Model status & pricing API

Two unauthenticated JSON endpoints: /api/provider/status reports the live availability of every model in every group, /api/provider/pricing returns the public price list that matches the model square. Use them for status dashboards, automatic model fallback, cost estimation or third-party listings.

Where to call

Both endpoints are served on the console host and on every API endpoint, e.g. https://cn.chatapi.app/api/provider/status or https://www.xycai.us/api/provider/status. No Authorization header is needed; cache results for at least a minute instead of polling tightly.

1. Model status `GET /api/provider/status`

GEThttps://cn.chatapi.app/api/provider/status

Enumeration matches the pricing list: one record per model × pricing group (the same model in Enterprise and Economy is two records). Models covered by probes report probe-derived states; models without probes are reported as operational with probed: false.

Request

curl https://cn.chatapi.app/api/provider/status

Python:

import requests

data = requests.get("https://cn.chatapi.app/api/provider/status", timeout=10).json()["data"]
print(data["summary"])
bad = [m for m in data["models"] if m["current_status"] != "operational"]
for m in bad:
    print(m["group_name"], m["model_name"], m["current_status"], m.get("current_rate"))

Response

{
  "schema_version": "1.0",
  "success": true,
  "message": "",
  "data": {
    "site_name": "XycAi",
    "generated_at": "2026-10-21T23:36:47Z",
    "window_hours": 24,
    "summary": {
      "total": 285,
      "probed": 31,
      "status":         { "operational": 263, "degraded": 22, "outage": 0 },
      "current_status": { "operational": 284, "degraded": 0,  "outage": 1 }
    },
    "models": [
      {
        "model_name": "claude-opus-5-5",
        "group_name": "Claude 企业版",
        "status": "operational",
        "current_status": "operational",
        "probed": true,
        "rate_24h": 100,
        "current_rate": 100,
        "last_check": 1792625400,
        "note": "status: 24h probe success rate ... current_status: latest 30-minute probe bucket ..."
      },
      {
        "model_name": "claude-2",
        "group_name": "Claude 工作流",
        "status": "operational",
        "current_status": "operational",
        "probed": false,
        "note": "No probe coverage for this model; reported as operational."
      }
    ]
  }
}

Fields

Field	Type	Meaning
`data.window_hours`	int	Statistics window, fixed at 24 hours
`data.summary.total` / `probed`	int	Number of records / how many have probe coverage
`data.summary.status` / `current_status`	object	Counts per state under each of the two definitions
`model_name` / `group_name`	string	Model name (the request `model`) and the display name of its pricing group
`status`	enum	24-hour view: probe success rate over the last 24h — ≥99% `operational`, ≥50% `degraded`, <50% `outage`
`current_status`	enum	Live view: the latest 30-minute probe bucket with data — ≥99% `operational`, >0% `degraded`, 0% `outage`. Same colouring as the model square
`probed`	bool	Probe coverage. When `false` both states are fixed to `operational` and the `rate_*` / `last_check` fields are absent
`rate_24h` / `current_rate`	number	24h success rate / latest-bucket success rate, in percent (0–100)
`last_check`	int	Start of the latest probe bucket, Unix seconds

Which view to use

For automatic fallback (switch model / group on failure) use current_status; for stability assessment use status and rate_24h. If the probe store cannot be read the endpoint returns HTTP 500 with success: false rather than pretending everything is green — treat that as "unknown", not "all down".

2. Public price list `GET /api/provider/pricing`

GEThttps://cn.chatapi.app/api/provider/pricing

Returns the current final public prices (group discounts already applied) in CNY, identical to the model square. Enumeration is again model × visible group.

curl https://cn.chatapi.app/api/provider/pricing

{
  "schema_version": "1.1",
  "success": true,
  "data": {
    "currency": "CNY",
    "price_unit": "per_1m_tokens",
    "updated_at": "2026-10-21T23:36:56Z",
    "models": [
      {
        "model_name": "claude-fable-5",
        "group_name": "Claude 企业版",
        "input_price": 26.91,
        "output_price": 134.55,
        "cache_input_price": 2.691,
        "cache_create_price": 26.91,
        "enabled": true,
        "note": "Final public price in CNY per 1M tokens, matching the model square."
      },
      {
        "model_name": "gpt-image-2.5-flare",
        "group_name": "GPT 企业版",
        "price_unit": "per_call",
        "unit_price": 0.1,
        "enabled": true,
        "note": "按张计价：1K / 2K / 4K 全档同价 ￥0.1 每张。"
      }
    ]
  }
}

Field	Meaning
`data.currency` / `price_unit`	Global units: `CNY`, per 1M tokens for token-billed models
`input_price` / `output_price`	Input / output price (¥ per 1M tokens)
`cache_input_price` / `cache_create_price` / `cache_create_price_1h`	Cache read / cache write (5 min) / cache write (1 h) prices; only present for models with prompt caching
`price_unit: "per_call"` + `unit_price`	Per-call models (images per picture, video per second); `note` explains the unit and tiers
`enabled`	Whether the model can currently be ordered

Account tiers (T1 / T2 / V1 …) and time-of-day discounts are not reflected here; the model square shows your account's actual prices once logged in.

3. Joining both lists

(model_name, group_name) is the shared key, so a "price + availability" view is one join away:

import requests

BASE = "https://cn.chatapi.app"
price = {(m["model_name"], m["group_name"]): m for m in requests.get(BASE + "/api/provider/pricing").json()["data"]["models"]}
for s in requests.get(BASE + "/api/provider/status").json()["data"]["models"]:
    p = price.get((s["model_name"], s["group_name"]), {})
    print(s["model_name"], s["group_name"], s["current_status"], p.get("input_price"), p.get("output_price"))

To list the models your key can reach, use the authenticated GET /v1/models instead (see Models).