Novita model pricing.

prices as of · 92 models · 144 prices

Serves open-weight models on its own GPUs; publishes list and promotional prices side by side.

Novita is a host selling 92 models, from $0.08 per million tokens for Llama 3.2 1B Instruct, read on 16 Sept 2026.

Novita prices

Kind of provider

Host

based in US

Where it runs

not stated

no regions published

How you pay

not stated

no payment terms published

Free tier

none published

nothing given away

Where Novita's prices land, and why

Novita publishes 144 prices we can compare, and 50 of them are below the list price for that model. 40 of those have a published reason behind them, so they rank like any other price. The other 2 sit below list on models whose weights are closed, with nothing published to account for the gap, so they are listed here in full and ranked nowhere on the site. Nobody here has read its terms; whether promo prices have end dates yet, so treat what it says about itself as its own claim.

Novita does not say whether it trains on what you send it. It does not say how long it keeps requests.

not yet checked: terms; whether promo prices have end dates · privacy policy ↗ · status page ↗

Models to start with

all 144 prices ↓

Everything Novita sells, against the list price

Cheapest first inside each group. The share is this row against the price the lab that trained the model charges.

Cheaper, and we know why

40 prices

Below list, with a published reason: hosting the open weights, a regional price list, credits, a stated discount.

  • Llama 3.2 1B Instruct

    Meta · 60k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.02 / $0.02in / out per M

    0.28×of list price

  • Llama 3.1 8B Instruct

    Meta · 131k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.02 / $0.05in / out per M

    0.48×of list price

  • Llama 3.1 8B Instruct

    Meta · 131k context

    Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.

    $0.02 / $0.05in / out per M

    0.48×of list price

  • Llama 3.2 3B Instruct

    Meta · 131k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.03 / $0.05in / out per M

    0.29×of list price

  • Qwen3 8B

    Alibaba Cloud · 131k context

    Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.

    $0.04 / $0.14in / out per M

    0.20×of list price

  • Qwen2.5 7B Instruct

    Alibaba Cloud · 131k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.07 / $0.07in / out per M

    0.23×of list price

  • Mistral Nemo

    Mistral AI · 128k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.04 / $0.17in / out per M

    0.48×of list price

  • Mistral Nemo

    Mistral AI · 128k context

    Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.

    $0.04 / $0.17in / out per M

    0.48×of list price

  • Qwen3-Coder 30B-A3B Instruct

    Alibaba Cloud · 262k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.07 / $0.27in / out per M

    0.13×of list price

  • Qwen3-Coder 30B-A3B Instruct

    Alibaba Cloud · 262k context

    Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.

    $0.07 / $0.27in / out per M

    0.13×of list price

  • MiMo-V2-Flash

    Xiaomi · 262k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.10 / $0.30in / out per M

    0.86×of list price

  • Qwen3 30B A3B Instruct 2507

    Alibaba Cloud · 262k context

    Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.

    $0.09 / $0.45in / out per M

    0.79×of list price

  • Qwen3 VL 8B Instruct

    Alibaba Cloud · 262k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.08 / $0.50in / out per M

    0.92×of list price

  • Qwen3 32B

    Alibaba Cloud · 131k context

    Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.

    $0.10 / $0.45in / out per M

    0.15×of list price

  • Gemma 4 26B A4B IT

    Google · 262k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.13 / $0.40in / out per M

    0.75×of list price

  • Gemma 4 26B A4B IT

    Google · 262k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision bf16.

    $0.13 / $0.40in / out per M

    0.75×of list price

  • Qwen3 235B-A22B

    Alibaba Cloud · 131k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.09 / $0.58in / out per M

    0.17×of list price

  • DeepSeek V3.2

    DeepSeek · 164k context

    4% under the list price, an ordinary reseller margin.

    $0.27 / $0.40in / out per M

    0.97×of list price

  • DeepSeek V3.2

    DeepSeek · 164k context

    4% under the list price, an ordinary reseller margin.

