InferIndex
Language, English, EN
Account

ProvidersNscale

Nscale

The 20 models Nscale serves, direct and through aggregators, with the price and conditions of each offer.

Prices seen via Hugging Face

No training on promptsNumber of this provider's offers whose published policy says prompts are not used for training, out of all its offers.
Not published
Cheapest on InferIndexModels for which this provider has the lowest price on InferIndex.
10 / 20 models

Offers

AllAt the lowestAbove the lowest 10 of 20 offers
Nscale: LLM API prices
Model BlendedA single price that mixes input and output: 3 input tokens for 1 output token, per million tokens. It makes offers easy to rank; your real cost depends on your own mix.$/1M In$/1M Out$/1M ObservationGap to the lowest price we track for this model. CtxThe maximum amount of text, counted in tokens, the model can take in and write in a single request. Past this limit, the request is refused or cut. Offer
Llama 3.1 8B Instruct (meta-llama/llama-3.1-8b-instruct) $0.06  $0.06 $0.06 2.4× Lowest on InferIndex: $0.025. 131k See pricing at Hugging Face (opens in a new tab)
gpt-oss-120b (openai/gpt-oss-120b) $0.175 $0.10 $0.40 2.9× Lowest on InferIndex: $0.06. 131k See pricing at Hugging Face (opens in a new tab)
gpt-oss-20b (openai/gpt-oss-20b) $0.088 $0.05 $0.20 2.3× Lowest on InferIndex: $0.036. 131k See pricing at Hugging Face (opens in a new tab)
Qwen3 14B (qwen/qwen3-14b) $0.103 $0.07 $0.20 +7% Lowest on InferIndex: $0.091. 41k See pricing at Hugging Face (opens in a new tab)
Qwen3 235B A22B (qwen/qwen3-235b-a22b) $0.30  $0.20 $0.60 +96% Lowest on InferIndex: $0.153. 32k See pricing at Hugging Face (opens in a new tab)
Qwen3 235B A22B Instruct 2507 (qwen/qwen3-235b-a22b-2507) $0.30  $0.20 $0.60 3.6× Lowest on InferIndex: $0.078. 33k See pricing at Hugging Face (opens in a new tab)
Qwen3 32B (qwen/qwen3-32b) $0.123 $0.08 $0.25 +2% Lowest on InferIndex: $0.12. 41k See pricing at Hugging Face (opens in a new tab)
Qwen3.8 27B (qwen/qwen3.8-27b) $0.775 $0.20 $2.50 5.5× Lowest on InferIndex: $0.14. 1M See pricing at Hugging Face (opens in a new tab)
Qwen3.8 Flash (qwen/qwen3.8-flash)fp8How finely the model's numbers are stored on the provider's servers. Lower precision (fp8, fp4) is cheaper to run and can slightly change answer quality; "unknown" means the provider doesn't say. $0.23  $0.15 $0.47 +28% Lowest on InferIndex: $0.18. 1M See pricing at Hugging Face (opens in a new tab)
GLM 5.3 (z-ai/glm-5.3) $2.15  $1.40 $4.40 4.7× Lowest on InferIndex: $0.43. 1M See pricing at Hugging Face (opens in a new tab)

Hugging Face Every offer of this provider is sold by Hugging Face.

Blended = (3 × input + output) / 4, per million tokens. Prices in USD, converted at the ECB rate when the provider bills in another currency.