Chinese model APIs on one OpenAI-compatible key. Browse models

Usage-based billing

Chinese model API pricing in USD

SmarToken shows token rates up front with no additional platform surcharge. Only routes marked Live are callable; Integrating rates are for reference.

Getting started

Prepaid

New accounts start at $0. Top up to use the API. View current rewards.

Platform fee

0%

No additional platform surcharge on listed model rates.

Controls

Budgets

Set daily, monthly and model-family limits per API key from the console.

DeepSeek pricing by time and cache

USD per 1M tokens. Prices reflect the model rates without a platform surcharge.

ModelPeriodInput (cache miss)Input (cache hit)Output
DeepSeek FlashPeak$0.3$0.006$1.2
DeepSeek FlashOff-peak$0.15$0.003$0.6
DeepSeek V4 ProPeak$1.32$0.044$3.96
DeepSeek V4 ProOff-peak$0.66$0.022$1.98

Peak: Monday–Friday, 09:00–12:00 and 14:00–18:00 Beijing time, excluding Chinese public holidays. All other hours are off-peak. The rate is selected when your request starts; cache discounts use the provider-reported token counts.

DeepSeek official pricing

DeepSeek reference prices use peak hours and uncached input. Off-peak rates are 50% lower; cached input is billed at its discounted rate. View all DeepSeek rates

DeepSeek Flash

Live

deepseek-chat

China

In: $0.3/1MOut: $1.2/1M

coding copilots, support agents

DeepSeek V4 Pro

Live

deepseek-v4-pro

China

In: $1.32/1MOut: $3.96/1M

research, coding

GLM-5.2

Live

glm-5.2

China

In: $1.4/1MOut: $4.4/1M

enterprise assistants, coding support

GLM-5.3

Live

glm-5.3

China

In: $1.4/1MOut: $4.4/1M

enterprise assistants, coding support

Kimi K2.7 Code

Live

kimi-k2.7-code

China

In: $0.95/1MOut: $4/1M

chat, coding

Kimi K3

Live

kimi-k3

China

In: $3/1MOut: $15/1M

deep research, agent planning

Kimi K3.1 Pro

Live

kimi-k3.1-pro

China

In: $2/1MOut: $10/1M

chat, coding

MiniMax M2.7

Live

minimax-m2

China

In: $0.3/1MOut: $1.2/1M

coding agents, text analysis

360 Zhinao

Integrating

360zhinao2-o1

China

In: $0.4/1MOut: $1/1M

security assistants, Chinese chat

Baichuan4 Turbo

Integrating

baichuan4-turbo

China

In: $1.5/1MOut: $1.5/1M

domain assistants, Chinese knowledge QA

Doubao Seed

Integrating

doubao-seed

China

In: $0.7/1MOut: $2.8/1M

consumer chat, content workflows

ERNIE 4 Turbo

Integrating

ernie-4-turbo

China

In: $0.9/1MOut: $3.6/1M

Chinese knowledge QA, enterprise search

GLM-4 Flash

Integrating

glm-4-flash

China

In: $0.8/1MOut: $3.2/1M

internal tools, knowledge assistants

GLM-5V Turbo

Integrating

glm-5v-turbo

China

In: $1.2/1MOut: $4/1M

visual QA, document screenshots

Hunyuan TurboS

Integrating

hunyuan-turbos

China

In: $0.8/1MOut: $3.2/1M

enterprise assistants, code generation

InternLM3

Integrating

internlm3

China

In: $0.2/1MOut: $0.8/1M

self-hosted chat, research evals

Kimi K2

Integrating

kimi-k2

China

In: $0.6/1MOut: $2.5/1M

research assistants, codebase analysis

Kimi K2.6

Integrating

kimi-k2.6

China

In: $0.95/1MOut: $4/1M

research assistants, codebase analysis

LongCat Flash

Integrating

longcat-flash

China

In: $0.4/1MOut: $1.6/1M

agentic reasoning, multimodal prototypes

MiniMax M3

Integrating

minimax-m3

China

In: $0.6/1MOut: $2.4/1M

coding agents, tool-use workflows

MiniMax Video-01

Integrating

minimax-video-01

China

In: $3/1MOut: $3/1M

marketing video drafts, avatar-style clips

Pangu NLP

Integrating

pangu-nlp

China

In: $1/1MOut: $4/1M

industry assistants, private cloud workflows

Qwen Plus

Integrating

qwen-plus

China

In: $1.2/1MOut: $4.8/1M

multilingual chat, structured extraction

Qwen3.7 Plus

Integrating

qwen3.7-plus

China

In: $0.276/1MOut: $1.101/1M

multilingual chat, vision QA

SenseNova V6

Integrating

sensenova-v6

China

In: $0.8/1MOut: $3.2/1M

multimodal assistants, visual QA

Spark X1

Integrating

spark-x1

China

In: $0.7/1MOut: $2.8/1M

education assistants, reasoning QA

Step-3

Integrating

step-3

China

In: $0.5/1MOut: $2/1M

coding tools, agent platforms

Wan Text-to-Video

Integrating

wan-t2v

China

In: $2.5/1MOut: $2.5/1M

promo clips, product demos

Yi Large

Integrating

yi-large

China

In: $0.9/1MOut: $0.9/1M

bilingual writing, structured output

Usage estimator

Estimate uses the listed model rates without a platform surcharge.

Selected billable rate

Input $0.3/1M tokens, output $1.2/1M tokens.

Catalog: $0.3 input / $1.2 output.

Estimated $0.54/ month

Calculated in USD using listed model rates.

How credits are consumed

  • Each completed request records prompt tokens, completion tokens, final billable cost and provider latency.
  • Billable model rates follow the published model rates without a platform surcharge.
  • Streaming responses settle after the stream finishes, then write usage and wallet debit records.
  • Unknown model IDs are rejected before provider calls, with available model suggestions.
  • Budget-limited API keys return 402 when a daily, monthly or model-scope rule is exceeded.
Read budget docs

Wallet balance

Prepaid USD credit

SmarToken settles usage against account balance after requests finish. Paid top-ups and any earned rewards appear in the wallet ledger so teams can reconcile usage with final billable spend.

Top-up methods

Check payment options in Billing

Add funds using Stripe Checkout. The Stripe merchant is Stellar Ever Co., Limited; payment options may vary by location. Contact support if you need help.

Security reminder

Verify the official domain

Before payment or API-key work, confirm the address bar shows https://thesmartoken.com. Do not enter credentials or payment details from search ads or unfamiliar domains.