OpenAI gpt-5.6-terra-long
POST https://openai.mm.family/x402/v1/models/gpt-5.6-terra-long/chat/completions
gpt-5.6-terra-long: OpenAI GPT 5.6 Terra (>272K input tokens) chat completions, USDC per 1M tokens in / out: Flex (default; slower, may answer 429 or 503) 2.0 / 9.0, Standard (service_tier default) 4.0 / 18.0, Fast (service_tier fast; lowest latency) 8.0 / 36.0, 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-long:<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. For prompts above 272000 input tokens; shorter prompts are cheaper on gpt-5.6-terra. Sheet: https://openai.mm.family/x402/pricing
Warnings
Price mismatch The live price differs from the catalogue listing.
How to buy
This endpoint takes pay-per-call payments over x402. Call it once without paying to see its live price; any x402 client then pays and retries automatically.
curl -i -X POST "https://openai.mm.family/x402/v1/models/gpt-5.6-terra-long/chat/completions"
# HTTP/1.1 402 Payment Required: price, asset and payTo are in the responseRecent checks
| Checked (UTC) | Result | Status | Time | Live price |
|---|---|---|---|---|
| 2026-10-11 08:45 | Valid 402 | 402 | 632 ms | $0.001 |
| 2026-10-11 04:30 | Valid 402 | 402 | 815 ms | $0.001 |
| 2026-10-11 00:00 | Valid 402 | 402 | 932 ms | $0.001 |
| 2026-10-10 19:00 | Valid 402 | 402 | 627 ms | $0.001 |
Receipts
No test purchases yet. Graded test purchases are next on our list; until then every number here comes from unpaid checks.
What a check proves