Models

🚀 News

Intern-S2 Official Release: Intern-S2-Preview-397B has been officially upgraded to Intern-S2, retaining the 397B parameter scale. Building on Intern-S2-Preview-397B’s dual leadership in scientific and general scenarios, it further extends long-horizon task processing capabilities, delivering a new option for long-range research workloads.

Set the model field in ChatAPI to intern-s2 to invoke this model. Deep-thinking mode is enabled by default (the model generates responses after a long chain-of-thought reasoning process).
Use thinking_mode (boolean) to toggle deep-thinking mode (applies only to intern-s2/intern-s2-preview-35b/intern-s2-preview/intern-s1-pro/intern-s1/intern-s1-mini).
For Intern-S2 agent capabilities (e.g., integration with harnesses such as openclaw, or workloads heavily dependent on tool calls), it is recommended to keep thinking_mode enabled by default. Agent scenarios are not recommended when running without thinking mode.

Intern-S2-Preview-397B will be decommissioned on October 31, 2026. Please migrate your model calls to Intern-S2 promptly for optimal performance.

Model Milestones

Intern-S2: A 397B-parameter scientific multimodal reasoning model. It continues the Intern-S2-Preview family’s exploration of scientific discovery and general agent capabilities, further extending long-horizon task processing and delivering a new option for long-range research workloads.
Intern-S1-Pro: An advanced open-source multimodal reasoning model with strong overall performance and built-in web search.
Intern-S1: An open-source multimodal reasoning model with strong general capabilities and state-of-the-art performance across a wide range of scientific tasks.

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-s2.
internvl3.5-latestautomatically refers to our most recent internvl series release, which currently points to internvl3.5-241b-a28b

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., intern-s2).

Compatibility note: intern-s2-preview is now marked as Legacy. This model ID remains temporarily available and points to intern-s2-preview-35b; new integrations should use an explicit version ID.

Model List

Multimodal Models

Model	Description	Context Length
intern-latest	Alias for our most recently released Intern-series model, currently pointing to `intern-s2-preview-397b`	256K
internvl3.5-latest	Alias for the latest InternVL3.5 series model, currently pointing to `internvl3.5-241b-a28b`	32K
intern-s2	A 397B-parameter model with a 256K context window for scientific multimodal reasoning, general agent capabilities, and complex long-horizon tasks	256K
intern-s2-preview-397b	The model will be decommissioned on October 31, 2026. Please migrate your model calls to Intern-S2 promptly for optimal performance	256K
intern-s2-preview-35b	A 35B-A3B model with a 256K context window, focused on scientific discovery and general agent capabilities	256K
intern-s2-preview	Legacy compatibility model ID that remains temporarily available and points to `intern-s2-preview-35b`	256K
intern-s1-pro	Open-source multimodal scientific reasoning model with strong overall performance	256K
intern-s1	Multimodal model with strong scientific reasoning capabilities	32K
intern-s1-mini	Lightweight multimodal model with strong scientific reasoning	32K
internvl3.5-241b-a28b	Our newest multimodal model featuring enhanced image-text comprehension and long-sequence image understanding capabilities, with performance comparable to top closed-source models	32K

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

Parameter	Type	Example	Description
object	string	list	Data type returned, in this case, "list"
data	object	{ "id": "intern-latest", "object": "model", "created": 1686935002, "owned_by": "pjlab"}	Model information

Relevant Structure Explanation

Data Structure Explanation

Parameter	Type	Example	Description
id	string	intern-latest	Model ID
object	string	model	Model category, always "model"
created	int	1677652288	Model creation timestamp
owned_by	string	SH-AILab	Model 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-s1-mini",
            "object": "model",
            "ref_model": "intern-s1-mini",
            "created": 1755677776,
            "owned_by": "SH-AILab"
        },
        {
            "id": "internvl3.5-241b-a28b",
            "object": "model",
            "ref_model": "internvl3.5-241b-a28b",
            "created": 1756368976,
            "owned_by": "SH-AILab"
        },
        {
            "id": "internvl3.5-latest",
            "object": "model",
            "ref_model": "internvl3.5-241b-a28b",
            "created": 1756368976,
            "owned_by": "SH-AILab"
        },
        {
            "id": "internvl-latest",
            "object": "model",
            "ref_model": "internvl3.5-241b-a28b",
            "created": 1756368976,
            "owned_by": "SH-AILab"
        },
        {
            "id": "intern-latest",
            "object": "model",
            "ref_model": "intern-s2",
            "created": 1784131200,
            "owned_by": "SH-AILab"
        },
        {
	        "id": "intern-s2",
	        "object": "model",
	        "ref_model": "intern-s2",
	        "created": 1788934120,
	        "owned_by": "SH-AILab"
	    },
        {
            "id": "intern-s2-preview-397b",
            "object": "model",
            "ref_model": "intern-s2-preview-397b",
            "created": 1784131200,
            "owned_by": "SH-AILab"
        },
        {
            "id": "intern-s2-preview-35b",
            "object": "model",
            "ref_model": "intern-s2-preview-35b",
            "created": 1778284800,
            "owned_by": "SH-AILab"
        },
        {
            "id": "intern-s2-preview",
            "object": "model",
            "ref_model": "intern-s2-preview-35b",
            "created": 1778284800,
            "owned_by": "SH-AILab"
        },
        {
            "id": "intern-s1",
            "object": "model",
            "ref_model": "Intern-S1",
            "created": 1753517776,
            "owned_by": "SH-AILab"
        },
        {
            "id": "intern-s1-pro",
            "object": "model",
            "ref_model": "intern-s1-pro",
            "created": 1753517776,
            "owned_by": "SH-AILab"
        }
    ]
}

Models

🚀 News​

Model Milestones​

Using the Latest Model​

Model List​

Multimodal Models​

Request Examples​

(1) Python Example​

(2) OpenAI SDK Example​

(3) OpenAI CLI Example​

Parameter Explanation​

Return Parameters​

Relevant Structure Explanation​