Provider
Nscale
26 Models · 34 Prices · Cheapest on 13 · Uptime — · updated 2026-11-03 07:16 UTC
Trust signals · SLA · model-version transparency · pricing stability · quantization-degradation · incident response · data privacy — measured by TKX probe (activating).
About
Nscale is an AI inference provider that utilizes machine-learning systems to serve 23 models via Hugging Face's official platform, facilitating the deployment of natural language processing capabilities.
AI-generated summary from public information — is this yours? Claim & edit
Models served
| Model | $ in /1M | $ out /1M | Cheapest | Router / Source | Evidence |
|---|---|---|---|---|---|
| Qwen2.5-Coder-3B-Instruct | $0.010 | $0.030 | ✓ | Pricebook (LiteLLM) ↗ | Official list |
| Qwen2.5-Coder-7B-Instruct | $0.010 | $0.030 | ✓ | Pricebook (LiteLLM) ↗ | Official list |
| Qwen3-4B-Instruct-2507 | $0.010 | $0.030 | ✓ | HuggingFace Router ↗ | API-measured |
| Qwen3-4B-Thinking-2507 | $0.010 | $0.030 | ✓ | HuggingFace Router ↗ | API-measured |
| DeepSeek-R1-Distill-Llama-8B | $0.025 | $0.025 | ✓ | Pricebook (LiteLLM) ↗ | Official list |
| Llama-3.1-8B-Instruct | $0.030 | $0.030 | — | Pricebook (LiteLLM) ↗ | Official list |
| DeepSeek-R1-Distill-Qwen-14B | $0.070 | $0.070 | ✓ | Pricebook (LiteLLM) ↗ | Official list |
| gpt-oss-20b | $0.050 | $0.200 | — | HuggingFace Router ↗ | API-measured |
| DeepSeek-R1-Distill-Qwen-1.5B | $0.090 | $0.090 | ✓ | Pricebook (LiteLLM) ↗ | Official list |
| Qwen2.5-Coder-32B-Instruct | $0.060 | $0.200 | — | Pricebook (LiteLLM) ↗ | Official list |
| Qwen3-8B | $0.070 | $0.180 | — | HuggingFace Router ↗ | API-measured |
| Qwen3-14B | $0.070 | $0.200 | ✓ | HuggingFace Router ↗ | API-measured |
| Qwen3-32B | $0.080 | $0.250 | — | HuggingFace Router ↗ | API-measured |
| Llama-4-Scout-17B-16E-Instruct | $0.090 | $0.290 | — | Pricebook (LiteLLM) ↗ | Official list |
| DeepSeek-R1-Distill-Qwen-32B | $0.150 | $0.150 | ✓ | Pricebook (LiteLLM) ↗ | Official list |
| DeepSeek-R1-Distill-Qwen-7B | $0.150 | $0.150 | ✓ | HuggingFace Router ↗ | API-measured |
| gpt-oss-120b | $0.100 | $0.400 | — | HuggingFace Router ↗ | API-measured |
| QwQ-32B | $0.180 | $0.200 | ✓ | Pricebook (LiteLLM) ↗ | Official list |
| Llama-3.3-70B-Instruct | $0.200 | $0.200 | — | Pricebook (LiteLLM) ↗ | Official list |
| Qwen3.8-Flash-Next-FP8 | $0.150 | $0.470 | ✓ | HuggingFace Router ↗ | API-measured |
| Qwen3-235B-A22B | $0.200 | $0.600 | — | HuggingFace Router ↗ | API-measured |
| Qwen3-235B-A22B-Instruct-2507 | $0.200 | $0.600 | — | HuggingFace Router ↗ | API-measured |
| DeepSeek-R1-Distill-Llama-70B | $0.375 | $0.375 | — | Pricebook (LiteLLM) ↗ | Official list |
| mixtral-8x22b-instruct-v0.1 | $0.600 | $0.600 | ✓ | Pricebook (LiteLLM) ↗ | Official list |
| Qwen3.8-27B | $0.200 | $2.50 | — | HuggingFace Router ↗ | API-measured |
| GLM-5.3 | $1.40 | $4.40 | — | HuggingFace Router ↗ | API-measured |