    $0.27 / $0.40in / out per M

    0.97×of list price

  • GLM-4.5-Air

    Z.ai · 131k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.13 / $0.85in / out per M

    0.73×of list price

  • GLM-4.5-Air

    Z.ai · 131k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision bf16.

    $0.13 / $0.85in / out per M

    0.73×of list price

  • Qwen3 235B-A22B

    Alibaba Cloud · 131k context

    Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.

    $0.20 / $0.80in / out per M

    0.29×of list price

  • Qwen2.5 72B Instruct

    Alibaba Cloud · 131k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.38 / $0.40in / out per M

    0.16×of list price

  • MiniMax-M2.7

    MiniMax · 205k context

    10% under the list price, an ordinary reseller margin.

    $0.27 / $1.08in / out per M

    0.90×of list price

  • Qwen3-Next 80B-A3B Instruct

    Alibaba Cloud · 131k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.15 / $1.50in / out per M

    0.56×of list price

  • Qwen3-Next 80B-A3B Instruct

    Alibaba Cloud · 131k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision bf16.

    $0.15 / $1.50in / out per M

    0.56×of list price

  • Qwen3-Next 80B-A3B (Thinking)

    Alibaba Cloud · 131k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.15 / $1.50in / out per M

    0.26×of list price

  • Qwen3 Coder Next

    Alibaba Cloud · 262k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.20 / $1.50in / out per M

    0.88×of list price

  • Qwen3 Coder Next

    Alibaba Cloud · 262k context

    Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.

    $0.20 / $1.50in / out per M

    0.88×of list price

  • Qwen3-VL 235B-A22B

    Alibaba Cloud · 131k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.30 / $1.50in / out per M

    0.49×of list price

showing the 30 cheapest of 40 · every row in the open dataset

Same price as the maker

102 prices

The same price the maker charges, sold by someone else.

  • Gemma 3 12B

    Google · 131k context

    The same price OpenRouter charges.

    $0.05 / $0.10in / out per M

    0.83×of list price

  • gpt-oss-20b

    OpenAI · 131k context

    33% above OpenRouter's price.

    $0.04 / $0.15in / out per M

    1.23×of list price

  • gpt-oss-20b

    OpenAI · 131k context

    33% above OpenRouter's price.

    $0.04 / $0.15in / out per M

    1.23×of list price

  • Nemotron 3 Nano 30B A3B

    NVIDIA · 262k context

    The same price OpenRouter charges.

    $0.05 / $0.20in / out per M

    1.00×of list price

  • Nemotron 3 Nano 30B A3B

    NVIDIA · 262k context

    The same price OpenRouter charges.

    $0.05 / $0.20in / out per M

    1.00×of list price

  • Ling 3.0 Flash

    InclusionAI · 262k context

    186% above OpenRouter's price.

    $0.06 / $0.18in / out per M

    2.86×of list price

  • Ling 3.0 Flash

    InclusionAI · 262k context

    186% above OpenRouter's price.

    $0.06 / $0.18in / out per M

    2.86×of list price

  • gpt-oss-120b

    OpenAI · 131k context

    35% above OpenRouter's price.

    $0.05 / $0.25in / out per M

    1.42×of list price

  • gpt-oss-120b

    OpenAI · 131k context

    35% above OpenRouter's price.

    $0.05 / $0.25in / out per M

    1.42×of list price

  • Gemma 3 27B

    Google · 131k context

    49% above OpenRouter's price.

    $0.12 / $0.20in / out per M

    0.81×of list price

  • Gemma 3 27B

    Google · 131k context

    49% above OpenRouter's price.

    $0.12 / $0.20in / out per M

    0.81×of list price

  • GLM-4.7-Flash

    Z.ai · 200k context

    16% above OpenRouter's price.

    $0.07 / $0.40in / out per M

    1.05×of list price

  • GLM-4.7-Flash

    Z.ai · 200k context

    16% above OpenRouter's price.

    $0.07 / $0.40in / out per M

    1.05×of list price

  • Llama-3.3-70B-Instruct

    Meta · 128k context

    35% above OpenRouter's price.

