tencent cloud

LLM Service TokenHub

DocumentationLLM Service TokenHubToken PlanPersonal Token PlanPersonal Token Plan Credit Deduction Rules

Personal Token Plan Credit Deduction Rules

Download
Focus Mode
Font Size
Last updated: 2026-09-15 14:56:06
AI-Translated
Credits are adopted as the unified consumption unit for usage within the Token Plan Personal Edition package. This document helps you quickly understand the rules for deducting package usage.

Credit Definition

Credits are the unified consumption billing unit for the Token Plan Personal Edition package, used to quantify the consumption of model resources.

Deduction Rules

Credits consumed per request = (Number of input tokens that cache input × Deduction coefficient for cached input + Number of input tokens that miss the cache × Deduction coefficient for non-cached input + Number of output tokens × Credit coefficient for output) / 1,000,000.

Credit Deduction Price

Attention:
The DeepSeek Vendor Direct model is now available. Meanwhile, to allocate resources more rationally and improve service stability, we are adjusting the model pricing policy in sync with the vendor by introducing a peak/off-peak pricing mechanism:
The off-peak price is half of the peak price. Peak hours are 9:00–12:00 and 14:00–18:00 Beijing Time (all other hours are off-peak). The new credit deduction rates will take effect at 00:00 Beijing Time on August 17, 2026.
Peak/Off-Peak Period Determination Rules: The billing period is determined by the period during which the request is initiated. Specifically, requests initiated during peak hours are billed at the peak price for the entire duration, and requests initiated during off-peak hours are billed at the off-peak price for the entire duration, regardless of when the requests are actually completed.
Limited-time discounts are available on the credit deduction coefficients of select models. For details, see Limited-Time Offers.
Model
Model ID
Condition
Deduction Coefficient for Cache-Missed Input
Output Deduction Coefficient
Deduction Coefficient for Cache Input
Auto model
auto
-
82
237
7
GLM-5.3-Flash
glm-5.3-flash
-
23.438
78.125
4.688
GLM-5.2
glm-5.2
glm-5-2
-
154
482
29
Kimi K3
kimi-k3
-
468.75
2343.75
46.875
Kimi-K2.6
kimi-k2.6
kimi-k-2-6
-
115
474
20
DeepSeek-V4.1-Flash (Vendor Direct)
deepseek/deepseek-flash
OFF-PEAK
21.429
85.714
0.429
PEAK
42.857
171.429
0.857
DeepSeek-V4-Pro 0813 Official Release (Vendor Direct)
deepseek-v4-pro-202606
deepseek/deepseek-v4-pro-0813
deepseek/deepseek-v4-pro
OFF-PEAK
94.286
282.857
3.143
PEAK
188.571
565.714
6.286
DeepSeek-V4-Flash 0731 Official Release (Vendor Direct)
deepseek-v4-flash-202605
deepseek/deepseek-v4-flash-0731
deepseek/deepseek-v4-flash
OFF-PEAK
21.429
85.714
0.429
PEAK
42.857
171.429
0.857
MiniMax-M3
minimax-m3
Input length (tokens) ≤ 512k
47
188
10
Input length (tokens) > 512k
94
375
19

Limited-Time Offer

During the promotion period, Personal Token Plan users can calculate credit consumption according to the promotional discount rules when invoking designated models. The discount takes effect automatically after the promotion starts, with no application required.
Eligible Participants: All Token Plan Personal Edition users.
Note:
The promotion only adjusts the credit deduction prices of applicable models during the promotion period, without changing other models in the plan, the plan quota refresh rules, or usage limits.
After the promotion ends, the credit prices of applicable models will revert to the list prices shown in Credit Deduction Prices. For requests that span the promotion period, credits will be deducted based on the credit price at the time the request is initiated.
Tencent Cloud may change or adjust the promotion based on operational conditions, including but not limited to the promotion rules and promotion period. Please refer to the latest content on the page.

Promotion 1

Promotion Period: 00:00:00 September 4, 2026 to 23:59:59 September 30, 2026 (Beijing Time)
Promotion Rules: The credit prices of the following models enjoy a 5% discount off the list price. The limited-time promotional credit prices are as follows:
Model
Model ID
Input Length
(tokens)
Input Deduction Coefficient
Output Deduction Coefficient
Cache Hit Deduction Coefficient
Kimi K3
kimi-k3
/
445.313
2226.563
44.531

Deduction Example

Assume the requested model is Kimi-K2.6, and for a specific request, the cached input is 50k tokens, the non-cached input is 10k tokens, and the output is 0.5k tokens. 2.387 credits are consumed. The detailed calculation is as follows:
Credits consumed per request
= (Number of input tokens that hit the cache × Deduction coefficient for cached input +
Number of input tokens that miss the cache × Deduction coefficient for non-cached input +
Number of output tokens × Credit coefficient for output) / 1,000,000
= (50000 × 20 + 10000 × 115 + 500 × 474) / 1000000
= 2.387


Help and Support

Was this page helpful?

Help us improve! Rate your documentation experience in 5 mins.

Feedback