Models / Huawei Cloud
Pangu model badge for the Huawei Pangu NLP API model page
Huawei Pangu API

Huawei Pangu API Access

Connect Huawei Pangu-style enterprise NLP and industry model routes through SmarToken's unified China model console.

Huawei Pangu model family
Industry NLP workflows
Enterprise route control
Usage and budget logs

5 min

to first call

USD

token pricing

32K

context window

SSE

streaming

Pangu industry route

OpenAI-compatible model gateway

Enterprise route

Client

</>

Your App

SDK, backend, agent or workflow.

SmarToken

Unified API Gateway

pangu-nlp

AuthBudgetRoute
SSE stream

Provider

Pangu NLP

Huawei Cloud route via admin pool.

01

Your app

Send a standard Chat Completions request with your SmarToken key.

02

SmarToken gateway

Validate the key, model scope, daily budget and monthly budget.

03

Model route pool

Choose an enabled upstream route by priority, weight and fallback.

04

Huawei Cloud

Call pangu-nlp, stream the response and record usage.

Response Preview

200 OK
{
  "model": "pangu-nlp",
  "choices": [{
    "message": {
      "role": "assistant",
      "content": "Pangu is relevant for industry assistants, private-cloud workflows and enterprise NLP scenarios."
    }
  }],
  "usage": { "tracked": true, "currency": "USD" }
}

Fast Deployment

Generate a key and run the Playground in minutes.

Global Access

Use one endpoint for configured China-first routes.

Unified Billing

Track USD token usage and wallet debits together.

Easy Migration

Keep OpenAI SDK shape, change baseURL and model.

Developer Friendly

Copy-ready cURL, Python and TypeScript examples.

Model fit

Why use Pangu?

A focused page for evaluating this model as an API route, not just reading a catalog row.

Industry workflows

Useful for teams evaluating Huawei Cloud industry model capabilities.

Enterprise deployment

A candidate for private-cloud and compliance-sensitive environments.

Budgeted gateway

SmarToken adds usage logs and model-family controls around upstream access.

Why SmarToken

Why not direct vendor accounts?

Direct accounts can work once region, billing, model IDs and credentials are settled. SmarToken is built for faster overseas evaluation and safer early production.

Unified key

One console key reaches mainstream Chinese model routes including DeepSeek, Kimi, Qwen, Hunyuan, MiniMax and Spark.

English docs

Model IDs, SDK samples and error semantics are written for overseas teams.

Budget control

Daily, monthly and model-family limits keep experiments predictable.

Route visibility

Usage logs connect model, API key, token estimate, latency and wallet debit.

Code sample

Copy-ready API examples

Open in Playground

curl

curl -s "https://thesmartoken.com/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_SMARTOKEN_KEY" \
  -d '{
    "model": "pangu-nlp",
    "stream": true,
    "messages": [
      { "role": "user", "content": "Explain the best use case for this model." }
    ]
  }'

python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_SMARTOKEN_KEY",
    base_url="https://thesmartoken.com/v1",
)

stream = client.chat.completions.create(
    model="pangu-nlp",
    stream=True,
    messages=[{"role": "user", "content": "Explain the best use case for this model."}],
)

for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

typescript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.SMTOKEN_API_KEY,
  baseURL: "https://thesmartoken.com/v1",
});

const stream = await client.chat.completions.create({
  model: "pangu-nlp",
  stream: true,
  messages: [{ role: "user", content: "Explain the best use case for this model." }],
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

Comparison

How Pangu compares

Position Chinese model families by context, pricing and workload fit before you lock in a default route.

ModelContextInput / 1MOutput / 1MReasoningCodingBest for
DeepSeek128K$0.50$1.505/55/5Reasoning, coding, research
Kimi256K$0.60$2.504/54/5Long context, agents, research
Qwen128K$1.20$4.804/54/5Multilingual apps, structured output
GLM128K$0.80$3.204/54/5Enterprise tools, business workflows
Doubao128K$0.70$2.803/53/5Consumer chat, content workflows
ERNIE128K$0.90$3.604/53/5Chinese knowledge, enterprise search
Hunyuan128K$0.80$3.204/54/5Enterprise assistants, Tencent Cloud routes
MiniMax128K$0.30$1.204/55/5Coding agents, developer automation
StepFun128K$0.50$2.004/54/5Coding tools, planning agents
Baichuan32K$1.50$1.504/53/5Domain QA, bilingual writing
Spark64K$0.70$2.804/54/5Chinese reasoning, education
SenseNova128K$0.80$3.204/53/5Multimodal enterprise workflows
Pangu32K$1.00$4.004/53/5Industry NLP, private routes
360 Zhinao32K$0.40$1.004/53/5Security assistants, Chinese QA
Yi32K$0.90$0.904/54/5Bilingual writing, structured output
InternLM200K$0.20$0.804/54/5Self-hosted evals, research
LongCat128K$0.40$1.604/54/5Open model evals, multimodal prototypes

Can I call Huawei Pangu with an OpenAI-compatible API?

Yes when Pangu is connected through a compatible upstream adapter or gateway route, then called as model: pangu-nlp.

What is Pangu best used for?

Pangu is best evaluated for industry NLP, enterprise assistants and Huawei Cloud-aligned deployments.

Use cases

Popular use cases

Start with a clear workload, then compare routes in Playground before moving traffic into production.

Industry assistant

Build vertical assistants for enterprise workflows.

Private deployment

Evaluate provider routes that align with private or cloud-specific requirements.

Enterprise NLP

Summarize, classify and extract information from business documents.

Knowledge automation

Automate repeatable Chinese-language knowledge tasks.

Migration

From your current AI gateway

The integration path stays familiar: same Chat Completions shape, one new baseURL and a China-first model ID.

Switch path

From OpenAI

Keep the SDK. Change baseURL to SmarToken and switch the model ID.

Switch path

From OpenRouter

Move from broad routing into a focused Chinese-model console with budgets.

Switch path

From Together.ai

Keep Chat Completions while adding China-first model pages and route control.

FAQ

Questions developers ask

How do I call Huawei Pangu with the OpenAI SDK?

Use the standard OpenAI SDK, set baseURL to https://thesmartoken.com/v1, authenticate with your SmarToken key, and pass model: pangu-nlp.

What is Huawei Pangu best for?

Huawei Pangu is a good candidate for industry NLP, enterprise assistants and private-cloud workflows. Test it in the Playground before routing production traffic.

How does Huawei Pangu compare with ERNIE and GLM?

Use the comparison table as a starting point, then run your own prompts because coding, reasoning, latency and cost can vary by upstream route.

Is this API compatible with the OpenAI SDK?

Yes. Use your SmarToken key, set baseURL to https://thesmartoken.com/v1, and pass the model ID shown on this page.

How is billing calculated?

Input and output tokens are priced separately in USD per 1M tokens. Final usage is recorded after the provider returns a response or a stream finishes.

Where do I get an API key?

Create an account, open the console, generate an API key, then copy the cURL, Python or TypeScript example from the Playground.

Can I restrict one key to this model family?

Yes. Console API keys can be limited by allowed model family plus daily and monthly USD budgets.

Start now

Start building with Chinese AI models in minutes

One smart key for DeepSeek, Kimi, Qwen, GLM, Doubao, ERNIE and other configured routes.

Get API Key