MultiRouter-AI/providers.yaml.example at main · Mykle23/MultiRouter-AI · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
# ╔═══════════════════════════════════════════════════════════════╗
# ║  MultiRouter AI — Provider Configuration                     ║
# ╚═══════════════════════════════════════════════════════════════╝
#
# This file defines your AI provider instances and routing strategy.
# Copy to providers.yaml and fill in your API keys.
#
# API keys can be placed directly here (recommended for local dev)
# or referenced from environment variables: ${VAR_NAME}
#
# Routing strategies:
#   exhaust      — Use providers in order until rate-limited,
#                  then failover to the next one (default)
#   round-robin  — Distribute requests evenly across all providers
#
# Order matters: providers are tried top-to-bottom.
# Put free tiers first and paid providers last.

routing:
  default_strategy: exhaust
  retry_after_seconds: 300   # Re-enable failed providers after 5 min

providers:
  # ── Groq (free tier) ─────────────────────────────────────────
  - id: groq-1
    type: groq
    api_key: your-groq-api-key
    models:
      - llama-3.3-70b-versatile
      - llama-3.1-8b-instant
      - qwen/qwen3-32b

  # Stack more Groq free-tier accounts:
  # - id: groq-2
  #   type: groq
  #   api_key: your-second-groq-key
  #   models:
  #     - llama-3.3-70b-versatile

  # - id: groq-3
  #   type: groq
  #   api_key: your-third-groq-key
  #   models:
  #     - llama-3.3-70b-versatile

  # ── Cerebras (free tier) ─────────────────────────────────────
  - id: cerebras-1
    type: cerebras
    api_key: your-cerebras-api-key
    models:
      - llama-3.3-70b
      - llama3.1-8b

  # ── Google Gemini (free tier) ────────────────────────────────
  - id: gemini-1
    type: gemini
    api_key: your-gemini-api-key
    models:
      - gemini-2.5-flash
      - gemini-2.5-pro

  # ── OpenRouter ───────────────────────────────────────────────
  - id: openrouter-1
    type: openrouter
    api_key: your-openrouter-api-key
    models:
      - meta-llama/llama-3.3-70b-instruct
      - anthropic/claude-sonnet-4
      - google/gemini-2.5-flash

  # ── OpenAI (paid — listed last so free tiers are used first) ─
  - id: openai-1
    type: openai
    api_key: your-openai-api-key
    models:
      - gpt-4o
      - gpt-4o-mini
      - gpt-4.1
      - gpt-4.1-mini
      - gpt-4.1-nano

  # ── Custom OpenAI-compatible endpoint ────────────────────────
  # Works with Ollama, LM Studio, vLLM, or any OpenAI-compat API
  # - id: local-ollama
  #   type: openai-compatible
  #   base_url: http://localhost:11434/v1
  #   api_key: ollama
  #   models:
  #     - llama3.2
  #     - codellama

  # ── Using environment variables (for Docker / CI / production) ─
  # Instead of putting keys directly, reference env vars:
  # - id: groq-ci
  #   type: groq
  #   api_key: ${GROQ_API_KEY}
  #   models:
  #     - llama-3.3-70b-versatile