Skip to main content
A2Agent charges per token consumed. Rates are listed below in USD per 1 million tokens and apply to both input (prompt) and output (completion) tokens counted separately. You only pay for what you use, there is no monthly subscription fee, and your balance never expires.

Pricing Table

ModelPlatformContextInput ($/1M)Output ($/1M)
deepseek-v4-flashDeepSeek128K$0.140$0.280
deepseek-v4-proDeepSeek128K$0.435$0.870
deepseek-chatDeepSeek64Kvariesvaries
glm-4.6GLM (智谱)205K$0.600$2.20
glm-4.7GLM (智谱)205K$0.600$2.20
glm-5GLM (智谱)203K$1.00$3.20
glm-5-turboGLM (智谱)203K$1.20$4.00
glm-5.1GLM (智谱)203K$1.15$4.00
glm-5.2GLM (智谱)$0.600$2.20
kimi-k2.5Kimi (Moonshot)256K$0.600$3.00
kimi-k2.6Kimi (Moonshot)256K$0.950$4.00
kimi-k2.7-codeKimi (Moonshot)$0.600$2.50
minimax-m2.1MiniMax200K$0.300$1.20
minimax-m2.5MiniMax200K$0.300$1.20
minimax-m2.7MiniMax200K$0.300$1.20
qwen3.5-plusQwen (通义千问)$0.500$3.00
qwen3.6-35b-a3bQwen (通义千问)$0.400$1.20
qwen3.6-plusQwen (通义千问)$0.325$1.95
qwen3.7-maxQwen (通义千问)$1.70$5.10
qwen3.7-plusQwen (通义千问)$0.400$1.20
Prices shown are standard channel rates synced with each platform’s billing. Logged-in users may see exclusive lower-priced channel options for select models. Log in to check your rates →

How Billing Works

A2Agent uses a straightforward pay-as-you-go model with no hidden charges.
  • Per-request token counting — Input tokens (your prompt, system message, and conversation history) and output tokens (the model’s response) are counted separately and billed at their respective rates.
  • Real-time balance deduction — Your account balance is deducted immediately after each request completes. You can monitor usage in your dashboard at any time.
  • No minimum spend — Top up any amount and start making requests right away. There is no minimum balance requirement.
  • Balance never expires — Any unused balance stays in your account indefinitely. You will not lose credits due to inactivity.

Volume Discounts (Enterprise)

If your application processes high token volumes, the A2Agent Enterprise plan gives you access to tiered top-up discounts and dedicated concurrency limits so your workloads are never rate-throttled by shared infrastructure.

Volume Top-Up Discounts

Unlock lower effective per-token rates as your monthly spend grows. Discounts are applied automatically based on your usage tier.

Dedicated Concurrency

Reserve concurrency capacity exclusive to your account so high-traffic spikes don’t affect your response times.
To discuss an Enterprise plan, contact the A2Agent team at a2agent.me/about.

Supported Top-Up Methods

You can add balance to your account using any of the following payment methods:
  • USDT — Direct stablecoin transfer; ideal for international users who prefer crypto payments.
  • Stripe — Credit and debit card payments processed securely via Stripe.
  • PayPal — Pay with your PayPal balance or any card linked to your PayPal account.
  • Overseas credit / debit cards — Visa, Mastercard, and other major international cards accepted directly.
For a full walkthrough of the top-up flow and minimum amounts, visit your billing page.