/v1/chat/completions and /v1/agents/run.
GET https://api.profy.cn/v1/models
Authentication
Bearer sk-pro-xxxx (API Key)Request Examples
from profy import Profy
async with Profy(api_key="sk-pro-your-key") as client:
models = await client.models.list()
for m in models:
print(f"{m['id']}: {m['name']}")
caps = m.get("capabilities", {})
if caps.get("supportsVision"):
print(" Supports vision")
if caps.get("supportsTools"):
print(" Supports tool calling")
import { Profy } from "@profy-ai/sdk";
const client = new Profy({ apiKey: "sk-pro-your-key" });
const models = await client.models.list();
for (const m of models) {
console.log(`${m.id}: ${m.name}`);
if (m.capabilities?.supportsVision) console.log(" Supports vision");
if (m.capabilities?.supportsTools) console.log(" Supports tool calling");
}
curl https://api.profy.cn/v1/models \
-H "Authorization: Bearer sk-pro-your-key"
Response
{
"models": [
{
"id": "deepseek-v3",
"type": "model",
"name": "DeepSeek V3",
"capabilities": {
"omitTemperature": false,
"fixedTemperature": null,
"requiresReasoning": false,
"maxInputTokens": 65536,
"maxOutputTokens": 8192,
"supportsTools": true,
"supportsVision": false
}
},
{
"id": "claude-sonnet-4-20250514",
"type": "model",
"name": "Claude Sonnet 4",
"capabilities": {
"omitTemperature": false,
"fixedTemperature": null,
"requiresReasoning": false,
"maxInputTokens": 200000,
"maxOutputTokens": 16384,
"supportsTools": true,
"supportsVision": true
}
},
{
"id": "profy-financial-advisor",
"type": "expert",
"name": "Financial Advisor",
"description": "Professional financial analysis and planning expert",
"created": 1752825600,
"owned_by": "creator-xxx"
}
]
}
Model Object
| Field | Type | Description |
|---|---|---|
id | string | Model identifier, use this value in API calls |
type | string | "model" (raw LLM) or "expert" (Profy Expert, use via profy-<identifier> in /v1/chat/completions) |
name | string | Model display name |
capabilities | object | Model capability description, only returned for type: "model" (see table below) |
description | string | Expert description, only returned for type: "expert" |
created | number | Creation timestamp (seconds), only returned for type: "expert" |
owned_by | string | Creator identifier, only returned for type: "expert" |
Capabilities Fields
| Field | Type | Description |
|---|---|---|
omitTemperature | boolean | Whether the temperature parameter should be omitted |
fixedTemperature | number | null | Fixed temperature value. null means freely configurable |
requiresReasoning | boolean | Whether this is a reasoning model (produces thinking output) |
maxInputTokens | number | null | Maximum input token count |
maxOutputTokens | number | null | Maximum output token count |
supportsTools | boolean | Whether Function Calling is supported |
supportsVision | boolean | Whether image understanding is supported |
Use Cases
Filter Models by Capability
async with Profy(api_key="sk-pro-your-key") as client:
models = await client.models.list()
tool_models = [m for m in models if m["capabilities"]["supportsTools"]]
vision_models = [m for m in models if m["capabilities"]["supportsVision"]]
best_context = max(
models,
key=lambda m: m["capabilities"].get("maxInputTokens") or 0,
)
Filter Expert Models
async with Profy(api_key="sk-pro-your-key") as client:
models = await client.models.list()
expert_models = [m for m in models if m.get("type") == "expert"]
for e in expert_models:
print(f"{e['id']}: {e['name']} — {e.get('description', '')}")
Handle Temperature Differences
Different models have different temperature parameter support. Checking capabilities before calling avoids request rejections:caps = model_map[target]["capabilities"]
params = {"model": target, "messages": messages}
if not caps["omitTemperature"]:
if caps["fixedTemperature"] is not None:
params["temperature"] = caps["fixedTemperature"]
else:
params["temperature"] = 0.7
resp = await client.chat.completions.create(**params)
The list of available models on the platform is updated periodically. We recommend your application call this endpoint at startup or on a regular schedule to get the latest list.
Error Codes
| HTTP Status Code | Description |
|---|---|
401 | Authentication failed |
Next Steps
Chat Completions
Use models for chat completions
Run an Expert
Invoke an Expert Agent