%	1Open weights
7	Kimi K2 ThinkingMoonshot AI	#2757.2	$0.60	$2.50	262K	bf16	97.74%	1
8	Qwen3 235B A22B Instruct 2507Qwen	#3153.6	$0.09	$0.58	131K	fp8	100.0%	1Open weights
9	Qwen3.5-122B-A10BQwen	#3351.8	$0.40	$3.20	262K	bf16	100.0%	1Open weights
10	Qwen3 VL 235B A22B InstructQwen	#3451.5	$0.30	$1.50	131K	bf16	95.35%	1Open weights
11	Qwen3 Next 80B A3B InstructQwen	#4046.6	$0.15	$1.50	131K	bf16	100.0%	1Open weights
12	Qwen3 VL 235B A22B ThinkingQwen	#4245.4	$0.98	$3.95	131K	bf16	—	1Open weights
13	Qwen3 235B A22B Thinking 2507Qwen	#4345.3	$0.30	$3.00	131K	fp8	—	1Open weights
14	Step 3.7 FlashStepFun	#4445.3	$0.20	$1.15	262K	fp8	—	1Open weights
15	Qwen3 Coder 480B A35BQwen	#4643.7	$0.38	$1.55	262K	fp8	95.48%	1Open weights
16	GLM 4.5 AirZ.ai	#5437.5	$0.13	$0.85	131K	bf16	98.85%	1Open weights
17	Ring-2.6-1TInclusionAI	#5737.1	$0.075	$0.625	262K	—	100.0%	1
18	GLM 4.6VZ.ai	#5836.9	$0.30	$0.90	131K	bf16	99.90%	1Open weights
19	GLM 4.7 FlashZ.ai	#6236.2	$0.07	$0.40	200K	bf16	89.69%	1Open weights
20	Gemma 3 27BGoogle	#6533.9	$0.119	$0.20	98K	bf16	89.41%	1
21	Ling-3.0-flashInclusionAI	#6633.4	$0.021	$0.063	262K	—	100.0%	1Open weights
22	Qwen3 Coder 30B A3B InstructQwen	#7428.4	$0.07	$0.27	160K	fp8	94.83%	1Open weights
23	Ling-2.6-1TInclusionAI	#7627.6	$0.075	$0.625	262K	—	100.0%	1
24	ERNIE 4.5 VL 424B A47BBaidu	#10425.5	$0.42	$1.25	123K	fp16	100.0%	1Open weights
25	Ling 3.0 TinyInclusionAI	#17825.0	Free	Free	262K	—	98.95%	1Open weights
26	Llama 4 MaverickMeta	#18123.5	$0.27	$0.85	1M	fp8	100.0%	1
27	Llama 4 ScoutMeta	#18821.7	$0.18	$0.59	131K	bf16	99.84%	1
28	Kimi K2.7 CodeMoonshot AI	#18921.5	$0.912	$3.84	262K	int4	—	1
29	Qwen3 Coder NextQwen	#19021.2	$0.20	$1.50	262K	fp8	100.0%	1Open weights
30	Llama 3.3 70B InstructMeta	#19320.3	$0.135	$0.40	12K	bf16	98.21%	1
31	Nemotron 3 Nano 30B A3BNVIDIA	#19519.9	$0.05	$0.20	262K	fp4	87.69%	1
32	Qwen2.5 72B InstructQwen	#19816.9	$0.38	$0.40	32K	bf16	—	1
33	Mistral NemoMistral AI	#20311.9	$0.04	$0.17	60K	fp8	64.79%	1Open weights
34	R1 Distill Llama 70BDeepSeek	#2174.2	$0.80	$0.80	8K	bf16	100.0%	1Open weights
35	Qwen3 VL 30B A3B InstructQwen	#2184.1	$0.20	$0.70	131K	bf16	98.66%	1Open weights
36	Llama 3.1 8B InstructMeta	#2193.7	$0.02	$0.05	16K	fp8	99.82%	1
37	GLM 4.5VZ.ai	—	$0.60	$1.80	66K	fp8	—	1Open weights
38	GLM 4.6Z.ai	—	$0.55	$2.20	205K	bf16	99.37%	1Open weights
39	GLM 4.7Z.ai	—	$0.54	$1.98	205K	fp8	91.85%	1Open weights
40	GLM 5Z.ai	—	$1.00	$3.20	203K	fp8	100.0%	1Open weights
41	GLM 5.1Z.ai	—	$1.38	$4.40	205K	fp8	—	1Open weights
42	Kimi K2.5Moonshot AI	—	$0.57	$2.85	262K	—	99.46%	1
43	Kimi K2.6Moonshot AI	—	$0.80	$3.40	262K	—	99.37%	1
44	Ling-2.6-flashInclusionAI	—	$0.01	$0.03	262K	—	100.0%	1
45	MiniMax M1MiniMax	—	$0.55	$2.20	1M	bf16	100.0%	1
46	Qwen3.5-27BQwen	—	$0.30	$2.40	262K	bf16	100.0%	1Open weights

Novita on ModelCap: common questions

How many AI models does Novita serve?

46 tracked models as of 11 August 2026: 46 language models (36 with a public ModelCap Index position), across 46 live endpoints observed through OpenRouter.

What is the best model available on Novita?

GLM 5.2 from Z.ai is the highest-ranked language model Novita serves, at ModelCap Index position #13 and $2.95 per 1M output tokens on Novita. The table lists every model in Index order.

What is the cheapest model on Novita?

Ling-2.6-flash at $0.03 per 1M output tokens ($0.01 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 5.2, 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 97.18% 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?

It re-renders within a minute of every dataset refresh; this snapshot was published 11 August 2026. Offers retained from a failed refresh are marked stale in the data and are not counted here.