    $0.14 / $0.40in / out per M

    1.30×of list price

  • Llama-3.3-70B-Instruct

    Meta · 128k context

    35% above OpenRouter's price.

    $0.14 / $0.40in / out per M

    1.30×of list price

  • Gemma 4 31B IT

    Google · 262k context

    56% above OpenRouter's price.

    $0.14 / $0.40in / out per M

    1.34×of list price

  • Gemma 4 31B IT

    Google · 262k context

    56% above OpenRouter's price.

    $0.14 / $0.40in / out per M

    1.34×of list price

  • GLM-5.3-Flash

    Z.ai · 1M context

    76% above Z.ai's price.

    $0.13 / $0.44in / out per M

    1.76×of list price

  • MiMo-V2.5

    Xiaomi · 1M context

    20% above Xiaomi's price.

    $0.17 / $0.34in / out per M

    1.20×of list price

  • MiMo-V2.5

    Xiaomi · 1M context

    20% above Xiaomi's price.

    $0.17 / $0.34in / out per M

    1.20×of list price

  • Qwen3.8 Flash

    Alibaba Cloud · 1M context

    The same price Alibaba Cloud charges.

    $0.15 / $0.47in / out per M

    1.00×of list price

  • GLM-5.3-Flash

    Z.ai · 1M context

    100% above Z.ai's price.

    $0.15 / $0.50in / out per M

    2.00×of list price

  • Hy3

    Tencent · 262k context

    6% above Tencent's price.

    $0.14 / $0.58in / out per M

    1.08×of list price

  • DeepSeek V3.2 Exp

    DeepSeek · 164k context

    The same price OpenRouter charges.

    $0.27 / $0.41in / out per M

    1.00×of list price

  • DeepSeek V3.2 Exp

    DeepSeek · 164k context

    The same price OpenRouter charges.

    $0.27 / $0.41in / out per M

    1.00×of list price

  • Qwen3-VL 30B-A3B

    Alibaba Cloud · 131k context

    The same price Alibaba Cloud charges.

    $0.20 / $0.70in / out per M

    0.93×of list price

  • Qwen3-VL 30B-A3B

    Alibaba Cloud · 131k context

    The same price Alibaba Cloud charges.

    $0.20 / $0.70in / out per M

    0.93×of list price

  • Qwen2.5 72B Instruct

    Alibaba Cloud · 33k context

    6% above OpenRouter's price.

    $0.38 / $0.40in / out per M

    1.04×of list price

  • Qwen2.5 72B Instruct

    Alibaba Cloud · 33k context

    6% above OpenRouter's price.

    $0.38 / $0.40in / out per M

    1.04×of list price

  • Qwen3 VL 30B A3B Thinking

    Alibaba Cloud · 262k context

    The same price Alibaba Cloud charges.

    $0.20 / $1in / out per M

    0.53×of list price

showing the 30 cheapest of 102 · every row in the open dataset

Cheaper, and nobody says why

2 prices · never ranked

Below list on a closed model with nothing to account for it. Shown, never ranked, never a pick.

  • Qwen-MT Plus

    Alibaba Cloud · 16k context

    0.10× Alibaba Cloud's list price on a closed model, and nobody says why. Listed, never ranked.

    $0.25 / $0.75in / out per M

    0.10×of list price

  • Qwen3.7 Max

    Alibaba Cloud · 1M context

    0.50× Alibaba Cloud's list price on a closed model, and nobody says why. Listed, never ranked.

    $1.25 / $3.75in / out per M

    0.50×of list price

Frequently asked

What is Novita?
Serves open-weight models on its own GPUs; publishes list and promotional prices side by side. It sells 92 of the models we track, and trades as Novita AI, based in US.
Is Novita cheaper than buying from the maker?
50 of its 144 prices sit below the list price for the model, and 40 of those have a published reason behind them, so they can lead a ranking. 2 are listed and never ranked.
Does Novita train on what you send it?
Novita does not say whether it trains on what you send it. It does not say how long it keeps requests.
How current are these Novita prices?
They come from its own public catalog, last read 16 Sept 2026. Prices exclude tax.