Input
- Official OpenAI
- $5
- Here (−50%)
- $2.5
GPT-5.5 is the previous-generation flagship — pinned for workloads evaluated against it. During the Sol promotion it retains the higher standard $5/$30 card.
| Rate | Official OpenAI | Here (−50%) |
|---|---|---|
| Input | $5 | $2.5 |
| Cached input | $0.5 | $0.25 |
| Cache write | $5 | $2.5 |
| Output | $30 | $15 |
Every request is metered at the official rate first, then the flat 50% B2C discount is subtracted before it touches your prepaid balance. Context window: 1.05M tokens. Max output: 128K tokens. Reasoning efforts: none, low, medium, high, xhigh.
Create a free account, generate one key, and point any OpenAI-compatible tool at https://router.apitoken.sale/v1 with model ID gpt-5.5 — Responses and Chat Completions both work, authenticated with Authorization: Bearer. Eligible new accounts include $5 of platform bonus credit — enough to test the model before topping up. Existing integrations on the legacy host https://openai.api.apitoken.sale/v1 keep working.
Officially $5 per 1M input tokens and $30 per 1M output tokens. With the flat 50% apiToken.sale discount that is $2.50/$15. Promotional GPT-5.6 Sol is cheaper through 2026-11-21.
New projects should default to gpt-5.6-sol, which is also cheaper during its promotion. Keep 5.5 when prompts or evals are pinned to it.
gpt-5.5 — use it as-is on the OpenAI-compatible endpoint at https://router.apitoken.sale/v1.
Run GPT-5.5 on the OpenAI-compatible API at a flat 50% off — instant key, prepaid balance, card or crypto.