Deducted based on tokens
Metrics are tracked separately for input, output, and cached tokens; invoices are itemized down to the individual request level and can be exported for reconciliation.
Plans and Pricing
Pay-as-you-go, with no expiration date on your credit balance
No monthly fees, no mandatory subscriptions, and no minimum spending requirements. You’re billed based on the actual number of tokens used per request. Below are the unit prices for all models—you can view them right now without having to register.
Plans & pricing
Pure pay-as-you-go. No monthly fee.
No rigid subscriptions. Top up when you need, credit never expires, and one key routes every major model.
No sunk cost · Top up anytime · Credit never expires · Billed only for usage
No monthly feeTry & validate
Developer Starter
For individual devs, scripts, and trying new models
$20/ from $50
Pay as you go — full balance becomes token credit
What's included
Credit never expires or resets
Every model: Claude, GPT, DeepSeek & more
Any OpenAI-compatible client or lightweight agent
Precise per-request billing details
Most popularTop up & go
Most popularHigh-throughput
Team Pay-as-you-go
For production and ongoing builds
$100/ from $500
Self-serve top-up, priority routing
What's included
Full feature set, credit never expires
Multi-key quotas and group permissions
High concurrency with automatic failover
WeChat / Alipay / card billing + invoices
EnterpriseCustom & dedicated
Enterprise Plan
A compliant, elastic model hub for enterprise teams
Custom
Framework agreements & postpaid credit lines
What's included
Dedicated clusters with high QPS limits
Invoice settlement and VAT receipts
SLA and 7×24 dedicated support
Audit log export and usage dashboards
Real-Time Rates
Real-Time Rates for All Models
Prices are quoted in U.S. dollars per million tokens (USD per 1M tokens), consistent with the gateway’s actual billing methodology. OpenAI-compatible protocols are supported, and model names follow the namespace/model format.
Currently displaying 49 models
| Model Name and ID | Context Window | Enter price / 1M | Output Price / 1M | Cache Hits / 1M |
|---|---|---|---|---|
Claude Fable 5 anthropic/claude-fable-5 | 1M | $3.25 / 1M | $16.25 / 1M | $0.325 / 1M |
Claude Fable 5.1 anthropic/claude-fable-5-1 | 1M | $3.25 / 1M | $16.25 / 1M | $0.08125 / 1M |
Claude Haiku 4.5 anthropic/claude-haiku-4-5-20251001 | 200K | $0.325 / 1M | $1.625 / 1M | $0.0325 / 1M |
Claude Haiku 5.5 anthropic/claude-haiku-5-5 | 1M | $0.0325 / 1M | $0.1625 / 1M | $0.00325 / 1M |
Claude Opus 4.5 anthropic/claude-opus-4-5-20251101 | 200K | $1.625 / 1M | $8.125 / 1M | $0.1625 / 1M |
Claude Opus 4.6 anthropic/claude-opus-4-6 | 1M | $1.625 / 1M | $8.125 / 1M | $0.1625 / 1M |
Claude Opus 4.7 anthropic/claude-opus-4-7 | 1M | $1.625 / 1M | $8.125 / 1M | $0.1625 / 1M |
Claude Opus 4.8 anthropic/claude-opus-4-8 | 1M | $1.625 / 1M | $8.125 / 1M | $0.1625 / 1M |
Claude Opus 5 anthropic/claude-opus-5 | 1M | $1.625 / 1M | $8.125 / 1M | $0.1625 / 1M |
Claude Opus 5.5 anthropic/claude-opus-5-5 | 1M | $1.3 / 1M | $6.5 / 1M | $0.065 / 1M |
Claude Sonnet 4.5 anthropic/claude-sonnet-4-5-20250929 | 200K | $0.975 / 1M | $4.875 / 1M | $0.0975 / 1M |
