Nscale Serverless Inference
LLM 6.0/10EU-sovereign AI cloud offering serverless open-model inference with free signup credits and no credit card.
Nscale Serverless Inference scores 6/10 for free value in LLM. The main constraint: $5 in free signup credits, no credit card; credits reported to expire within roughly 30-90 days. Pay-per-token after exhaustion; credit card required to top up.
Free value score
6.0 / 10Show the math
Key metrics
Models
19 free · 19 total| Model | Family | AA | Access |
|---|---|---|---|
| GPT OSS 120B | GPT | 23.8 | free |
| GPT OSS 20B | GPT | 14.9 | free |
| Llama 4 Scout 17B 16E Instruct | Llama | 10 | free |
| DeepSeek R1 Distill Llama 8B | DeepSeek | — | free |
| DeepSeek R1 Distill Qwen 14B | DeepSeek | — | free |
| DeepSeek R1 Distill Qwen 7B (Math) | DeepSeek | — | free |
| Devstral Small 2505 | Mistral | — | free |
| Flux.1 [schnell] | FLUX | — | free |
| Llama 3.1 8B Instruct | Llama | — | free |
| Llama 3.2 11B Vision Instruct | Llama | — | free |
| Mixtral 8x22B Instruct v0.1 | Mistral | — | free |
| Qwen 2.5 Coder 32B Instruct | Qwen | — | free |
| Qwen 2.5 Coder 3B Instruct | Qwen | — | free |
| Qwen 2.5 Coder 7B Instruct | Qwen | — | free |
| Qwen 3 235B A22B | Qwen | — | free |
| Qwen 3 235B A22B Instruct 2507 | Qwen | — | free |
| Qwen3 4B Instruct 2507 | Qwen | — | free |
| Qwen3 4B Thinking 2507 | Qwen | — | free |
| Qwen3 Embedding 8B | Qwen | — | free |
What you get
$5 free credits, no credit card to start
EU-sovereign data centers in Norway
Serverless pay-per-token after free credits
Listed in maintained awesome-free-llm-apis
Limitations
- $5 one-time signup credit
Every new user receives a one-time $5 credit pool that does not renew; once exhausted the service becomes pay-per-token.
- Card required to top up
A credit card must be added before you can top up once the free credit is exhausted; no card needed to claim the initial $5.
Sources
-
"Every account starts with $5 free credit."
https://docs.nscale.com/changelog/changelog -
"Nscale doesn't enforce rate limits for serverless inference, allowing you to scale dynamically without artificial constraints—your workload is only limited by your allocated resources, ensuring consistent performance even under high demand."
https://docs.nscale.com/docs/faqs/rate-limits -
"Purchased credits expire 3 years after the date of purchase. You can view the expiry date for each credit commit in the Credit tab under Usage & Billing. Startup credits have a separate expiry policy."
https://docs.nscale.com/docs/manage/credit -
"gpt-oss-120b (high) scores 33 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 15)."
https://artificialanalysis.ai/models/gpt-oss-120b -
"This Series C round supports Nscale's acceleration of AI infrastructure deployments globally, valuing Nscale at $14.6 billion."
https://www.nscale.com/press-releases/nscale-series-c