Input
- Official OpenAI
- $4
- Here (−50%)
- $2
GPT-5.6 Sol is the flagship of the GPT-5.6 line for reasoning and agentic coding on the OpenAI-compatible endpoint. GPT-6 Astra is the latest GPT model. Here is what it costs per token, and how to run it cheaper on the same key and balance.
| Rate | Official OpenAI | Here (−50%) |
|---|---|---|
| Input | $4 | $2 |
| Cached input | $0.4 | $0.2 |
| Cache write | $5 | $2.5 |
| Output | $20 | $10 |
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, max.
Create a free account, generate one key, and point any OpenAI-compatible tool at https://router.apitoken.sale/v1 with model ID gpt-5.6-sol — 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.
Through 2026-11-21 inclusive, the temporary official card is $4 input, $0.40 cached input, $5 cache write and $20 output per 1M tokens. Here that is $2/$0.20/$2.50/$10 after 50% off. Standard $5 input and $30 output return on 2026-11-22 UTC.
gpt-5.6-sol (gpt-5.6 is an alias of the same model). Use it with the OpenAI SDK, Codex CLI, opencode or any OpenAI-compatible tool pointed at https://router.apitoken.sale/v1.
Yes. One sk-pool key and one prepaid balance cover both surfaces: Anthropic Messages API for Claude models and the OpenAI-compatible API for GPT models. The same discount applies to both.
Run GPT-5.6 Sol on the OpenAI-compatible API at a flat 50% off — instant key, prepaid balance, card or crypto.