Confirm identity and visibility first
Use shape, Base URL, model list, and lightweight chat probe together. Compatible OpenAI protocol alone is not identity.
- Model ID: openrouter/auto
- Provider: Openrouter
- Check dimension: limit and speed probe
Model key route
Auto Router | limit and speed probe
Auto Router limit probing should cover RPM, TPM, concurrency, max output, first-token latency, and occasional 429/5xx risk.
Provider
Openrouter
3 models in catalog
Context
2,000,000
global route
Input price
route based
USD / 1M tokens
Output price
route based
USD / 1M tokens
Key route summary
Model ID
openrouter/auto
Provider
Openrouter
Check dimension
limit-probe
Read-only check. Detection data burns after 5 minutes.
The result shows observed facts only and never stores the full key.
Then split capability and limits
The result shows observed facts only and never stores the full key.
- Parameter surface: supports frequency_penalty
- Parameter surface: supports include_reasoning
- Parameter surface: supports logit_bias
- Parameter surface: supports logprobs
- Parameter surface: supports max_completion_tokens
- Context: 2,000,000
- Input price: route based · Output price: route based
Finish with operator action
Do not end at success or failure. Return the next action: fill price, add metadata, change route, monitor balance, or do not list yet.
- Read-only check. Detection data burns after 5 minutes.
- global route
- limit-probe