Open model route
A good fit for teams comparing hosted gateways with self-hosted Chinese models.
Evaluate InternLM open Chinese model routes for self-hosted chat, long-context QA and research-friendly application testing.
5 min
to first call
USD
token pricing
200K
context window
SSE
streaming
InternLM open route
OpenAI-compatible model gateway
Client
Your App
SDK, backend, agent or workflow.
SmarToken
Unified API Gateway
internlm3
Provider
InternLM3
Shanghai AI Laboratory 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
Shanghai AI Laboratory
Call internlm3, stream the response and record usage.
Response Preview
200 OK{
"model": "internlm3",
"choices": [{
"message": {
"role": "assistant",
"content": "InternLM is useful for open-source evaluation, self-hosted deployments and long-context Chinese model experiments."
}
}],
"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
A focused page for evaluating this model as an API route, not just reading a catalog row.
A good fit for teams comparing hosted gateways with self-hosted Chinese models.
Useful for prompt experiments, model comparisons and reproducible internal evals.
Candidate for retrieval and document QA when the deployment supports large context.
Why SmarToken
Direct accounts can work once region, billing, model IDs and credentials are settled. SmarToken is built for faster overseas evaluation and safer early production.
One console key reaches mainstream Chinese model routes including DeepSeek, Kimi, Qwen, Hunyuan, MiniMax and Spark.
Model IDs, SDK samples and error semantics are written for overseas teams.
Daily, monthly and model-family limits keep experiments predictable.
Usage logs connect model, API key, token estimate, latency and wallet debit.
Code sample
curl
curl -s "https://thesmartoken.com/v1/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_SMARTOKEN_KEY" \
-d '{
"model": "internlm3",
"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="internlm3",
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: "internlm3",
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
Position Chinese model families by context, pricing and workload fit before you lock in a default route.
| Model | Context | Input / 1M | Output / 1M | Reasoning | Coding | Best for |
|---|---|---|---|---|---|---|
| DeepSeek | 128K | $0.50 | $1.50 | 5/5 | 5/5 | Reasoning, coding, research |
| Kimi | 256K | $0.60 | $2.50 | 4/5 | 4/5 | Long context, agents, research |
| Qwen | 128K | $1.20 | $4.80 | 4/5 | 4/5 | Multilingual apps, structured output |
| GLM | 128K | $0.80 | $3.20 | 4/5 | 4/5 | Enterprise tools, business workflows |
| Doubao | 128K | $0.70 | $2.80 | 3/5 | 3/5 | Consumer chat, content workflows |
| ERNIE | 128K | $0.90 | $3.60 | 4/5 | 3/5 | Chinese knowledge, enterprise search |
| Hunyuan | 128K | $0.80 | $3.20 | 4/5 | 4/5 | Enterprise assistants, Tencent Cloud routes |
| MiniMax | 128K | $0.30 | $1.20 | 4/5 | 5/5 | Coding agents, developer automation |
| StepFun | 128K | $0.50 | $2.00 | 4/5 | 4/5 | Coding tools, planning agents |
| Baichuan | 32K | $1.50 | $1.50 | 4/5 | 3/5 | Domain QA, bilingual writing |
| Spark | 64K | $0.70 | $2.80 | 4/5 | 4/5 | Chinese reasoning, education |
| SenseNova | 128K | $0.80 | $3.20 | 4/5 | 3/5 | Multimodal enterprise workflows |
| Pangu | 32K | $1.00 | $4.00 | 4/5 | 3/5 | Industry NLP, private routes |
| 360 Zhinao | 32K | $0.40 | $1.00 | 4/5 | 3/5 | Security assistants, Chinese QA |
| Yi | 32K | $0.90 | $0.90 | 4/5 | 4/5 | Bilingual writing, structured output |
| InternLM | 200K | $0.20 | $0.80 | 4/5 | 4/5 | Self-hosted evals, research |
| LongCat | 128K | $0.40 | $1.60 | 4/5 | 4/5 | Open model evals, multimodal prototypes |
Yes when an InternLM-compatible deployment or aggregator route is configured, then clients call model: internlm3.
Choose InternLM when open model evaluation, self-hosted deployment or research control is more important than managed vendor convenience.
Use cases
Start with a clear workload, then compare routes in Playground before moving traffic into production.
Connect a private InternLM-compatible deployment behind SmarToken.
Compare open Chinese models with provider-hosted alternatives.
Test retrieval and document analysis workflows.
Use low-cost routes for prompt and workflow iteration.
Migration
The integration path stays familiar: same Chat Completions shape, one new baseURL and a China-first model ID.
Switch path
Keep the SDK. Change baseURL to SmarToken and switch the model ID.
Switch path
Move from broad routing into a focused Chinese-model console with budgets.
Switch path
Keep Chat Completions while adding China-first model pages and route control.
FAQ
Use the standard OpenAI SDK, set baseURL to https://thesmartoken.com/v1, authenticate with your SmarToken key, and pass model: internlm3.
InternLM is a good candidate for self-hosted Chinese model evaluation, long-context QA and research workflows. Test it in the Playground before routing production traffic.
Use the comparison table as a starting point, then run your own prompts because coding, reasoning, latency and cost can vary by upstream route.
Yes. Use your SmarToken key, set baseURL to https://thesmartoken.com/v1, and pass the model ID shown on this page.
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.
Create an account, open the console, generate an API key, then copy the cURL, Python or TypeScript example from the Playground.
Yes. Console API keys can be limited by allowed model family plus daily and monthly USD budgets.
Start now
One smart key for DeepSeek, Kimi, Qwen, GLM, Doubao, ERNIE and other configured routes.