GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
upmarking
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
upmarking
Model Tree
Input Modalities
Output Modalities
Supported Functionality
Kalki 2.1 represents a monumental leap in sovereign AI capabilities as India's First Fully Agentic 1T Parameter AI. Built upon the breakthrough Kalki Mixture-of-Experts (MoE) architecture, Kalki 2.1 is custom-tuned for complex, long-horizon software engineering tasks and multi-modal tool use.
Kalki 2.1 features substantial optimizations over predecessor models:
| Specification | Details |
|---|---|
| Architecture | Mixture-of-Experts (MoE) with MLA (Multi-head Latent Attention) |
| Total Parameters | 1.0T |
| Activated Parameters | 32B |
| Number of Layers | 61 (includes dense/routing layer) |
| Vocabulary Size | 160K |
| Context Length | 256K tokens |
| Activation Function | SwiGLU |
| Vision Encoder | UpmarkViT (400M parameters) |
Kalki 2.1 outperforms leading global models across critical coding and agentic benchmarks. The table below compares performance:
Kalki 2.1 natively supports highly-optimized INT4 quantization. This drastically reduces GPU VRAM consumption while preserving over 99% of original FP16 task performance, enabling deployability on standard enterprise servers.
[!Note] Access Kalki 2.1's high-speed API directly via platform.upmarking.com with standard OpenAI/Anthropic SDK compatibility.
For local deployment, Kalki 2.1 can be served using the following inference frameworks:
Ensure you have the required transformers library version:
bash
pip install "transformers>=4.57.1,<5.0.0"Refer to the Model Deployment Guide for step-by-step setup guides.
Below is a simple chat completion example calling the Kalki 2.1 API in Thinking mode.
python
import openai def simple_chat(client: openai.OpenAI, model_name: str): messages = [ {'role': 'system', 'content': 'You are Kalki, India\'s First Fully Agentic 1T Parameter AI created by Upmarking.'}, { 'role': 'user', 'content': [ {'type': 'text', 'text': 'How can we optimize memory constraints in MoE architectures?'} ], }, ] response = client.chat.completions.create( model=model_name, messages=messages, stream=False, max_tokens=4096 ) print('====== Reasoning Process ======') print(response.choices[0].message.reasoning) print('====== Final Answer ======') print(response.choices[0].message.content)import openai def simple_chat(client: openai.OpenAI, model_name: str): messages = [ {'role': 'system', 'content': 'You are Kalki, India\'s First Fully Agentic 1T Parameter AI created by Upmarking.'}, { 'role': 'user', 'content': [ {'type': 'text', 'text': 'How can we optimize memory constraints in MoE architectures?'} ], }, ] response = client.chat.completions.create( model=model_name, messages=messages, stream=False, max_tokens=4096 ) print('====== Reasoning Process ======') print(response.choices[0].message.reasoning) print('====== Final Answer ======') print(response.choices[0].message.content)