Blekline
v0.3.0GitHub

Integrations

Model Providers

L2 model APIs and routers via Blekline ingress proxy.

View as Markdown

Route model traffic through Blekline before it reaches upstream APIs. Use Ingress proxy with SDK base-URL swap.

Comparison

ProviderCategoryDoc
Azure OpenAIEnterpriseEU residency, BYOK
AWS BedrockEnterpriseIAM, VPC sidecar
Google VertexEnterpriseGCP credentials
OpenRouterRouterMulti-model dev
TogetherRouterOpen models
FireworksRouterFast inference
MistralSpecialtyMistral API
CohereSpecialtySDK mask path
ReplicateSpecialtySDK mask path
QwenRouterOpenRouter / DashScope

Universal ingress pattern

from openai import OpenAI
client = OpenAI(
    base_url="https://app.blekline.com/api/ingress/v1",
    api_key="blw_...",
    default_headers={
        "x-blekline-workspace-token": "blw_...",
        "x-blekline-client-surface": "sdk",
    },
)

Set server OPENAI_API_BASE to your provider endpoint. Blekline masks user messages inline before forwarding.


Next steps: Ingress proxy · Deployment · Trust boundaries · Open workspace