Claude Sonnet 4.6 anthropic/claude-sonnet-4-6 | 1M | $0.975 / 1M | $4.875 / 1M | $0.0975 / 1M |
Claude Sonnet 5 anthropic/claude-sonnet-5 | 1M | $0.65 / 1M | $3.25 / 1M | $0.065 / 1M |
Claude Sonnet 5.5 anthropic/claude-sonnet-5-5 | 1M | $0.65 / 1M | $3.25 / 1M | $0.0325 / 1M |
Gemini 2.5 Flash google/gemini-2.5-flash | 1.0M | $0.135 / 1M | $1.125 / 1M | $0.0135 / 1M |
Gemini 2.5 Flash Lite google/gemini-2.5-flash-lite | 1.0M | $0.045 / 1M | $0.18 / 1M | $0.0045 / 1M |
Gemini 2.5 Pro google/gemini-2.5-pro | 1.0M | $0.5625 / 1M | $4.5 / 1M | $0.05625 / 1M |
Gemini 3 Flash Preview google/gemini-3-flash-preview | 1.0M | $0.225 / 1M | $1.35 / 1M | $0.0225 / 1M |
Gemini 3.1 Flash Lite google/gemini-3.1-flash-lite | 1.0M | $0.1125 / 1M | $0.675 / 1M | $0.01125 / 1M |
Gemini 3.1 Flash Lite Preview google/gemini-3.1-flash-lite-preview | 1.0M | $0.1125 / 1M | $0.675 / 1M | $0.01125 / 1M |
Gemini 3.1 Pro Preview google/gemini-3.1-pro-preview | 1.0M | $0.9 / 1M | $5.4 / 1M | $0.09 / 1M |
Gemini 3.5 Flash google/gemini-3.5-flash | 1.0M | $0.675 / 1M | $4.05 / 1M | $0.0675 / 1M |
Gemini 3.5 Flash Lite google/gemini-3.5-flash-lite | 1.0M | $0.135 / 1M | $1.125 / 1M | $0.0135 / 1M |
Gemini 3.6 Flash google/gemini-3.6-flash | 1.0M | $0.3375 / 1M | $1.6875 / 1M | $0.03375 / 1M |
Gemini 3.7 Flash google/gemini-3.7-flash | 1.0M | $0.3375 / 1M | $1.6875 / 1M | $0.03375 / 1M |
Gemini 3.8 Flash google/gemini-3.8-flash | 1.0M | $0.37125 / 1M | $1.85625 / 1M | $0.037125 / 1M |
Gemini 4 Argon google/gemini-4-argon | 1.0M | $0.9 / 1M | $4.5 / 1M | $0.045 / 1M |
Kimi K2.5 moonshot/kimi-k2.5 | 262K | $0.325 / 1M | $1.625 / 1M | $0.0975 / 1M |
Kimi K2.6 moonshot/kimi-k2.6 | 262K | $0.4225 / 1M | $2.2165 / 1M | $0.0975 / 1M |
Kimi K2.7 Code moonshot/kimi-k2.7-code | 262K | $0.43628 / 1M | $2.1775 / 1M | $0.0975 / 1M |
Kimi K3 moonshot/kimi-k3 | 1.0M | $0.15535 / 1M | $7.7584 / 1M | $0.1365 / 1M |
GPT-5.5 openai/gpt-5.5 | 1.1M | $0.3 / 1M | $1.8 / 1M | $0.03 / 1M |
GPT-5.6 Luna openai/gpt-5.6-luna | 1.1M | $0.012 / 1M | $0.072 / 1M | $0.0012 / 1M |
GPT-5.6 Sol openai/gpt-5.6-sol | 1.1M | $0.24 / 1M | $1.2 / 1M | $0.024 / 1M |
GPT-5.6 Terra openai/gpt-5.6-terra | 1.1M | $0.12 / 1M | $0.72 / 1M | $0.012 / 1M |
GPT-6 Astra openai/gpt-6-astra | 1.1M | $0.6 / 1M | $3.00 / 1M | $0.06 / 1M |
GPT-6 Sol openai/gpt-6-sol | 1.1M | $0.12 / 1M | $0.6 / 1M | $0.012 / 1M |
GPT-6.1 Sol openai/gpt-6.1-sol | 1.1M | $0.12 / 1M | $0.6 / 1M | $0.006 / 1M |
GLM-4.5-Air zhipu/glm-4.5-air | 131K | $0.0715 / 1M | $0.4675 / 1M | $0.01375 / 1M |
GLM-4.6 zhipu/glm-4.6 | 205K | $0.3025 / 1M | $1.21 / 1M | $0.0605 / 1M |
GLM-4.6V zhipu/glm-4.6v | 128K | $0.165 / 1M | $0.495 / 1M | $0.03025 / 1M |
GLM-4.7 zhipu/glm-4.7 | 205K | $0.297 / 1M | $1.089 / 1M | $0.05445 / 1M |
GLM-5 zhipu/glm-5 | 203K | $0.55 / 1M | $1.76 / 1M | $0.11 / 1M |
GLM-5-Turbo zhipu/glm-5-turbo | 203K | $0.66 / 1M | $2.2 / 1M | $0.132 / 1M |
GLM-5.1 zhipu/glm-5.1 | 203K | $0.77 / 1M | $2.42 / 1M | $0.143 / 1M |
GLM-5.2 zhipu/glm-5.2 | 262K | $0.018755 / 1M | $3.85 / 1M | $0.01815 / 1M |
GLM-5.3 zhipu/glm-5.3 | 328K | $0.04345 / 1M | $0.77 / 1M | $0.0429 / 1M |
GLM-5.3-Flash zhipu/glm-5.3-flash | 1M | $0.0825 / 1M | $0.275 / 1M | $0.0165 / 1M |
