Checked 2026-10-26

GPT API pricing

GPT input, cached-input and output prices on one key, read live from the catalog. Prepaid by card or crypto, no KYC, no subscription.

The cheapest one that does the task: Luna for short high-volume work, Sol for most coding and writing, Astra where the harder answer is worth the price. Run the same prompt on each and compare. Every row below is a live catalog read; prices are USD per million tokens and the developer list appears where recorded.

01Every GPT model

ModelInputCachedOutputDeveloper list in / outContext
GPT-6.1 Sol$0.60 (70% under)$0.06$3.00 (70% under)$2.00 / $10.001.1M tokens
GPT-6 Luna$0.0625 (37% under)$0.0125$0.20 (60% under)$0.10 / $0.501.1M tokens
GPT-6 Sol$0.60 (70% under)$0.12$3.00 (70% under)$2.00 / $10.001.1M tokens
GPT-6 Astra$3.00 (70% under)$0.30$15.00 (70% under)$10.00 / $50.001.1M tokens
GPT-5.6 Luna$0.12 (40% under)$0.012$0.72 (40% under)$0.20 / $1.201.1M tokens
GPT-5.6 Sol$1.20 (70% under)$0.12$3.00 (85% under)$4.00 / $20.001.1M tokens
GPT-5.6 Terra$1.20 (40% under)$0.12$3.60 (70% under)$2.00 / $12.001.1M tokens
GPT-5.5$1.80 (64% under)$0.16$9.00 (70% under)$5.00 / $30.001.1M tokens
GPT-5.4 Mini$0.75$0.075$4.50$0.75 / $4.50400K tokens
GPT-5.3-Codex$1.75$0.175$14.00$1.75 / $14.00400K tokens
GPT-4o mini$0.15$0.075$0.60$0.15 / $0.60128K tokens
GPT-4o$2.50$1.25$10.00$2.50 / $10.00128K tokens
GPT 5.2$1.75$0.175$14.00$1.75 / $14.00—
GPT 4.1$6.40$1.60$25.60—1M tokens
GPT 4.1 Mini$1.28$0.32$5.12—1M tokens
GPT 4.1 Nano$0.32$0.08$1.28—1M tokens
GPT 4O 2024 08 06$8.00$4.00$32.00——
GPT 4O 2024 11 20$8.00$4.00$32.00——
GPT 5$4.00$0.40$32.00—400K tokens
GPT 5 Mini$0.80$0.08$6.40—400K tokens
GPT 5 Nano$0.2376$0.0238$1.9008—400K tokens
GPT 5 PRO$48.00input rate$384.00—400K tokens
GPT 5.1$4.00$0.40$32.00—400K tokens
GPT 5.2 PRO$67.20input rate$537.60—400K tokens
GPT 5.4 Nano$0.1335$0.0134$0.8346—400K tokens
GPT 5.6$0.792$0.0792$3.96—1.1M tokens
GPT 6 Astra PRO$4.00$0.40$20.00—272K tokens
GPT 6 Luna Plus$0.12$0.012$0.60—272K tokens
GPT 6 SOL Plus$4.00input rate$20.00—272K tokens
GPT 6 SOL PRO Stable$1.80input rate$9.00—1M tokens
GPT 6.1 SOL NEW$0.3529$0.0176$1.7647—1M tokens
GPT 6.1 SOL Plus$4.00$0.20$20.00—272K tokens
GPT 6.1 SOL PRO$0.80$0.04$4.00—272K tokens
GPT 6.1 SOL PRO MAX$1.60$0.08$8.00—1M tokens
GPT 6.1 Terra$0.2353$0.0235$1.1765—1M tokens
gpt-oss-120b$0.20$0.04$1.80——
gpt-oss-20b$0.16input rate$0.72——

USD per million tokens, read from the RelaySwitch catalog when this page was built. Developer list: the catalog's record of the developer's own price.

02Which model should I use?

The cheapest one that does the task: Luna for short high-volume work, Sol for most coding and writing, Astra where the harder answer is worth the price. Run the same prompt on each and compare. Compare the worked models below before choosing for production.

03Worked models

  • GPT-6 Astra — 3.0000 input / 15.0000 output per million tokens.
  • GPT-6.1 Sol — 0.6000 input / 3.0000 output per million tokens.
  • GPT-6 Luna — 0.0625 input / 0.2000 output per million tokens.

Questions

Is GPT billed monthly?
No. Credit is prepaid and each request bills per token.
Can I pay for GPT with crypto?
Yes: USDT, USDC, BTC, ETH or SOL, alongside card, Apple Pay and PayPal.