Dual Wire Protocols · Zero Latency Overhead

Ship against the gateway in minutes.

One key, two compatible wire formats, 15 frontier models. Speak Anthropic's wire protocol or OpenAI's to the same gateway — no extra wrapper libraries or proxy rewrites required.

terminal · curl

curl https://api.selora.lol/v1/chat/completions \
  -H "Authorization: Bearer $SELORA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-5-5",
    "messages": [{ "role": "user", "content": "Explain quantum entanglement in 1 line." }]
  }'

Connection Endpoints

Two protocols, two endpoints, one key

Configure the base URL that matches your tooling. Anthropic SDKs append /v1/messages to the bare origin; OpenAI SDKs append /chat/completions to the /v1 endpoint.

Anthropic Wire Protocol

Anthropic

Base URL

https://api.selora.lol

SDK automatically appends /v1/messagesAuthenticate via x-api-key: sk-gw-...

OpenAI Wire Protocol

OpenAI

Base URL

https://api.selora.lol/v1

SDK automatically appends /chat/completionsAuthenticate via Authorization: Bearer sk-gw-...

Protocol Header Resolution: The gateway inspects x-api-key first and falls back to Authorization: Bearer. Both wire formats accept standard sk-gw-... gateway keys. Notice that the Anthropic URL is the bare origin (because official Anthropic SDKs append /v1/messages), while OpenAI tooling takes .../v1 (because OpenAI SDKs append /chat/completions).

Model Registry & Context Specs

One gateway, 15 live frontier models

Browse supported models, verified context windows, and real-time input/output token pricing per 1M tokens.

Standard Catalog Snapshot

Universal Client Compatibility

Drop-in support for your favorite agent

Selora speaks the standard OpenAI and Anthropic wire formats. Any tool that lets you customize your API base URL and key works instantly.

Claude Code

Anthropic CLI agent

Selora guide Docs ↗

Cursor

AI code editor

Selora guide Docs ↗

Windsurf

Cascade agent IDE

Selora guide Docs ↗

Cline

VS Code agent

Selora guide Docs ↗

Aider

Terminal pair programmer

Selora guide Docs ↗

Kilo Code

Open aggregator agent

Selora guide Docs ↗

OpenCode

Open-source terminal agent

Selora guide Docs ↗

Codex

OpenAI CLI agent

Selora guide Docs ↗

Zero Code Changes

Set up Selora in three steps

Nothing to install from us. Create one API key, paste one configuration into your existing tool, and start shipping.

Claude Code

Create your API key

Sign in to the Selora console, navigate to API keys, and click Create key. Scoped keys allow rolling budgets and fine-grained model permissions.

Your full secret key (starting with sk-gw-...) is displayed exactly once upon creation. Copy and store it securely.

Open the API Keys console

Paste the configuration into your tool

Select your coding harness below to view the exact copy-paste configuration block:

Anthropic’s official command-line coding agent. The standard tool developers use with Selora.

Where this goes: Create (or open) the file .claude/settings.json inside your project root and paste this in. It applies automatically to all sessions.

.claude/settings.json

{
  "env": {
    "ANTHROPIC_BASE_URL": "https://api.selora.lol",
    "ANTHROPIC_AUTH_TOKEN": "sk-gw-..."
  }
}

Note: Replace sk-gw-... with your API key. Notice that the base URL has NO /v1 at the end — Claude Code appends /v1/messages itself.

Base URL Reference

Selora provides two native wire protocols with zero latency transformation overhead:

Anthropic Wire Protocol

Anthropic

Base URL

https://api.selora.lol

SDK automatically appends /v1/messagesAuthenticate via x-api-key: sk-gw-...

OpenAI Wire Protocol

OpenAI

Base URL

https://api.selora.lol/v1

SDK automatically appends /chat/completionsAuthenticate via Authorization: Bearer sk-gw-...

Run your first test request

Verify your connectivity in seconds. Pick your operating system, substitute your sk-gw-... key, and run:

zsh · verify connectivity

bash

curl "https://api.selora.lol/v1/chat/completions" \
  -H "Authorization: Bearer sk-gw-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"claude-sonnet-5","messages":[{"role":"user","content":"Hello"}]}'

Architectural Flow

From zero to streaming in three steps

Create an API key

Issue a scoped key from the console. Fine-tune rolling budget allocations and allowed model endpoints.

Select your wire protocol

Anthropic tools use the bare origin; OpenAI tools use the origin plus /v1. Both authenticate via standard gateway keys.

Call any frontier model

Swap the model parameter to route seamlessly across Claude, GPT, Kimi and GLM. 0ms failover across upstream providers.

Knowledge Base

The complete documentation library

Explore deep-dive technical manuals, SDK references, and status codes.

Quickstart Guide

Your first API request end to end in under 3 minutes using standard OpenAI or Anthropic SDKs.

Read documentation

Authentication & Scopes

API key authorization, x-api-key vs Bearer headers, rate-limiting rules, and safe credential rotation.

Read documentation

Model Zoo & Context Windows

Complete listing of all 15 supported frontier models, verified context limits, and token pricing.

Read documentation

REST API Reference

Comprehensive specification of endpoints, streaming SSE schemas, and telemetry headers.

Read documentation

TypeScript & Node.js

Drop-in integration patterns using the official openai and @anthropic-ai/sdk packages.

Read documentation

Error Handling & Status Codes

How the gateway surfaces 429 rolling window resets, 503 failover handling, and credit exhaustion.

Read documentation

Ready to test your first call?

Open Developer Console