Sarvam AI
DeepSeek

DeepSeek V4 Pro

DeepSeek's large open model for complex coding, agents and long-document analysis, with a 1M-token context window.

  • Reasoning
  • Chat
  • Code
  • LLM
Provisioned Throughput

Best suited for

  1. 01

    Coding and software engineering

    Generate production code and resolve engineering tasks across repositories and programming languages.

  2. 02

    Reasoning and knowledge

    Choose fast answers or maximum-effort reasoning for science, maths and general knowledge questions.

  3. 03

    Agents and long context

    Run search and multi-tool agents, and work over large codebases and documents in a long context window.

Benchmarks

Score
  • Kimi K2.6 58.6
  • GLM 5.1 58.4
  • GPT-5.4 57.7
  • Claude Opus 4.6 57.3
  • DeepSeek V4 Pro 55.4
  • Gemini 3.1 Pro 54.2
Score
  • GPT-5.4 75.1
  • Gemini 3.1 Pro 68.5
  • DeepSeek V4 Pro 67.9
  • Kimi K2.6 66.7
  • Claude Opus 4.6 65.4
  • GLM 5.1 63.5
Score
  • Claude Opus 4.6 73.8
  • DeepSeek V4 Pro 73.6
  • GLM 5.1 71.8
  • Gemini 3.1 Pro 69.2
  • GPT-5.4 67.2
  • Kimi K2.6 66.6
Score
  • Claude Opus 4.6 71.7
  • DeepSeek V4 Pro 62.0
  • Gemini 3.1 Pro 53.8

API usage

Build with the Sarvam SDK

pip install --upgrade sarvamaiV2 · Sarvam SDK · Chat Completions
from sarvamai import SarvamAI​client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")​response = client.chat.completions_v2(    model="deepseekv4-pro",    messages=[        {            "role": "user",            "content": "Explain the difference between a B-tree and a B+ tree index.",        }    ],    max_tokens=2000,)​print(response.choices[0].message.content)
  1. 01 Install the Sarvam SDK

    Install sarvamai for Python or JavaScript. Store your key in SARVAM_API_KEY.

  2. 02 Choose your model

    Use model ID deepseekv4-pro. The SDK calls https://api.sarvam.ai/v2/chat/completions for this example.

    Provisioned Throughput; contact Sarvam to arrange access. V2 Chat Completions. High reasoning is the default. Reasoning tokens count toward the 8,000-token output budget.

    API reference
  3. 03 Validate your application

    Check output quality, supported parameters and tool behaviour on representative requests before moving production traffic.

Read API docs

Frequently asked questions

Explore other models

View catalogue

Build with frontier open-weight models. Served from India.