API reference

Reasoning models

Understand model-dependent reasoning and output usage.

OPENAI BASE URLhttps://www.modelmesh.in/api/v1

Check capabilities

Reasoning support and accepted parameters vary by model. Choose a model with published reasoning support. Unsupported provider-specific options may be rejected.

Budget for the complete response

Reasoning can increase output usage and latency. Visible answer length is not a reliable token count. Review returned usage and dashboard records; accounting relies on provider reporting.

Evaluate your own tasks

Compare models on your coding, analysis, or writing tasks. Rankings orders price or context specifications; it does not claim benchmark scores or measured intelligence.

Request example

POSThttps://www.modelmesh.in/api/v1/chat/completions

Model from the live catalog

Replace the key placeholder before running this example. This page does not send requests. Paid requests consume your allowance or funds.

$env:MODELMESH_API_KEY = 'YOUR_MODELMESH_KEY'

Invoke-RestMethod -Method Post -Uri 'https://www.modelmesh.in/api/v1/chat/completions' `
  -Headers @{Authorization="Bearer $env:MODELMESH_API_KEY"} `
  -ContentType 'application/json' `
  -Body '{
  "model": "YOUR_MODEL_ID",
  "messages": [
    {
      "role": "user",
      "content": "Say hello in one sentence."
    }
  ],
  "max_tokens": 64
}'