Scout
Download
← All models

Auto

RouterFreeToolsVision
auto

Uses the server’s configured route and falls through to the next model on rate limits, errors or stalls.

Cost
What the answering model costs
Context
1M tokens
Price
Free
Status
Available

Routes to

Tried in this order. If one fails or is rate limited, the next one answers.

  1. GPT-OSS 120B gpt-oss-120b
  2. GLM 5.3 glm-5.3
  3. Qwen 3.8 27B qwen3.8-27b
  4. GPT 6 Luna gpt-6-luna
  5. Nemotron 3 Ultra nemotron-3-ultra
  6. Nemotron 3 Super nemotron-3-super
  7. MiniMax M3.1 Flash minimax-m3.1-flash
  8. Muse Glimmer 30B muse-glimmer-30b
  9. North Mini Code north-mini-code
  10. Gemma 4 31B gemma-4-31b
  11. Grok 4.7 grok-4.7
  12. Claude Haiku 5.5 claude-haiku-5.5
  13. Claude Haiku 5.5 (Batch) claude-haiku-5.5-batch
  14. Mercury 3 mercury-3
  15. MiMo-V2.6-Flash mimo-v2.6-flash
  16. GPT 6.1 Terra gpt-6.1-terra
  17. Deepseek v4.1 Flash deepseek-v4.1-flash
  18. Agnes 3.0 Flash agnes-3.0-flash
  19. Agnes 2.5 Flash agnes-2.5-flash
  20. DeepSeek v4.1 Flash deepseek

Use it

Send "model": "auto" to the OpenAI-compatible endpoint. API docs

curl http://localhost:4321/v1/chat/completions \
  -H "Authorization: Bearer $SCOUTCODE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'