Skip to main content

Models

Model Milestones

  • Intern-S1: Our latest open-source multimodal large model enhanced with advanced scientific reasoning capabilities. It currently delivers the best overall performance among all open-source multimodal models.
  • InternLM3: Our latest series of large language models with exceptional reasoning capabilities, leading the open-source models in this class.
  • InternVL2.5: Our multimodal large model series, the first open-source model to match the performance of top proprietary models like GPT-4 and Gemini Pro.

Using the Latest Model

For multi-turn conversation APIs, use the following in the model field:

  • intern-latest automatically refers to our most recent model release, which currently points to intern-s1.
  • internlm3-latest will automatically point to the latest version in the large language model series.

You can check the specific model version they point to by checking the ref_model field in the response from the models API (e.g., internlm3-8b-instruct).

Model List

Multimodal Models

ModelDescriptionContext Length
intern-latestAlias for our most recently released Intern-series model, currently pointing to intern-s132K
intern-s1Our latest multimodal model with strong scientific reasoning, offering top-tier performance32K
internvl-latestPoints to our latest release in the InternVL series, currently internvl3-78b32K
internvl3-78bOur most recent multimodal model, featuring enhanced image-text understanding and long-horizon visual reasoning. Its performance rivals leading proprietary models32K

Large Language Models

ModelDescriptionWindow Length
internlm3-latestDefault points to the latest released InternLM3 model series, currently pointing to internlm3-8b-instruct32K
internlm3-8b-instructOur latest model with leading reasoning capabilities in its scale32K
internlm2.5-latestDefault points to the latest released InternLM2.5 model series, currently pointing to internlm2.5-20b-chat32K

Request Examples

(1) Python Example

import requests
import json

url = 'https://chat.intern-ai.org.cn/api/v1/models'
header = {
'Content-Type': 'application/json',
"Authorization": "Bearer eyJ0eXBlIjoiSl...Please provide the correct token!"
}
data = {}

res = requests.get(url, headers=header, data=json.dumps(data))
print(res.status_code)
print(res.json())
print(res.json()["data"])

(2) OpenAI SDK Example

from openai import OpenAI

client = OpenAI(
api_key="eyJ0eXBlIjoiSl...Please provide the correct token!", # Provide token here, without 'Bearer'
base_url="https://chat.intern-ai.org.cn/api/v1/",
)

models = client.models.list()
for model in models:
print(model)

(3) OpenAI CLI Example

openai -b "https://chat.intern-ai.org.cn/api/v1/" 
-k "eyJ0eXBlIjoiSl...Please provide the correct token!"
api models.list

Parameter Explanation

Return Parameters

ParameterTypeExampleDescription
objectstringlistData type returned, in this case, "list"
dataobject{ "id": "intern-latest", "object": "model", "created": 1686935002, "owned_by": "pjlab"}Model information

Relevant Structure Explanation

  • Data Structure Explanation
ParameterTypeExampleDescription
idstringintern-latestModel ID
objectstringmodelModel category, always "model"
createdint1677652288Model creation timestamp
owned_bystringSH-AILabModel owner, default is "SH-AILab"
// Request
Schema: HTTP
Path: /api/v1/models
Method: GET
Header:
sso-ak: xxxxxx
Authorization: $BearerToken

// Response
Status Code: 200
Body:
{
"object": "list",
"data": [
{
"id": "intern-latest",
"object": "model",
"ref_model": "intern-s1",
"created": 1722424576,
"owned_by": "SH-AILab"
},
{
"id": "internvl3-latest",
"object": "model",
"ref_model": "internvl3-78b",
"created": 1722424576,
"owned_by": "SH-AILab"
},
{
"id": "internlm3-latest",
"object": "model",
"ref_model": "internlm2.5-20b-0719",
"created": 1722424576,
"owned_by": "SH-AILab"
}
]
}