Speech billing estimate

File: config/system/system-speech-pricing.json. Side: client. A missing file is read after being copied from the file of the same name under the JAR's defaults.

Field	Type	Required	Default	Description
version	Integer	no	1	Pricing table format version.
currency	String	no	"CNY"	Currently CNY only.
asOf	String	no	"2026-10-25"	Reference date of the price list; does not mean live official prices.
rates	Array	no	See the bundled price list	List of price entries, see the table below.

rates entries

Field	Type	Required	Default	Description
provider	String	required for a valid entry	empty	Provider ID.
model	String	required for a valid entry	empty	Model name.
region	String	required for a valid entry	empty	Region.
unit	String	required for a valid entry	omitted	characters, tokens or calls; case-insensitive.
units	Positive integer	required for a valid entry	no valid default	Number of units the price applies to.
input	Non-negative decimal number or string	required for a valid entry	omitted	Price of the input characters / tokens / calls.
output	Non-negative decimal number or string	required for a valid entry	omitted	Price of output tokens; must be 0 for units other than tokens.

Entries are matched by provider, model and region; when the price is missing or the billing unit does not match, only usage is recorded and the amount stays unpriced; duplicate entries keep the first one. A missing price is never treated as free. Prices are local estimates, not the provider's bill, and asOf in the bundled table only indicates the reference date. A completed NLS recognition is estimated as calls.

Bundled default file

config/system/system-speech-pricing.json

{
  "version": 1,
  "currency": "CNY",
  "asOf": "2026-10-25",
  "rates": [
    {
      "provider": "aliyun",
      "model": "qwen3-tts-flash",
      "region": "beijing",
      "unit": "CHARACTERS",
      "units": 10000,
      "input": 0.8,
      "output": 0
    },
    {
      "provider": "aliyun",
      "model": "qwen3-tts-flash",
      "region": "singapore",
      "unit": "CHARACTERS",
      "units": 10000,
      "input": 0.733924,
      "output": 0
    },
    {
      "provider": "aliyun",
      "model": "qwen-audio-3.1-tts-flash",
      "region": "beijing",
      "unit": "TOKENS",
      "units": 1000000,
      "input": 1.5,
      "output": 12
    },
    {
      "provider": "aliyun",
      "model": "qwen-audio-3.1-tts-flash",
      "region": "singapore",
      "unit": "TOKENS",
      "units": 1000000,
      "input": 1.677,
      "output": 13.636
    },
    {
      "provider": "aliyun",
      "model": "qwen-audio-3.1-tts-plus",
      "region": "beijing",
      "unit": "CHARACTERS",
      "units": 10000,
      "input": 1.4,
      "output": 0
    },
    {
      "provider": "aliyun",
      "model": "qwen-audio-3.1-tts-plus",
      "region": "singapore",
      "unit": "CHARACTERS",
      "units": 10000,
      "input": 2.19,
      "output": 0
    },
    {
      "provider": "aliyun",
      "model": "qwen-audio-3.0-tts-plus",
      "region": "beijing",
      "unit": "CHARACTERS",
      "units": 10000,
      "input": 1.4,
      "output": 0
    },
    {
      "provider": "aliyun",
      "model": "qwen-audio-3.0-tts-plus",
      "region": "singapore",
      "unit": "CHARACTERS",
      "units": 10000,
      "input": 1.49884,
      "output": 0
    },
    {
      "provider": "aliyun",
      "model": "qwen-audio-3.0-tts-flash",
      "region": "beijing",
      "unit": "CHARACTERS",
      "units": 10000,
      "input": 1,
      "output": 0
    },
    {
      "provider": "aliyun",
      "model": "qwen-audio-3.0-tts-flash",
      "region": "singapore",
      "unit": "CHARACTERS",
      "units": 10000,
      "input": 1.12413,
      "output": 0
    },
    {
      "provider": "aliyun-nls",
      "model": "sentence-recognition",
      "region": "shanghai",
      "unit": "CALLS",
      "units": 1000,
      "input": 3.5,
      "output": 0
    },
    {
      "provider": "aliyun-nls",
      "model": "sentence-recognition",
      "region": "beijing",
      "unit": "CALLS",
      "units": 1000,
      "input": 3.5,
      "output": 0
    },
    {
      "provider": "aliyun-nls",
      "model": "sentence-recognition",
      "region": "shenzhen",
      "unit": "CALLS",
      "units": 1000,
      "input": 3.5,
      "output": 0
    }
  ]
}