Don’t miss out on NVIDIA Blackwell! Join the waitlist.
Login Create account
inference_large

The Lowest Cost
AI Inference Anywhere

Use the latest models, scale effortlessly, and only pay for the tokens you use with no rate limits on Lambda's serverless inference API endpoints.

Generate your API key Read the docs

Built for Builders

nvidia_gpu_icon-large-2

Low cost

Cut costs, not corners. Get fast, cost-effective AI Inference without the middleman. 

gpus_icon-large

Scalable

Easily scale from prototype to production without ever having to manage infrastructure and no rate limits.

cloud_icon-large-1

Engineered for AI

An AI-first stack by Lambda, optimized to power AI workloads of any size, from hardware to API.

Read the docs

Lambda Inference API Pricing*

131k context windows, state-of-the-art models, and automatic scaling–all in one serverless API.

 

Model Quantization Context
Price per 1M input tokens
 
Price per 1M output tokens
Core
Llama-3.1-8B-Instruct
 BF16 131K $0.025 $0.04
Llama-3.1-70B-Instruct
 FP8 131K $0.12 $0.30
Llama-3.1-405B-Instruct
 FP8 131K $0.80 $0.80
Sandbox
Llama-3.3-70B-Instruct  FP8 131K $0.12 $0.30
Llama-3.2-3B-Instruct
 FP8 131K $0.015 $0.025
Hermes-3-Llama-3.1-8B
 BF16 131K $0.025 $0.04
Hermes-3-Llama-3.1-70B (FP8)
 FP8 131K $0.12 $0.30
Hermes-3-Llama-3.1-405B (FP8)
 FP8 131K $0.80 $0.80
LFM-40b
 BF16 66K $0.15 $0.15
Llama3.1-nemotron-70b-instruct FP8 131K $0.12 $0.30
Qwen2.5-Coder-32B
 BF16 33K $0.07 $0.16

* plus applicable sales tax

Generate your API key

Bring In Those Long Prompts!

Access state-of-the-art models and effortless scalability all in one serverless inference API endpoint.
 
Example Inference API transaction
Model Llama-3.1-405B-Instruct-FP8
Pricing
$0.80 per 1M tokens of input or output
1 token = $0.00000008

Input

"Convert 30,000 tokens to single space pages of text assuming there are an average of 4 characters per token including spaces and punctuation."

Tokens: 63
Cost: 0.005¢
Output
“To estimate the conversion of 30,000 tokens to single-spaced pages of text, we'll break down the process step by step …”
 
Tokens: 234
Cost: 0.02¢
Total Tokens Used
297
Grand Total 0.025¢

 

Generate your API key

Ready to get started?

Unlock fast, scalable inference at the lowest market cost per token with no rate limits, or contact us to learn how our Private Cloud can accelerate your AI workloads.