OpenAI gpt-5.6-terra

POST https://openai.mm.family/x402/v1/models/gpt-5.6-terra/chat/completions

gpt-5.6-terra: OpenAI GPT 5.6 Terra (<=272K input tokens) chat completions, USDC per 1M tokens in / out: Flex (default; slower, may answer 429 or 503) 1.0 / 6.0, Standard (service_tier default) 2.0 / 12.0, Fast (service_tier fast; lowest latency) 4.0 / 24.0, plus 0.0025 per call on Base or 0.002 on Solana. Reasoning levels: none, low, medium, high, xhigh (send model gpt-5.6-terra:<level> or reasoning_effort). Quote charges input plus 10% of max_tokens as output (the model may use all of it); reasoning tokens count as output and come first, so send max_tokens >= 128 for short answers. Empty answers are free. Prompts above 272000 input tokens are quoted at the gpt-5.6-terra-long rates. Sheet: https://openai.mm.family/x402/pricing