Inference provider
Nscale API pricing: every model, compared
We track 13 Nscale prices that other providers also sell. Nscale has the lowest listed price for 8 of them; for the rest, the table shows how much more you pay than at the cheapest provider.
Standard list prices in USD. Last price change Sep 28, 2026. How we rank.
LLMs, most widely offered first
Nscale LLM prices vs the cheapest provider
| Model | Rank | Cheapest elsewhere | Input / 1M | Output / 1M | Context | Source |
|---|---|---|---|---|---|---|
| Llama-3.3-70B-Instruct | #2 of 13 | Nebius Token Factoryyou pay 1% more here | $0.20 | $0.20 | - | Pricing page |
| Llama-3.1-8B-Instruct | #3 of 10 | Novita AIyou pay 9% more here | $0.03 | $0.03 | - | Pricing page |
| Llama 4 Scout 17B 16E Instruct | #2 of 7 | Lambdayou pay 124% more here | $0.09 | $0.29 | - | Pricing page |
| deepseek-r1-distill-llama-70b | #2 of 6 | DeepInfrayou pay 25% more here | $0.375 | $0.375 | - | Pricing page |
| Deepseek R1 Distill Qwen 32B | #1 of 5 | Nscale is cheapest | $0.15 | $0.15 | - | Pricing page |
| Qwen2.5 Coder 32B Instruct | #2 of 5 | Lambdayou pay 52% more here | $0.06 | $0.20 | - | Pricing page |
| Qwq 32B | #1 of 5 | Nscale is cheapest | $0.18 | $0.20 | - | Pricing page |
| deepseek-r1-distill-qwen-14b | #1 of 3 | Nscale is cheapest | $0.07 | $0.07 | - | Pricing page |
| deepseek-r1-distill-llama-8b | #1 of 2 | Nscale is cheapest | $0.025 | $0.025 | - | Pricing page |
| deepseek-r1-distill-qwen-1.5b | #1 of 2 | Nscale is cheapest | $0.09 | $0.09 | - | Pricing page |
| deepseek-r1-distill-qwen-7b | #1 of 2 | Nscale is cheapest | $0.20 | $0.20 | - | Pricing page |
| qwen2.5-coder-3b-instruct | #1 of 2 | Nscale is cheapest | $0.01 | $0.03 | - | Pricing page |
| qwen2.5-coder-7b-instruct | #1 of 2 | Nscale is cheapest | $0.01 | $0.03 | - | Pricing page |
Rank and difference use the blended price (3 input : 1 output tokens). Equal prices share a rank.
Ranked for your volume
Llama-3.3-70B-Instruct monthly cost by provider
Change the monthly tokens and the ranking updates instantly, using each provider's standard list price.
More requirements: caching, context, features, provider
| Provider | Estimated / month | Input / 1M | Output / 1M | Context |
|---|---|---|---|---|
1 Nebius Token Factorylowest for your volumePricing page | $2.10 | $0.13 | $0.40 | 131,072 |
2 Novita AIPricing page | $2.15 | $0.135 | $0.40 | 12,288 |
3 NscalePricing page | $2.40 | $0.20 | $0.20 | Not listed |
4 DeepInfraPricing page | $3.10 | $0.23 | $0.40 | 131,072 |
5 SambaNovaPricing page | $8.40 | $0.60 | $1.20 | 131,072 |
6 Microsoft Azure AI FoundryPricing page | $8.52 | $0.71 | $0.71 | 128,000 |
7 W&B Inference (CoreWeave)Pricing page | $8.52 | $0.71 | $0.71 | 128,000 |
8 Amazon BedrockPricing page | $8.64 | $0.72 | $0.72 | 128,000 |
9 Oracle Cloud Generative AIPricing page | $8.64 | $0.72 | $0.72 | 128,000 |
10 OVHcloud AI EndpointsBilled in EUR: €0.67 input, €0.67 output per 1M tokens. USD at the ECB rate of Oct 30, 2026 (1.1172).Pricing page | $8.98 | $0.7485 | $0.7485 | 131,000 |
Input volume includes the cached share, not an additional token volume. This is a list-price estimate, not a quote: cache-write charges, cache eligibility/TTL, batch discounts, long-context surcharges, regional pricing and taxes are excluded. Check the provider's terms for your workload before switching.
Ranked #1? Show it on your site
Nscale has the lowest blended list price (3 input : 1 output tokens) for these models. The badge states that basis, updates daily and always shows the current rank, whatever it is; ranking is by price only.
<a href="https://aiselect.online/models/deepseek-r1-distill-qwen-32b"><img src="https://aiselect.online/badge/deepseek-r1-distill-qwen-32b/nscale.svg" alt="Deepseek R1 Distill Qwen 32B API price ranking on AISelect" height="20"></a>
<a href="https://aiselect.online/models/qwq-32b"><img src="https://aiselect.online/badge/qwq-32b/nscale.svg" alt="Qwq 32B API price ranking on AISelect" height="20"></a>
<a href="https://aiselect.online/models/deepseek-r1-distill-qwen-14b"><img src="https://aiselect.online/badge/deepseek-r1-distill-qwen-14b/nscale.svg" alt="deepseek-r1-distill-qwen-14b API price ranking on AISelect" height="20"></a>Compare more
Other providers
Alibaba Cloud Model Studio, Amazon Bedrock, Anthropic, Baseten, Cloudflare Workers AI, Cohere, DeepInfra, DeepSeek, fal, Fireworks AI, FriendliAI, Google Cloud Vertex AI, Google Gemini API, IBM watsonx.ai, Lambda, Microsoft Azure AI Foundry, Mistral AI, Moonshot AI, Nebius Token Factory, Novita AI, OpenAI, Oracle Cloud Generative AI, OVHcloud AI Endpoints, Perplexity, Replicate, SambaNova, Scaleway, SiliconFlow, Together AI, W&B Inference (CoreWeave), xAI, Z.ai