Pricing

Model multipliers, cache hits, and first API-key purchase

Model Pricing

The RMB site uses a CNY 100 per 100M token benchmark, with CNY 10, 50, 100, 298, and 488 packages.

Get API accessTop up existing keyRead integration docs
Existing usersAlready have an API key? Top it up directlyTop up, look up orders, and confirm delivery here; 500M tokens cost CNY 488.Go to top-up
Access URLPrefer the /v1 Base URL
Recommended Base URLhttps://new.weeanno.shop/v1

Use this first for most clients. If your client rejects it, switch to the fallback.

Fallback Base URLhttps://new.weeanno.shop

Different API routers validate Base URLs differently, so test the address when you switch models or clients.

Unified quotaOne key for all supported models
  • Multipliers only map model cost differences; billing stays consistent.
  • You do not need separate keys for separate models.
  • Quota does not expire or reset, which fits long-running testing and stable production usage.
Cache

Cache-Hit Billing

When part of a request matches previously processed content, the system can reuse that computation instead of charging the full input cost again.

What counts as a cache hitRepeated context can be reused

Cache reuse can improve response speed and reduce usage cost, especially in multi-turn chats, repeated workflow calls, and code-completion loops.

  • Normal input: billed at the model multiplier.
  • Repeated cached input: billed from 0.1x.
  • For high-cost models, cache multipliers may rise to 0.2x or be paused during extreme upstream volatility.
Simple example

If you repeatedly include a large shared context across a long conversation, the matched repeated portion can be charged at a lower multiplier.

Cache hits start at 0.1x

Matched cached input is billed at only 10% of the regular input cost.

Longer sessions can cost less

Follow-up chats, workflow calls, and code-completion loops are more likely to reuse repeated context.

Premium models may adjust

When upstream costs move sharply, cache multipliers may change and can be paused in extreme cases.

Note: cache hits depend on whether the request content qualifies for system cache reuse.

Reference

Model Price Reference

Compare multipliers, converted per-token cost, context size, and vision support before you buy.

Updated from the latest model listCurrent converted prices and multipliers

A practical reference for understanding model cost before purchase.

