Pricing & Billing Guide

How token pricing works, with live multipliers from the database.

Base Rate

1× multiplier = $0.056 per 1M tokens (equivalent to ¥0.4 at 1×). Higher-multiplier models cost proportionally more per token.

Formula: Cost = multiplier × base × tokens / 1,000,000

Cache hits: only 10% of the regular cost (0.1× multiplier)

Multiplier Reference (32 models)

MultiplierPrice / 1M tokensModels
Premium (20+×)$2.250 — $1.444claude-fable-5, kimi-k3, claude-opus-5, claude-opus-4-8, claude-opus-4-7, claude-opus-4-6
Advanced (10-20×)$0.867 — $0.578claude-sonnet-5, qwen3.8-max, glm-5.2, qwen3.7-max, gpt-5.6-sol, gpt-5.5
Pro (5-10×)$0.433 — $0.289gpt-5.6-luna, gpt-5.6-terra, deepseek-v4-pro, glm-5.1, qwen3.7-plus, gpt-5.4
Standard (2-5×)$0.217 — $0.139qwen3.6-plus, doubao-seed-2.0-code, doubao-seed-2.0-pro, mimo-v2.5-pro, grok-4.5, mimo-v2.5, deepseek-v4-flash
Budget (≤2×)$0.078 — $0.072claude-haiku-4-5-20251001, LongCat-2.0, hy3, MiniMax-M3, step-3.7-flash, gpt-5.3-codex-spark
Aggregated$0.044 — $0.044claude-sonnet-4-6

Cache & Billing Notes

  • Cache hits billed at 0.1× multiplier (10% of regular cost)
  • Credits never expire, no monthly minimum
  • Pricing auto-updated when upstream changes (monitored every 30 min)
  • For the complete model catalog with providers and context windows, see the Tutorials Workspace