Your privacy choices

Allow optional cookies for referral attribution, visit analytics, and Google Ads purchase measurement.

Pricing

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

Model Pricing

Billing is based on 100M tokens: 1x costs CNY 40, or CNY 0.40 per 1M tokens. Purchase and top-up packages share the same six self-service tiers; contact support for larger volume.

Get API accessTop up existing keyRead integration docs
Existing usersAlready have an API key? Top it up directlyRecharge, order lookup, and delivery checks all happen here. New packages go as low as CNY 26.67 / 100M tokens.Go to top-up
Billing

How Billing Works

We bill in 100M-token units. Multipliers simply map model cost differences, and one key works across all supported models.

Core conversionStart with the baseline price
100M tokensCNY 40

Baseline at 1x

1M tokensCNY 0.40

Converted at 1x

USD-equivalentCNY 0.20

NewAPI $2 / 1M maps to our 1x standard

1M tokens cost CNY 0.40 at the baseline. A NewAPI marketplace price of $2 / 1M maps to our 1x standard.

One API key works across all models. Multipliers keep model costs easy to compare, so you can choose by use case without changing keys.

BaselineMultiplier Quick Reference
Multiplier100M tokens1M tokens
0.5xCNY 20CNY 0.2
1xCNY 40CNY 0.4
2xCNY 80CNY 0.8
2.5xCNY 100CNY 1
3xCNY 120CNY 1.2
4xCNY 160CNY 1.6
5xCNY 200CNY 2
6xCNY 240CNY 2.4
7.5xCNY 300CNY 3
8xCNY 320CNY 3.2
10xCNY 400CNY 4
15xCNY 600CNY 6
20xCNY 800CNY 8
25xCNY 1000CNY 10
37.5xCNY 1500CNY 15
40xCNY 1600CNY 16
Access URLPrefer the /v1 Base URL
Recommended Base URLhttps://api.llm-token.cn/v1

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

Fallback Base URLhttps://gpt-agent.cc

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.

claude-sonnet-4-6 concurrency route

claude-sonnet-4-6 is a concurrency-oriented route compatible with common client defaults, suitable for high-concurrency workflows, Python scripts, and text processing.

Premium model note

Premium model cost and availability may move with upstream supply. Use the live multiplier shown here and your actual call results as the final reference.

Python concurrency limit

Python-script concurrency is only allowed on claude-sonnet-4-6. Other models should not be used for high-concurrency scripts.

Updated from the latest model listCurrent converted prices and multipliers

A practical reference for understanding model cost before purchase.

