Implementation:Langchain ai Langchain MistralAI Model Profiles
| Knowledge Sources | |
|---|---|
| Domains | LLM, MistralAI, Model Configuration |
| Last Updated | 2026-02-11 00:00 GMT |
Overview
MistralAI Model Profiles is an auto-generated data module that defines capability profiles (token limits, modality support, tool calling) for Mistral AI models.
Description
The _profiles.py file in the langchain-mistralai partner package contains a dictionary named _PROFILES that maps Mistral AI model identifiers to their capability metadata. Each profile entry includes maximum input/output token counts, supported input/output modalities (text, image, audio, video), reasoning output capability, and tool calling support. This data is auto-generated by the langchain-profiles CLI tool from the models.dev project and should not be manually edited. The profiles are consumed by ChatMistralAI to automatically set model profile metadata for token counting and capability detection.
Usage
This module is used internally by ChatMistralAI during initialization to populate the model's profile with appropriate token limits and capabilities. It is not typically imported directly by end users.
Code Reference
Source Location
- Repository: Langchain_ai_Langchain
- File:
libs/partners/mistralai/langchain_mistralai/data/_profiles.py - Lines: 1-383
Signature
_PROFILES: dict[str, dict[str, Any]] = {
"model-name": {
"max_input_tokens": int,
"max_output_tokens": int,
"text_inputs": bool,
"image_inputs": bool,
"audio_inputs": bool,
"video_inputs": bool,
"text_outputs": bool,
"image_outputs": bool,
"audio_outputs": bool,
"video_outputs": bool,
"reasoning_output": bool,
"tool_calling": bool,
},
...
}
Import
from langchain_mistralai.data._profiles import _PROFILES
I/O Contract
Inputs
| Name | Type | Required | Description |
|---|---|---|---|
| (none) | -- | -- | This is a static data module with no runtime inputs. |
Outputs
| Name | Type | Description |
|---|---|---|
| _PROFILES | dict[str, dict[str, Any]] | A dictionary mapping model name strings to profile dictionaries containing token limits and capability flags. |
Registered Models
The module includes profiles for the following Mistral AI models (among others):
| Model | Max Input Tokens | Max Output Tokens | Image Input | Reasoning | Tool Calling |
|---|---|---|---|---|---|
| mistral-large-latest | 262,144 | 262,144 | Yes | No | Yes |
| mistral-large-2512 | 262,144 | 262,144 | Yes | No | Yes |
| mistral-small-latest | 128,000 | 16,384 | Yes | No | Yes |
| mistral-medium-latest | 128,000 | 16,384 | Yes | No | Yes |
| mistral-nemo | 128,000 | 128,000 | No | No | Yes |
| codestral-latest | 256,000 | 4,096 | No | No | Yes |
| magistral-small | 128,000 | 128,000 | No | Yes | Yes |
| magistral-medium-latest | 128,000 | 16,384 | No | Yes | Yes |
| mistral-embed | 8,000 | 3,072 | No | No | No |
| open-mixtral-8x22b | 64,000 | 64,000 | No | No | Yes |
Usage Examples
Accessing a Model Profile
from langchain_mistralai.data._profiles import _PROFILES
profile = _PROFILES.get("mistral-large-latest")
print(profile["max_input_tokens"]) # 262144
print(profile["tool_calling"]) # True
print(profile["image_inputs"]) # True