Assumes max_tokens=8192
ProviderModelMultiplierExample: 2x means 100M tokens deducts 200M quotaRecommended context windowAssumes max_tokens=8192Vision support
China aggregate route(High concurrency)
claude-sonnet-4-6Fast response
0.5x1M✅
OpenAI
gpt-5.6-sol
6x258K✅
OpenAI
gpt-5.6-terra
1x258K✅
OpenAI
gpt-5.4
2x1M✅
OpenAI
gpt-5.5
4x258K✅
OpenAI
gpt-5.3-codex-spark
1x128K
OpenAI
gpt-image-2
per image1–2K 出图
OpenAI
gpt-image-2-4k
per image4K 出图
通义千问
qwen3.6-plus
3x1M✅
通义千问
qwen3.7-plus
4x1M✅
通义千问
qwen3.7-max
10x1M
通义千问
qwen3.8-max
20x1M✅
美团 LongCat
LongCat-2.0Agentic Coding
1x1M
腾讯混元
hy3
1x256K
MiniMax
MiniMax-M3
1x1M✅
MiniMax
image-01
per image
MiniMax
image-01-live
per second
StepFun
step-3.7-flashFast response
1x256K✅
ByteDance
doubao-seed-2.1-turbo
3x128K✅
Xiaomi
mimo-v2.5-pro
4x1M
Xiaomi
mimo-v2.5
2x1M✅
DeepSeek
deepseek-v4-pro
7.5x1M
DeepSeek
deepseek-v4-flash
2.5x1M
Kimi
kimi-k3
25x1M✅
Zhipu AI
glm-5.1
5x256K✅
Zhipu AI
glm-5.2
8x1M✅
xAI / Grok
grok-4.5
5x500K✅
Anthropic
claude-haiku-4-5-20251001
1x256K✅
Anthropic
claude-sonnet-5高能力主力
10x1M✅
Anthropic
claude-fable-5顶级任务
40x1M✅
Anthropic
claude-opus-4-6
15x1M✅
Anthropic
claude-opus-4-7
15x1M✅
Anthropic
claude-opus-4-8
15x1M✅
Anthropic
claude-opus-5
15x1M✅
Google
gemini-3.1-pro
10x1M✅
Google
gemini-3.5-flash
6x1M✅
China aggregate routeContext 1M
(High concurrency)claude-sonnet-4-6Fast response
Multiplier0.5x
context window1M
Vision✅
OpenAIContext 258K
gpt-5.6-sol
Multiplier6x
context window258K
Vision✅
OpenAIContext 258K
gpt-5.6-terra
Multiplier1x
context window258K
Vision✅
OpenAIContext 1M
gpt-5.4
Multiplier2x
context window1M
Vision✅
OpenAIContext 258K
gpt-5.5
Multiplier4x
context window258K
Vision✅
OpenAIContext 128K
gpt-5.3-codex-spark
Multiplier1x
context window128K
OpenAIContext 1–2K 出图
gpt-image-2
Multiplierper image
context window1–2K 出图
OpenAIContext 4K 出图
gpt-image-2-4k
Multiplierper image
context window4K 出图
通义千问Context 1M
qwen3.6-plus
Multiplier3x
context window1M
Vision✅
通义千问Context 1M
qwen3.7-plus
Multiplier4x
context window1M
Vision✅
通义千问Context 1M
qwen3.7-max
Multiplier10x
context window1M
通义千问Context 1M
qwen3.8-max
Multiplier20x
context window1M
Vision✅
美团 LongCatContext 1M
LongCat-2.0Agentic Coding
Multiplier1x
context window1M
腾讯混元Context 256K
hy3
Multiplier1x
context window256K
MiniMaxContext 1M
MiniMax-M3
Multiplier1x
context window1M
Vision✅
MiniMax
image-01
Multiplierper image
MiniMax
image-01-live
Multiplierper second
StepFunContext 256K
step-3.7-flashFast response
Multiplier1x
context window256K
Vision✅
ByteDanceContext 128K
doubao-seed-2.1-turbo
Multiplier3x
context window128K
Vision✅
XiaomiContext 1M
mimo-v2.5-pro
Multiplier4x
context window1M
XiaomiContext 1M
mimo-v2.5
Multiplier2x
context window1M
Vision✅
DeepSeekContext 1M
deepseek-v4-pro
Multiplier7.5x
context window1M
DeepSeekContext 1M
deepseek-v4-flash
Multiplier2.5x
context window1M
KimiContext 1M
kimi-k3
Multiplier25x
context window1M
Vision✅
Zhipu AIContext 256K
glm-5.1
Multiplier5x
context window256K
Vision✅
Zhipu AIContext 1M
glm-5.2
Multiplier8x
context window1M
Vision✅
xAI / GrokContext 500K
grok-4.5
Multiplier5x
context window500K
Vision✅
AnthropicContext 256K
claude-haiku-4-5-20251001
Multiplier1x
context window256K
Vision✅
AnthropicContext 1M
claude-sonnet-5高能力主力
Multiplier10x
context window1M
Vision✅
AnthropicContext 1M
claude-fable-5顶级任务
Multiplier40x
context window1M
Vision✅
AnthropicContext 1M
claude-opus-4-6
Multiplier15x
context window1M
Vision✅
AnthropicContext 1M
claude-opus-4-7
Multiplier15x
context window1M
Vision✅
AnthropicContext 1M
claude-opus-4-8
Multiplier15x
context window1M
Vision✅
AnthropicContext 1M
claude-opus-5
Multiplier15x
context window1M
Vision✅
GoogleContext 1M
gemini-3.1-pro
Multiplier10x
context window1M
Vision✅
GoogleContext 1M
gemini-3.5-flash
Multiplier6x
context window1M
Vision✅

Prices above are reference conversions based on current multipliers. Image models are billed per image or second. Actual usage follows the platform multiplier and request consumption; ✅ means vision is supported.

Next

Ready to buy after checking the price table

This page explains multipliers, cache hits, and model cost. New users can buy an API key; existing users can top up an existing key.

Get API accessRead integration docsTop up existing key