Assumes max_tokens=8192
1x = CNY 40 / 100M tokens0.8x from CNY 0.32 / 1M tokens25x premium routes = CNY 10 / 1M tokensUp to 1M context
ProviderModelMultiplierExample: 2x means 100M tokens deducts 200M quota1M tokensConverted priceRecommended context windowAssumes max_tokens=8192Vision support
Guishu optimised(High concurrency)
claude-sonnet-4-6
0.5xInput CNY 0.2 · Output CNY 11M✅
OpenAI
gpt-5.4
3xInput CNY 1.2 · Output CNY 7.21M✅
OpenAI
gpt-5.5
6xInput CNY 2.4 · Output CNY 14.4258K✅
OpenAI
gpt-image-2
Per imageCNY 0.1 / image1–2K output
OpenAI
gpt-5.6-sol
6xInput CNY 2.4 · Output CNY 14.4258K✅
OpenAI
gpt-5.6-terra
2.5xInput CNY 1 · Output CNY 5258K✅
xAI / Grok
grok-4.6
10xInput CNY 4 · Output CNY 20500K
xAI / Grok
grok-4.5
5xInput CNY 2 · Output CNY 10500K✅
Anthropic
claude-haiku-4-5-20251001
1xInput CNY 0.4 · Output CNY 2256K✅
Anthropic
claude-sonnet-5
10xInput CNY 4 · Output CNY 201M✅
Anthropic
claude-fable-5
40xInput CNY 16 · Output CNY 801M✅
Anthropic
claude-opus-4-6
15xInput CNY 6 · Output CNY 301M✅
Anthropic
claude-opus-4-7
15xInput CNY 6 · Output CNY 301M✅
Anthropic
claude-opus-4-8
15xInput CNY 6 · Output CNY 301M✅
Anthropic
claude-opus-5
15xInput CNY 6 · Output CNY 301M✅
Alibaba Cloud / Qwen
qwen3.6-plus
3xInput CNY 1.2 · Output CNY 61M✅
Alibaba Cloud / Qwen
qwen3.7-plus
4xInput CNY 1.6 · Output CNY 81M✅
Alibaba Cloud / Qwen
qwen3.7-max
10xInput CNY 4 · Output CNY 121M
Alibaba Cloud / Qwen
qwen3.8-max
20xInput CNY 8 · Output CNY 241M✅
Meituan / LongCat
LongCat-2.0
1xInput CNY 0.4 · Output CNY 1.61M
Tencent Hunyuan
hy3
1xInput CNY 0.4 · Output CNY 2256K
MiniMax
MiniMax-M3
1xInput CNY 0.4 · Output CNY 21M✅
MiniMax
image-01
Per imageCNY 0.8 / image—
MiniMax
image-01-live
4xInput CNY 1.6 · Output CNY 1.6—
StepFun
step-3.7-flash
1xInput CNY 0.4 · Output CNY 2256K✅
ByteDance / Doubao
doubao-seed-2.1-turbo
3xInput CNY 1.2 · Output CNY 6128K✅
Xiaomi / MiMo
mimo-v2.5-pro
4xInput CNY 1.6 · Output CNY 81M
Xiaomi / MiMo
mimo-v2.5
2xInput CNY 0.8 · Output CNY 41M✅
DeepSeek
deepseek-v4-pro
7.5xInput CNY 3 · Output CNY 151M
DeepSeek
deepseek-v4-flash
2.5xInput CNY 1 · Output CNY 51M
Moonshot AI / Kimi
kimi-k3
25xInput CNY 10 · Output CNY 501M✅
Zhipu AI / Z.ai
glm-5.1
5xInput CNY 2 · Output CNY 10256K✅
Zhipu AI / Z.ai
glm-5.2
8xInput CNY 3.2 · Output CNY 161M✅
Anthropic
claude-opus-4-5-20251101
20xInput CNY 8 · Output CNY 40—
Anthropic
claude-opus-4-5-20251101-thinking
37.5xInput CNY 15 · Output CNY 75—
Anthropic
claude-opus-4-6-high
15xInput CNY 6 · Output CNY 301M✅
Anthropic
claude-opus-4-6-low
15xInput CNY 6 · Output CNY 301M✅
Anthropic
claude-opus-4-6-max
15xInput CNY 6 · Output CNY 301M✅
Anthropic
claude-opus-4-6-medium
15xInput CNY 6 · Output CNY 301M✅
Anthropic
claude-opus-4-6-thinking
15xInput CNY 6 · Output CNY 301M✅
Anthropic
claude-opus-4-7-high
37.5xInput CNY 15 · Output CNY 751M✅
Anthropic
claude-opus-4-7-low
37.5xInput CNY 15 · Output CNY 751M✅
Anthropic
claude-opus-4-7-max
15xInput CNY 6 · Output CNY 301M✅
Anthropic
claude-opus-4-7-medium
37.5xInput CNY 15 · Output CNY 751M✅
Anthropic
claude-opus-4-7-thinking
37.5xInput CNY 15 · Output CNY 751M✅
Anthropic
claude-opus-4-7-xhigh
37.5xInput CNY 15 · Output CNY 751M✅
