Nexus
1.x
Docs/Nexus/Lepton AI
Open

Reading1 min
Updated31 Jul 2026
Sourcev1/providers/lepton.mdx

Lepton AI provides serverless GPU inference for open-source models. Uses an OpenAI-compatible API.

Installation01

import "github.com/xraph/nexus/providers/lepton"

Quick Start02

provider := lepton.New(os.Getenv("LEPTON_API_KEY"))

gw := nexus.New(
    nexus.WithProvider(provider),
)

Options03

OptionDescription
lepton.WithBaseURL(url)Override the API base URL (default: https://api.lepton.ai/v1)

Capabilities04

CapabilitySupported
ChatYes
StreamingYes
EmbeddingsNo
VisionNo
ToolsNo
ThinkingNo

Models05

ModelContextMax OutputInput PriceOutput Price
llama3.1-8b131K4,096$0.07/M$0.07/M
llama3.1-70b131K4,096$0.80/M$0.80/M