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: openai/gpt-4
- Provider: OpenAI
- Check dimension: pricing and context check
Model key route
OpenAI: GPT-4 | pricing and context check
OpenAI: GPT-4 should not stop at callable or not. The result should show input $30, output $60, context 8,191, and provider OpenAI.
Provider
OpenAI
62 models in catalog
Context
8,191
global route
Input price
$30
USD / 1M tokens
Output price
$60
USD / 1M tokens
Key route summary
Model ID
openai/gpt-4
Provider
OpenAI
Check dimension
pricing-context
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 logit_bias
- Parameter surface: supports logprobs
- Parameter surface: supports max_completion_tokens
- Parameter surface: supports max_tokens
- Context: 8,191
- Input price: $30 · Output price: $60
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
- pricing-context