omni-auth

Manage API key authentication and session tokens. Start here to authenticate requests via Bearer token, obtain session cookies, and configure login requirements for the NextRoute API.

SKILL.md

GitHub
<!-- generated by src/lib/agentSkills/generator.ts; manual edits will be overwritten -->

Overview

Manage API key authentication and session tokens. Start here to authenticate requests via Bearer token, obtain session cookies, and configure login requirements for the NextRoute API.

Authentication

All requests require a valid Bearer token or session cookie. Obtain a token via POST /api/auth/login or configure REQUIRE_API_KEY=false for local development.

Endpoints

POST /api/auth/login

Authenticate user

curl -X POST https://localhost:20128/api/auth/login \
  -H "Authorization: Bearer $NEXTROUTE_TOKEN"
  -H "Content-Type: application/json" \
  -d '{}'

POST /api/auth/logout

Log out

curl -X POST https://localhost:20128/api/auth/logout \
  -H "Authorization: Bearer $NEXTROUTE_TOKEN"
  -H "Content-Type: application/json" \
  -d '{}'

Payloads

See the full OpenAPI specification at GET /api/openapi/spec or docs/reference/openapi.yaml for detailed request/response schemas.

<!-- skill:custom-start --> <!-- Migrated from skills/nextroute/SKILL.md (preserved curated content) -->

NextRoute

Local/remote AI gateway exposing OpenAI-compatible REST. One key, 207+ providers, auto-fallback, RTK token saver, MCP server, A2A agents.

Setup

export NEXTROUTE_URL="http://localhost:20128"      # or VPS / tunnel URL
export NEXTROUTE_KEY="sk-..."                       # from Dashboard → API Keys

All requests: ${NEXTROUTE_URL}/v1/... with Authorization: Bearer ${NEXTROUTE_KEY}.

Verify: curl $NEXTROUTE_URL/api/health → {"ok":true}

Discover models

curl $NEXTROUTE_URL/v1/models                  # chat/LLM (default)
curl $NEXTROUTE_URL/v1/models/image            # image-gen
curl $NEXTROUTE_URL/v1/models/tts              # text-to-speech
curl $NEXTROUTE_URL/v1/models/embedding        # embeddings
curl $NEXTROUTE_URL/v1/models/web              # web search + fetch
curl $NEXTROUTE_URL/v1/models/stt              # speech-to-text

Use data[].id as model field in requests. Combos appear with owned_by:"combo".

Capability skills

Capability Raw URL
Chat / code-gen https://raw.githubusercontent.com/diegosouzapw/NextRoute/main/skills/nextroute-chat/SKILL.md
Image generation https://raw.githubusercontent.com/diegosouzapw/NextRoute/main/skills/nextroute-image/SKILL.md
Text-to-speech https://raw.githubusercontent.com/diegosouzapw/NextRoute/main/skills/nextroute-tts/SKILL.md
Speech-to-text https://raw.githubusercontent.com/diegosouzapw/NextRoute/main/skills/nextroute-stt/SKILL.md
Embeddings https://raw.githubusercontent.com/diegosouzapw/NextRoute/main/skills/nextroute-embeddings/SKILL.md
Web search https://raw.githubusercontent.com/diegosouzapw/NextRoute/main/skills/nextroute-web-search/SKILL.md
Web fetch https://raw.githubusercontent.com/diegosouzapw/NextRoute/main/skills/nextroute-web-fetch/SKILL.md
MCP server (37 tools) https://raw.githubusercontent.com/diegosouzapw/NextRoute/main/skills/nextroute-mcp/SKILL.md
A2A protocol https://raw.githubusercontent.com/diegosouzapw/NextRoute/main/skills/nextroute-a2a/SKILL.md
Routing & combos https://raw.githubusercontent.com/diegosouzapw/NextRoute/main/skills/nextroute-routing/SKILL.md
Token compression https://raw.githubusercontent.com/diegosouzapw/NextRoute/main/skills/nextroute-compression/SKILL.md
Monitoring & health https://raw.githubusercontent.com/diegosouzapw/NextRoute/main/skills/nextroute-monitoring/SKILL.md

CLI skills (nextroute binary)

Capability Raw URL
CLI entry point https://raw.githubusercontent.com/diegosouzapw/NextRoute/main/skills/nextroute-cli/SKILL.md
CLI admin & lifecycle https://raw.githubusercontent.com/diegosouzapw/NextRoute/main/skills/nextroute-cli-admin/SKILL.md
CLI providers & keys https://raw.githubusercontent.com/diegosouzapw/NextRoute/main/skills/nextroute-cli-providers/SKILL.md
CLI cloud agents https://raw.githubusercontent.com/diegosouzapw/NextRoute/main/skills/nextroute-cli-cloud/SKILL.md
CLI evals & benchmarks https://raw.githubusercontent.com/diegosouzapw/NextRoute/main/skills/nextroute-cli-eval/SKILL.md

Errors

  • 401 → set/refresh NEXTROUTE_KEY (Dashboard → API Keys)
  • 400 Invalid model format → check model exists in /v1/models/<kind>
  • 503 Provider circuit open → upstream provider down; retry after Retry-After seconds
  • 429 → rate limited; honor Retry-After

Differentiators vs OpenAI direct

  • Auto-fallback combos (14 strategies): never stop coding even if a provider rate-limits
  • RTK token saver: tool_result compressed via 47 specialized filters (git-diff, test-jest, terraform-plan, docker-logs…) — 20-40% token reduction
  • Caveman mode: optional terse system prompt injection (LITE/FULL/ULTRA) — 15-25% completion reduction
  • MCP + A2A servers built-in (this is the only AI router that exposes both protocols)
  • Memory with FTS5 + Qdrant for persistent agent context
  • Guardrails for PII masking, prompt injection detection, vision policies<!-- skill:custom-end -->