OPERATIONAL

Status

Loading usage

GPT Pro · 0.22x

Pro account pool for stable text-model access. The Luna models (gpt-6-luna, gpt-5.6-luna) are not served here; use the Luna channel.

gpt-6-astra

gpt-6-sol

gpt-5.6-sol

gpt-5.6-terra

gpt-5.5

GPT Economy · 0.09x

Plus account pool: lowest cost first, with average stability. gpt-6-astra and the Luna models (gpt-6-luna, gpt-5.6-luna) are not served here.

gpt-6-sol

gpt-5.6-sol

gpt-5.6-terra

gpt-5.5

GPT Anti-Downgrade · 0.35x

Not guaranteed 100% downgrade-free，This pool rotates fresh accounts daily behind residential proxy IPs to keep the model at full capability as much as possible. Serves gpt-6-astra, gpt-6-sol and gpt-5.6-sol only; other models are refused. Codex and OpenAI-compatible access.

gpt-6-astra

gpt-6-sol

gpt-5.6-sol

Luna · 0.7x

Separate account pool serving gpt-6-luna and gpt-5.6-luna only. Supports Codex and OpenAI-compatible clients.

gpt-6-luna

gpt-5.6-luna

Grok Heavy · 15% of official price

Supports Grok 4.7, Grok 4.6, Grok 4.5, Codex, OpenAI-compatible clients, and Claude Code.

grok-4.7

grok-4.6

grok-4.5

DeepSeek V4.1 Flash (CN) · 60% of official price

DeepSeek V4.1 Flash at 60% of the official price. Credits deducted are official USD x 0.6 x 6.8. Busy hours are 09:00-12:00 and 14:00-18:00 Beijing time on weekdays; all other hours and weekends are off-peak. 1M context, with thinking mode, tool calling and image input. Works with Codex and OpenAI-compatible clients.