Run prompts through the LLM of your choice and get each answer with the exact model version, its maker, the finish reason, token counts and the exact cost of the call. You pay exactly what each call costs at the model's own token rates.
Sample
Here's a sample run of one prompt over 3 images, showing the exact schema and results you can expect.
| # | ID | Prompt | File URL | Answer | Model | Provider | Finish Reason | Prompt Tokens | Completion Tokens | Reasoning Tokens | Total Tokens | Cost (USD) | Created At |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
1 | gen-1794256172-sFQSXJKIw2DGTe9KEDT9 | Describe this image in one short sentence. | A close-up of an orange tabby cat with striking yellow eyes. | openai/gpt-4o-mini | OpenAI | stop | 25,516 | 14 | 0 | 25,530 | 0.002 | 2026-11-09T20:29:32Z | |
2 | gen-1794256172-EMkjFek8zKVf73C56IbH | Describe this image in one short sentence. | The image features three colorful dice—red, blue, and green—floating above a vibrant background. | openai/gpt-4o-mini | OpenAI | stop | 25,516 | 20 | 0 | 25,536 | 0.004 | 2026-11-09T20:29:32Z | |
3 | gen-1794256172-HtyXwQ5Kvq6pZvsM5HYe | Describe this image in one short sentence. | The image features the text "just an Example" in a bold, red font, tilted to the side. | openai/gpt-4o-mini | OpenAI | stop | 8,515 | 22 | 0 | 8,537 | 0.001 | 2026-11-09T20:29:32Z |
Playground
Advanced parameters are collapsed below.
Fill in the fields below or .
curl -X POST "https://api.mindcase.co/v1/data/llm/route/run?wait=true" \
-H "Authorization: Bearer mk_live_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"params": {
"prompts": [],
"model": "",
"files": []
}
}'Related
How AI assistants answer your prompts and whether they mention your brand or competitors, with assistant, model, country and the full answer. Pass prompts, brand aliases, competitors and assistants.
Ask a decision model one typed question about each item you send (a yes/no, a pick from your options, or a position on your scale) and get the decision with its score, confidence and probabilities, the exact model version, its maker, token counts and the exact cost of each call. You pay exactly what each call costs at the model's own token rates.