Lepton AI
NVIDIA DGX Cloud Lepton — enterprise serverless inference on DGX infrastructure
Lepton AI was acquired by NVIDIA and rebranded as NVIDIA DGX Cloud Lepton in 2026. The platform now runs on NVIDIA's DGX Cloud infrastructure, offering serverless inference for popular open-weight models with enterprise-grade reliability. The OpenAI-compatible API and developer experience remain intact, now backed by NVIDIA's global DGX Cloud footprint.
The only serverless inference platform running directly on NVIDIA DGX Cloud — enterprise reliability with the latest NVIDIA hardware, no infrastructure management required.
- Backed by NVIDIA DGX Cloud infrastructure
- Enterprise-grade reliability and SLAs
- Serverless — no infrastructure management
- OpenAI-compatible API
- Auto-scaling handles traffic spikes
- Access to latest NVIDIA GPU hardware
- Smaller model catalog than Together AI or Fireworks
- Pricing may be higher than budget inference providers
- No fine-tuning support
Lepton AI Models
| Model | Modality | Tier | Price | Cached /1M | TTFT | Throughput | Context | Intel. | Caps | |
|---|---|---|---|---|---|---|---|---|---|---|
llama3-3-70b Llama 3.3 | Chat | efficient | $0.80/ $0.80 in / out per 1M EST Jul 2026 | — | 260ms | 280 t/s | 131K | 64 |
Lepton AI — Frequently Asked Questions (FAQs)
Similar Providers
Lepton AI Reviews
All LLM Providers
Full comparison tableLepton AI LLM pricing overview
Lepton AI is an inference API provider that hosts open-weight and third-party large language models. Lepton AI was acquired by NVIDIA and rebranded as NVIDIA DGX Cloud Lepton in 2026. The platform now runs on NVIDIA's DGX Cloud infrastructure, offering serverless inference for popular open-weight models with enterprise-grade reliability. The OpenAI-compatible API and developer experience remain intact, now backed by NVIDIA's global DGX Cloud footprint. Common use cases include Enterprise inference, Serverless, Open-source, Production workloads. Headquartered in San Jose, CA, founded 2023. All models are accessible via a REST API compatible with standard OpenAI-style request formats, enabling drop-in integration with most LLM frameworks and orchestration tools.
Lepton AI vs other LLM providers
Lepton AI competes with OpenAI, Anthropic, Google, Groq, Together AI, Mistral, Cohere, and other inference API providers across dimensions of price, throughput, latency, context window, and model intelligence. The only serverless inference platform running directly on NVIDIA DGX Cloud — enterprise reliability with the latest NVIDIA hardware, no infrastructure management required. Use the LLM provider comparison tool to see Lepton AI token pricing, latency, and throughput side-by-side with any other provider. The full LLM pricing table shows all providers ranked by input token cost, output token cost, and throughput in a single sortable view.
Why choose Lepton AI?
Lepton AI stands out because: The only serverless inference platform running directly on NVIDIA DGX Cloud — enterprise reliability with the latest NVIDIA hardware, no infrastructure management required.. The API currently offers 1 model, spanning 1 efficient tier. For teams running high-volume inference workloads, prompt caching and batch API endpoints can reduce effective input token costs by 50–90% — check the context window cost guide for a full breakdown of caching economics.
Understanding Lepton AI token pricing
Lepton AI charges separately for input (prompt) and output (completion) tokens, priced per 1M tokens in USD. Output tokens are typically 3–5× more expensive than input tokens due to the compute cost of autoregressive generation. The cheapest {meta.name} input rate is currently $0.80/1M tokens. Prices shown are sourced from Lepton AI's public pricing page and updated every 15 minutes. Need help estimating your spend? Read the LLM API cost calculator guide — it covers tokens, context windows, prompt caching, and batch discounts with worked examples for RAG, chat history, and document processing workloads.
Lepton AI context window and model capabilities
Context window size directly affects both capability and cost — every token in the context window is charged as an input token. Lepton AI's largest context window is 131K tokens. For RAG and document processing workloads, longer context windows enable richer retrieval but increase per-call costs proportionally. Prompt caching — where supported — stores the KV state of repeated prefixes and charges 75–90% less for cache hits, making it the most impactful cost optimization for applications with consistent system prompts or retrieved documents. See the LLM context window cost guide for a full analysis of how context length affects your API bill.
Self-hosted vs managed inference: when Lepton AI makes sense
Managed inference APIs like Lepton AI eliminate infrastructure overhead — no GPU provisioning, driver management, or model serving stack to maintain. The trade-off is cost at scale: a single H100 at ~$2.50/hr can serve ~500K tokens/min of Llama 3.3 70B, which at Lepton AI API rates would cost significantly more per token. The break-even point depends on your request volume, latency requirements, and engineering capacity. For teams processing fewer than ~10M tokens/day, managed APIs are almost always cheaper when total cost of ownership is considered. Above that threshold, self-hosted inference on rented GPU compute typically wins on unit economics. Read the cheapest GPU cloud guide for a full break-even analysis. Historical Lepton AI token price data is available in the LLM price history charts.
Compare Lepton AI With Another LLM Provider
Compare Lepton AI vs other providers
Side-by-side token pricing, latency, throughput, and context window. View all LLM provider comparisons →
Looking for alternatives?
Compare Lepton AI with other LLM API providers side by side.