OpenModelsHQ

Novita

Novita serves 26 open models from 7 labs on OpenRouter, in 26 offers. Of the 23 models it shares with other providers, it has the lowest blended price on 3 (2 of them tied). It is the only provider for 3 models. Its median blended price is $0.9988 (₹94) per million tokens, blended 3:1 input to output. Its most common precision is 8-bit (15 of 26 offers).

Models served
26
7 labs · 26 offers
Median blended / 1M
$0.9988
₹94 · 3:1 input to output
Lowest price, shared models
13%
3 of 23, 2 tied · only provider for 3
Max context
1,048,576
8-bit 15 · 16-bit 6 · Not listed 4 · 4-bit 1

Company and policies

Headquarters listed by OpenRouter
United States
Datacenter countries listed by OpenRouter
Not listed

Provider-level locations do not guarantee where a particular request is processed. Check the provider's terms for data handling. Directory source, checked 14 Nov 2026.

Precision and price rank

Precision mix
Precision as the provider lists it on OpenRouter. 4-bit covers FP4, NVFP4, MXFP4 and INT4; 16-bit covers BF16 and FP16.
Precision mix: data
Offers4-bit8-bit16-bitNot listedTotal
Offers1156426
Price rank on shared models
One entry per model that two or more providers serve, using Novita's cheapest offer. A tie for the lowest price counts as lowest. Not shown: 3 models with no other provider.
Price rank on shared models: data
RankModels
Lowest or tied3
2nd1
3rd4
4th or lower15

Every model Novita serves 26

USD and INR per million tokens
PrecisionLabPricing
$0.6138₹58$0.4092₹39$1.2276₹11619 of 231,048,576FP8DeepSeekAll providers
$2.00₹189$1.60₹151$3.20₹3029 of 121,048,576FP8DeepSeekAll providers
$1.485₹140$0.99₹93$2.97₹2805 of 201,048,576FP8DeepSeekAll providers
$0.3412₹32$0.195₹18$0.78₹7415 of 281,048,576FP8DeepSeekAll providers
$0.2888₹27$0.165₹16$0.66₹6218 of 381,048,576FP8DeepSeekAll providers
$0.1975₹19$0.13₹12$0.40₹3811 of 15262,144BF16GoogleAll providers
$0.205₹19$0.14₹13$0.40₹389 of 15262,144BF16GoogleAll providers
$0.31₹29$0.13₹12$0.85₹801 of 3Lowest131,072BF16Z.ai (Zhipu)All providers
$0.9625₹91$0.55₹52$2.20₹2073 of 4204,800BF16Z.ai (Zhipu)All providers
$1.00₹94$0.60₹57$2.20₹2073 of 5204,800FP8Z.ai (Zhipu)All providers
$0.1525₹14$0.07₹6.60$0.40₹382 of 2200,000BF16Z.ai (Zhipu)All providers
$1.55₹146$1.00₹94$3.20₹3026 of 8202,800FP8Z.ai (Zhipu)All providers
$2.135₹201$1.38₹130$4.40₹4157 of 11204,800FP8Z.ai (Zhipu)All providers
$0.9976₹94$0.6496₹61$2.0416₹1936 of 241,048,576FP8Z.ai (Zhipu)All providers
$0.9675₹91$0.63₹59$1.98₹1878 of 371,048,576FP8Z.ai (Zhipu)All providers
$0.133₹13$0.084₹7.92$0.28₹268 of 371,048,576FP8Z.ai (Zhipu)All providers
$0.25₹24$0.14₹13$0.58₹553 of 4262,144Not listedTencent HunyuanAll providers
$1.2508₹118$0.834₹79$2.501₹2364 of 6Ties for lowest1,000,000FP8Tencent HunyuanAll providers
$1.0025₹95$0.57₹54$2.30₹2171 of 1Only provider131,072FP8Moonshot AIAll providers
$1.075₹101$0.60₹57$2.50₹2361 of 1Only provider262,144FP8Moonshot AIAll providers
$1.075₹101$0.60₹57$2.50₹2361 of 1Only provider262,144BF16Moonshot AIAll providers
$1.14₹107$0.57₹54$2.85₹2693 of 5262,144Not listedMoonshot AIAll providers
$1.45₹137$0.80₹75$3.40₹32111 of 15262,144Not listedMoonshot AIAll providers
$1.644₹155$0.912₹86$3.84₹3626 of 10262,144INT4Moonshot AIAll providers
$1.065₹100$0.42₹40$3.00₹28318 of 231,000,000Not listedAlibaba QwenAll providers
$0.4375₹41$0.20₹19$1.15₹1081 of 2Ties for lowest262,144FP8StepFunAll providers
Rank is this offer's position among the model's providers by blended price (3 parts input to 1 part output). 1 is the lowest. Equal prices are ordered by provider name and marked "Ties for lowest".

Where Novita is cheapest

3 of 23 models shared with other providers

Only provider for 3 models: Kimi-K2-Instruct, Kimi-K2-Instruct-0905, Kimi-K2-Thinking. With no other provider to compare, these are not counted as cheapest.

Novita questions

Which open models does Novita serve?

Novita serves 26 open models from 7 labs on OpenRouter. The most downloaded on Hugging Face are Qwen3.8-27B, gemma-4-31B-it and GLM-5.3-Flash. Prices were fetched 14 Nov 2026.

Is Novita the cheapest provider for any open model?

Yes, among models that other providers also serve. Novita has the lowest blended price on 3 of 23: lowest on GLM-4.5-Air, and ties for the lowest on Hy4-preview and Step-3.7-Flash. For GLM-4.5-Air it charges $0.31 (₹29) per million tokens, blended 3:1 input to output. It is also the only provider for 3 models, which we do not count as cheapest.

What precision does Novita serve models at?

Of its 26 offers, Novita lists 4-bit for 1, 8-bit for 15 and 16-bit for 6, and no precision for 4. Prices are in US dollars; we show rupees at ₹94.29 per $1.

About this data

Every number on this page comes from the endpoints OpenRouter lists for each model, fetched 14 Nov 2026. INR is shown beside USD at ₹94.29 per $1. Prices change, so check the provider before you build on a number.