Anthropic
claude-opus-5-high
20xInput CNY 8 · Output CNY 401M✅
Anthropic
claude-opus-5-low
20xInput CNY 8 · Output CNY 401M✅
Anthropic
claude-opus-5-max
20xInput CNY 8 · Output CNY 401M✅
Anthropic
claude-opus-5-medium
20xInput CNY 8 · Output CNY 401M✅
Anthropic
claude-opus-5-thinking
20xInput CNY 8 · Output CNY 401M✅
Anthropic
claude-opus-5-xhigh
20xInput CNY 8 · Output CNY 401M✅
字节跳动
doubao-seed-2.0-code
3xInput CNY 1.2 · Output CNY 6—
字节跳动
doubao-seed-2.0-lite
1xInput CNY 0.4 · Output CNY 2—
字节跳动
doubao-seed-2.0-pro
3xInput CNY 1.2 · Output CNY 6—
Google
gemini-3-flash
3xInput CNY 1.2 · Output CNY 6—
Google
gemini-3.1-pro
10xInput CNY 4 · Output CNY 20—
Google
gemini-3.5-flash
6xInput CNY 2.4 · Output CNY 12—
智谱
glm-5-turbo
5xInput CNY 2 · Output CNY 10—
智谱
glm-5.3
8xInput CNY 3.2 · Output CNY 16—
OpenAI
gpt-5.4-mini
2xInput CNY 0.8 · Output CNY 4.8—
OpenAI
gpt-5.4-openai-compact
2.5xInput CNY 1 · Output CNY 61M✅
OpenAI
gpt-5.5-openai-compact
5xInput CNY 2 · Output CNY 10258K✅
OpenAI
gpt-5.6-luna
1xInput CNY 0.4 · Output CNY 2.4—
Moonshot
kimi-k2.6
2xInput CNY 0.8 · Output CNY 4—
Moonshot
kimi-k2.7
8xInput CNY 3.2 · Output CNY 16—
其他
MiniMax-M2.7
0.5xInput CNY 0.2 · Output CNY 1—
其他
MiniMax-M2.7-highspeed
1xInput CNY 0.4 · Output CNY 2—
MiniMax
MiniMax-M3-highspeed
2xInput CNY 0.8 · Output CNY 41M✅
阿里巴巴
qwen3.6-flash
2xInput CNY 0.8 · Output CNY 4—
字节跳动
火山-豆包/doubao-seed-2.0-code
37.5xInput CNY 15 · Output CNY 15—
字节跳动
火山-豆包/doubao-seed-2.1-turbo
37.5xInput CNY 15 · Output CNY 15—
Guishu optimisedContext 1M
(High concurrency)claude-sonnet-4-6
Multiplier0.5x
1M tokensInput CNY 0.2 · Output CNY 1
context window1M
Vision✅
OpenAIContext 1M
gpt-5.4
Multiplier3x
1M tokensInput CNY 1.2 · Output CNY 7.2
context window1M
Vision✅
OpenAIContext 258K
gpt-5.5
Multiplier6x
1M tokensInput CNY 2.4 · Output CNY 14.4
context window258K
Vision✅
OpenAIContext 1–2K output
gpt-image-2
MultiplierPer image
1M tokensCNY 0.1 / image
context window1–2K output
OpenAIContext 258K
gpt-5.6-sol
Multiplier6x
1M tokensInput CNY 2.4 · Output CNY 14.4
context window258K
Vision✅
OpenAIContext 258K
gpt-5.6-terra
Multiplier2.5x
1M tokensInput CNY 1 · Output CNY 5
context window258K
Vision✅
xAI / GrokContext 500K
grok-4.6
Multiplier10x
1M tokensInput CNY 4 · Output CNY 20
context window500K
xAI / GrokContext 500K
grok-4.5
Multiplier5x
1M tokensInput CNY 2 · Output CNY 10
context window500K
Vision✅
AnthropicContext 256K
claude-haiku-4-5-20251001
Multiplier1x
1M tokensInput CNY 0.4 · Output CNY 2
context window256K
Vision✅
AnthropicContext 1M
claude-sonnet-5
Multiplier10x
1M tokensInput CNY 4 · Output CNY 20
context window1M
Vision✅
AnthropicContext 1M
claude-fable-5
Multiplier40x
1M tokensInput CNY 16 · Output CNY 80
context window1M
Vision✅
AnthropicContext 1M
claude-opus-4-6
Multiplier15x
1M tokensInput CNY 6 · Output CNY 30
context window1M
Vision✅
AnthropicContext 1M
claude-opus-4-7
Multiplier15x
1M tokensInput CNY 6 · Output CNY 30
context window1M
Vision✅
AnthropicContext 1M
claude-opus-4-8
Multiplier15x
1M tokensInput CNY 6 · Output CNY 30
context window1M
Vision✅
AnthropicContext 1M
claude-opus-5
Multiplier15x
1M tokensInput CNY 6 · Output CNY 30
