Model Pricing

Pricing details for AI models supported by QCode

Model Pricing ¶

QCode supports seven model families: Claude, GPT/Codex, Gemini, GLM, Kimi, DeepSeek, and Qwen. Pricing is based on each provider's official rates, with a service rate multiplier applied. The live list is qcode.cc/models. No grok.

Pricing Formula ¶

QCode Price = Official API Price × Service Rate

Service Rates ¶

The service rate is a multiplier that covers routing, reliability, and infrastructure costs. Rates may vary by provider, reflecting differences in access costs.

Visit the Models & Pricing page to see current rates in the rate cards section. Rates are managed by QCode administrators and can be adjusted at any time.

Supported Model Families ¶

Anthropic Claude ¶

Includes Claude Sonnet, Opus, and Haiku series. Pricing covers input/output tokens and prompt caching (cache write/read).

OpenAI / Codex ¶

Includes GPT and Codex series models. Used with Claude Code, Codex CLI, and other tools.

Google Gemini ¶

Includes Gemini Pro, Flash, and other variants. Accessed via Vertex AI.

Zhipu GLM / Moonshot Kimi / DeepSeek / Qwen ¶

These four China-family lines share the same cr_ key and the same access points as the three above. Live ids (such as glm-5.2, kimi-k3, deepseek-v4-pro, qwen3.7-max) and rates come only from qcode.cc/models. How to fill the protocol and model name: China-family models.

View Detailed Pricing ¶

Visit qcode.cc/en/models for real-time pricing, context windows, capability badges, and usage popularity for all models.

Pricing data is sourced from qcode.cc/models and automatically synced every 10 minutes.

Billing — Plan billing rules and quota details
China-family models — paths and ids for GLM / Kimi / DeepSeek / Qwen
FAQ — Frequently asked questions

← Previous

Crypto Payment Guide

FAQ

Model Pricing

Related Documents