$DEV/COSTS
Discounts
Models & APIs / Nscale Serverless Inference API pricing Verified 13 Nov 2026, 12:00 UTC Source docs.nscale.com/docs/ai-services/models

Nscale Serverless Inference API pricing

by Nscaleper 1M tokens
$0.47 / 1M outputQwen3.8 Flash Next (Nscale) · the cheapest model

Nscale Serverless Inference API costs $0.15–$1.40 per 1M input tokens and $0.47–$4.40 per 1M output tokens. Output tokens cost several times more than input, so long answers drive the bill.

Estimate my bill
Cheapest output$0.47Qwen3.8 Flash Next (Nscale) · per 1M
Top model$4.40GLM 5.3 (Nscale) · per 1M output

Every model, per 1M tokens

USD list price, before batch or volume discounts
ModelInputOutputCached inputContext
GLM 5.3 (Nscale)$1.40$4.40——
Mistral Large 3 675B (Nscale)$1.00$2.50——
Qwen3.8 27B (Nscale)$0.20$2.50——
Qwen3.8 Flash Next (Nscale)$0.15$0.47——
Bill estimate

What will you pay?

$5.80
per month on GLM 5.3 (Nscale)

Other model APIs

Compare all models →
AI21 Jamba API pricingQwen API pricingClaude API pricingArcee API pricingAtlas Cloud API pricingBaseten Model APIs pricingCerebras Inference API pricingChutes API pricingCloudflare Workers AI API pricingCrusoe Managed Inference API pricingDeepInfra API pricingDeepSeek API pricingFireworks AI API pricingFriendliAI API pricingGemini API pricingGroq API pricingHyperbolic API pricingInference.net API pricingLiquid AI LFM API pricingMiniMax API pricingMistral API pricingKimi API pricingNovita AI API pricingOpenAI API pricingParasail API pricingReka API pricingSambaNova API pricingSiliconFlow API pricingTogether AI API pricingUpstage Solar API pricingVenice API pricingWriter Palmyra API pricingGrok API pricingGLM API (Z.ai) pricing
Prices from docs.nscale.com/docs/ai-services/models How we collect prices Some links are affiliate links; they never change the prices or the order shown. Disclosure