context window1M
Vision✅
Alibaba Cloud / QwenContext 1M
qwen3.6-plus
Multiplier3x
1M tokensInput CNY 1.2 · Output CNY 6
context window1M
Vision✅
Alibaba Cloud / QwenContext 1M
qwen3.7-plus
Multiplier4x
1M tokensInput CNY 1.6 · Output CNY 8
context window1M
Vision✅
Alibaba Cloud / QwenContext 1M
qwen3.7-max
Multiplier10x
1M tokensInput CNY 4 · Output CNY 12
context window1M
Alibaba Cloud / QwenContext 1M
qwen3.8-max
Multiplier20x
1M tokensInput CNY 8 · Output CNY 24
context window1M
Vision✅
Meituan / LongCatContext 1M
LongCat-2.0
Multiplier1x
1M tokensInput CNY 0.4 · Output CNY 1.6
context window1M
Tencent HunyuanContext 256K
hy3
Multiplier1x
1M tokensInput CNY 0.4 · Output CNY 2
context window256K
MiniMaxContext 1M
MiniMax-M3
Multiplier1x
1M tokensInput CNY 0.4 · Output CNY 2
context window1M
Vision✅
MiniMaxContext —
image-01
MultiplierPer image
1M tokensCNY 0.8 / image
context window—
MiniMaxContext —
image-01-live
Multiplier4x
1M tokensInput CNY 1.6 · Output CNY 1.6
context window—
StepFunContext 256K
step-3.7-flash
Multiplier1x
1M tokensInput CNY 0.4 · Output CNY 2
context window256K
Vision✅
ByteDance / DoubaoContext 128K
doubao-seed-2.1-turbo
Multiplier3x
1M tokensInput CNY 1.2 · Output CNY 6
context window128K
Vision✅
Xiaomi / MiMoContext 1M
mimo-v2.5-pro
Multiplier4x
1M tokensInput CNY 1.6 · Output CNY 8
context window1M
Xiaomi / MiMoContext 1M
mimo-v2.5
Multiplier2x
1M tokensInput CNY 0.8 · Output CNY 4
context window1M
Vision✅
DeepSeekContext 1M
deepseek-v4-pro
Multiplier7.5x
1M tokensInput CNY 3 · Output CNY 15
context window1M
DeepSeekContext 1M
deepseek-v4-flash
Multiplier2.5x
1M tokensInput CNY 1 · Output CNY 5
context window1M
Moonshot AI / KimiContext 1M
kimi-k3
Multiplier25x
1M tokensInput CNY 10 · Output CNY 50
context window1M
Vision✅
Zhipu AI / Z.aiContext 256K
glm-5.1
Multiplier5x
1M tokensInput CNY 2 · Output CNY 10
context window256K
Vision✅
Zhipu AI / Z.aiContext 1M
glm-5.2
Multiplier8x
1M tokensInput CNY 3.2 · Output CNY 16
context window1M
Vision✅
AnthropicContext —
claude-opus-4-5-20251101
Multiplier20x
1M tokensInput CNY 8 · Output CNY 40
context window—
AnthropicContext —
claude-opus-4-5-20251101-thinking
Multiplier37.5x
1M tokensInput CNY 15 · Output CNY 75
context window—
AnthropicContext 1M
claude-opus-4-6-high
Multiplier15x
1M tokensInput CNY 6 · Output CNY 30
context window1M
Vision✅
AnthropicContext 1M
claude-opus-4-6-low
Multiplier15x
1M tokensInput CNY 6 · Output CNY 30
context window1M
Vision✅
AnthropicContext 1M
claude-opus-4-6-max
Multiplier15x
1M tokensInput CNY 6 · Output CNY 30
context window1M
Vision✅
AnthropicContext 1M
claude-opus-4-6-medium
Multiplier15x
1M tokensInput CNY 6 · Output CNY 30
context window1M
Vision✅
AnthropicContext 1M
claude-opus-4-6-thinking
Multiplier15x
1M tokensInput CNY 6 · Output CNY 30
context window1M
Vision✅
AnthropicContext 1M
claude-opus-4-7-high
Multiplier37.5x
1M tokensInput CNY 15 · Output CNY 75
context window1M
Vision✅
AnthropicContext 1M
claude-opus-4-7-low
Multiplier37.5x
1M tokensInput CNY 15 · Output CNY 75
context window1M
Vision✅
AnthropicContext 1M
claude-opus-4-7-max
Multiplier15x
1M tokensInput CNY 6 · Output CNY 30