GLM-5.3-FlashX zhipu/glm-5.3-flashx | 1M | $0.2035 / 1M | $0.6875 / 1M | $0.0495 / 1M |
The above are the standard unit prices for public channels; billing is based on actual token usage. View the complete model catalog
Billing Highlights
You can see exactly where your money goes at a glance on your bill
There are only four billing rules—no hidden fees and no tiered pricing traps designed to make the service “seem cheaper.”
The credit limit is valid indefinitely.
The prepaid balance does not reset monthly; it is deducted as you use it, making it ideal for small-scale projects with irregular usage.
No charge for failed attempts
Requests that do not generate an output—such as those with parameter errors, authentication failures, or rate-limiting—are not charged.
Price Snapshot Remains Unchanged
Each usage charge is calculated based on the price snapshot at the time of use, and historical bills will always reflect the price in effect at that time.
Billing FAQ
Billing FAQs
All your questions about billing criteria, validity periods, and deductions are answered here. The answers are written directly in the HTML, so you can read them even without running JavaScript.
How does Admesh.ai charge for its services?
Pure Pay-as-You-Go: Billed based on the actual number of tokens used per request, with no monthly fees, no mandatory subscriptions, and no minimum spending requirement. Pricing is in U.S. dollars per million tokens, and invoices are itemized by individual request.
Do top-up credits expire?
No. The balance you top up remains valid indefinitely; it is not reset monthly, nor does it expire due to prolonged inactivity.
How are input, output, and cache tokens calculated, respectively?
Input tokens are billed at the input unit price, and output tokens are billed at the output unit price; input tokens that hit the prompt cache are billed at the lower cache-hit unit price. These three items are listed separately in the billing details for the same request.
What payment methods are accepted? Can you issue an invoice?
We accept WeChat Pay, Alipay, UnionPay credit cards, and corporate bank transfers. After making a purchase, you can request an invoice yourself on the Finance page of the control panel.
Will the price change?
We may adjust our prices in tandem with changes made by upstream vendors, and will announce such changes in advance via the console and in the release notes. Usage that has already occurred will be billed based on the price snapshot at that time, and historical invoices will not be altered due to price changes.
Will I be charged if the call fails?
No. Requests that do not generate upstream output—such as those resulting in parameter errors (400), authentication failures (401), insufficient balance (402), or rate limiting (429)—are not billed; however, the portion of the output already generated in the streaming response will be billed accordingly.
Still not sure which option to choose?
For low-traffic projects, start directly with the trial plan; the top-up amount is valid indefinitely. For team and compliance requirements, proceed through corporate partnerships; corporate contracts, invoices, and dedicated channels will be discussed together.