One coding balance across multiple model ecosystems

Use one Coding Application token across the protocols linked to Coding Plan, then choose the matching endpoint, authentication method, and protocol in the setup center.

View plans Open setup center

CLAUDE

Messages and Count Tokens

Claude Messages, message token counting, and a Claude Chat Completions-compatible endpoint.

OPENAI

Responses and Chat Completions

The Responses protocol used by Codex and OpenAI Chat Completions.

MODEL ECOSYSTEMS

Multi-model Chat Completions

Public Chat Completions endpoints for Gemini, GLM, Grok, Kimi, and DeepSeek.

Coding Plus

500 Credits400 base + 100 bonus · ¥99

For short projects, test coverage, and occasional use.

Coding Standard

1,600 Credits1,200 base + 400 bonus · ¥299

For everyday development, multiple repositories, and code review.

Coding Pro

4,000 Credits3,000 base + 1,000 bonus · ¥699

For sustained agents, complex refactors, and frequent use.

Coding Max

10,000 Credits8,000 base + 2,000 bonus · ¥1,399

For team workloads, multi-agent runs, and automation.

Four separately metered usage types

Uncached input
Model output
Cache writes
Cache reads

Purchase and balance boundaries

Each purchase extends the Coding Application by 30 days
No automatic renewal
No fallback to the general balance
Normal API concurrency and rate limits still apply

View client setup

Do tiers have different model permissions?

No. All tiers have the same Coding model access. Exact models depend on the live directory and the compatibility range of your client profile.

How are Credits deducted?

Uncached input, output, cache writes, and cache reads are metered separately. Long context, tools, and parallel tasks can increase consumption.

Will Coding use my general balance automatically?

No. Coding Applications disable general-balance fallback. You decide whether to purchase again.

How do I see current models?

Request the live model directory with a valid Coding credential and use an exact model ID marked compatible by your current profile.

How do I troubleshoot a configured client?

First confirm that the token belongs to a Coding Application, then compare the endpoint, protocol, model ID, and launch method with the client guide.

Choose a plan, then choose the model for each task

One token, one bill, and per-call usage details. Start with the guide for your client.

Choose a plan Configure a client

Claude Messages Count Tokens API

POSThttps://api.ai.moses.day/v1/messages/count_tokens

POSThttps://api.ai.moses.day/claude/messages/count_tokens

Claude Count Tokens API calculates the number of input tokens.

Claude Messages API

POSThttps://api.ai.moses.day/v1/messages

POSThttps://api.ai.moses.day/claude/messages

Claude Messages API, and the official input and output are completely consistent.

OpenAI Chat Completion API

POSThttps://api.ai.moses.day/openai/chat/completions

POSThttps://api.ai.moses.day/v1/chat/completions

OpenAI Chat Completion API, compatible with the official API format.

Claude Chat Completion API

POSThttps://api.ai.moses.day/v1/chat/completions

POSThttps://api.ai.moses.day/claude/chat/completions

Claude Chat Completion API, compatible with the official API format.

DeepSeek Chat Completion API

POSThttps://api.ai.moses.day/deepseek/chat/completions

POSThttps://api.ai.moses.day/v1/chat/completions

DeepSeek Chat Completion API, compatible with the official API format.

GLM Chat Completion API

POSThttps://api.ai.moses.day/glm/chat/completions

POSThttps://api.ai.moses.day/v1/chat/completions

Zhipu GLM chat completion API, compatible with the OpenAI Chat Completions format. Supports models including glm-3-turbo, glm-4.5-air, glm-4.6, glm-4.7, and glm-5.1, with streaming, function calling, multi-turn conversations, and system prompts.

Gemini Chat Completion API

POSThttps://api.ai.moses.day/gemini/chat/completions

POSThttps://api.ai.moses.day/v1/chat/completions

Gemini Chat Completion API, compatible with the official API format.

Grok Chat Completion API

POSThttps://api.ai.moses.day/grok/chat/completions

POSThttps://api.ai.moses.day/v1/chat/completions

Grok Chat Completion API, compatible with the official API format.

Kimi Chat Completion API

POSThttps://api.ai.moses.day/kimi/chat/completions

POSThttps://api.ai.moses.day/v1/chat/completions

Kimi Chat Completion API, compatible with the official interface format.

OpenAI Responses API

POSThttps://api.ai.moses.day/openai/responses

POSThttps://api.ai.moses.day/v1/responses

OpenAI Responses API, compatible with the official API format.

Monthly Plans

One-time purchase. Credits remain valid for 30 days and do not auto-renew. Every tier unlocks the same models and clients.

Coding PlusOccasional coding

$14.65 Monthly Credit Allowance

500Included Credits

Base Credits 400Limited-time bonus +100

Offer ends 09/30/2026

500 Credits during the promotion, including a 100-Credit limited-time bonus

Coding StandardEveryday coding

$44.23 Monthly Credit Allowance

1,600Included Credits

Base Credits 1,200Limited-time bonus +400

Offer ends 09/30/2026

1,600 Credits during the promotion, including a 400-Credit limited-time bonus
For multi-repository development, code review, and sustained agent work

Coding ProHigh-intensity development

$103.41 Monthly Credit Allowance

4,000Included Credits

Base Credits 3,000Limited-time bonus +1,000

Offer ends 09/30/2026

4,000 Credits during the promotion, including a 1,000-Credit limited-time bonus
For multi-repository development, code review, and sustained agent work

Coding MaxTeams and automation

$206.96 Monthly Credit Allowance

10,000Included Credits

Base Credits 8,000Limited-time bonus +2,000

Offer ends 09/30/2026

10,000 Credits during the promotion, including a 2,000-Credit limited-time bonus
Built for long context, complex refactors, and frequent agent loops

One-time purchase · Credits valid for 30 days from purchase · No automatic renewal · All plans unlock the same model and client access

How to understand Credit usage

Uncached input, output, cache writes, and cache reads are metered separately. Actual usage depends on the model, context, caching, tools, and parallel work. Each purchase extends the Coding Application by 30 days with no auto-renewal.