context window1M
Vision✅
AnthropicContext 1M
claude-opus-4-7-medium
Multiplier37.5x
1M tokensInput CNY 15 · Output CNY 75
context window1M
Vision✅
AnthropicContext 1M
claude-opus-4-7-thinking
Multiplier37.5x
1M tokensInput CNY 15 · Output CNY 75
context window1M
Vision✅
AnthropicContext 1M
claude-opus-4-7-xhigh
Multiplier37.5x
1M tokensInput CNY 15 · Output CNY 75
context window1M
Vision✅
AnthropicContext 1M
claude-opus-5-high
Multiplier20x
1M tokensInput CNY 8 · Output CNY 40
context window1M
Vision✅
AnthropicContext 1M
claude-opus-5-low
Multiplier20x
1M tokensInput CNY 8 · Output CNY 40
context window1M
Vision✅
AnthropicContext 1M
claude-opus-5-max
Multiplier20x
1M tokensInput CNY 8 · Output CNY 40
context window1M
Vision✅
AnthropicContext 1M
claude-opus-5-medium
Multiplier20x
1M tokensInput CNY 8 · Output CNY 40
context window1M
Vision✅
AnthropicContext 1M
claude-opus-5-thinking
Multiplier20x
1M tokensInput CNY 8 · Output CNY 40
context window1M
Vision✅
AnthropicContext 1M
claude-opus-5-xhigh
Multiplier20x
1M tokensInput CNY 8 · Output CNY 40
context window1M
Vision✅
字节跳动Context —
doubao-seed-2.0-code
Multiplier3x
1M tokensInput CNY 1.2 · Output CNY 6
context window—
字节跳动Context —
doubao-seed-2.0-lite
Multiplier1x
1M tokensInput CNY 0.4 · Output CNY 2
context window—
字节跳动Context —
doubao-seed-2.0-pro
Multiplier3x
1M tokensInput CNY 1.2 · Output CNY 6
context window—
GoogleContext —
gemini-3-flash
Multiplier3x
1M tokensInput CNY 1.2 · Output CNY 6
context window—
GoogleContext —
gemini-3.1-pro
Multiplier10x
1M tokensInput CNY 4 · Output CNY 20
context window—
GoogleContext —
gemini-3.5-flash
Multiplier6x
1M tokensInput CNY 2.4 · Output CNY 12
context window—
智谱Context —
glm-5-turbo
Multiplier5x
1M tokensInput CNY 2 · Output CNY 10
context window—
智谱Context —
glm-5.3
Multiplier8x
1M tokensInput CNY 3.2 · Output CNY 16
context window—
OpenAIContext —
gpt-5.4-mini
Multiplier2x
1M tokensInput CNY 0.8 · Output CNY 4.8
context window—
OpenAIContext 1M
gpt-5.4-openai-compact
Multiplier2.5x
1M tokensInput CNY 1 · Output CNY 6
context window1M
Vision✅
OpenAIContext 258K
gpt-5.5-openai-compact
Multiplier5x
1M tokensInput CNY 2 · Output CNY 10
context window258K
Vision✅
OpenAIContext —
gpt-5.6-luna
Multiplier1x
1M tokensInput CNY 0.4 · Output CNY 2.4
context window—
MoonshotContext —
kimi-k2.6
Multiplier2x
1M tokensInput CNY 0.8 · Output CNY 4
context window—
MoonshotContext —
kimi-k2.7
Multiplier8x
1M tokensInput CNY 3.2 · Output CNY 16
context window—
其他Context —
MiniMax-M2.7
Multiplier0.5x
1M tokensInput CNY 0.2 · Output CNY 1
context window—
其他Context —
MiniMax-M2.7-highspeed
Multiplier1x
1M tokensInput CNY 0.4 · Output CNY 2
context window—
MiniMaxContext 1M
MiniMax-M3-highspeed
Multiplier2x
1M tokensInput CNY 0.8 · Output CNY 4
context window1M
Vision✅
阿里巴巴Context —
qwen3.6-flash
Multiplier2x
1M tokensInput CNY 0.8 · Output CNY 4
context window—
字节跳动Context —
火山-豆包/doubao-seed-2.0-code
Multiplier37.5x
1M tokensInput CNY 15 · Output CNY 15
context window—
字节跳动Context —
火山-豆包/doubao-seed-2.1-turbo
Multiplier37.5x
1M tokensInput CNY 15 · Output CNY 15
context window—

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