Thinking
Thinking is not a gateway-wide switch. Use only the controls accepted by your selected model, endpoint and pool.
Choose a supported control
Some OpenAI-compatible models accept reasoning controls; some Anthropic-compatible models accept a thinking configuration. These are different request formats. Check your model’s supported parameters before sending either.
Budget for reasoning
Reasoning can consume output tokens and increase latency. Set a bounded output budget and account for reasoning usage where the selected model reports it. Do not assume the visible answer length equals billed output tokens.
Validate your route
Start with a short non-streaming request. Test an accepted reasoning control, inspect errors and usage, then test streaming separately. Remove unsupported fields rather than retrying the same invalid body.
Questions about your integration? support@zrelay.net