Sarvam AI
Alibaba

Qwen 3.8 27B

Alibaba's 27B vision-language model for coding, computer use and document understanding.

  • Chat
  • Reasoning
  • Vision
Provisioned Throughput

Best suited for

  1. 01

    Agentic software engineering

    Run terminal and repository agents that finish multi-step engineering tasks, with reasoning effort set per step.

  2. 02

    Computer and device automation

    Automate desktop, browser and mobile workflows with agents that read screenshots and act on what they see.

  3. 03

    Document and visual analysis

    Parse documents, charts and diagrams alongside text, and work across large mixed sets in one request.

Benchmarks

Score (%)
  • GPT-5.6 Sol 94.1
  • Claude Opus 5 93.2
  • Grok 4.5 93.1
  • Claude Fable 5 92.6
  • GPT-5.6 Luna 91.1
  • Qwen 3.8 27B 89.2
Score (%)
  • Claude Fable 5 53.0
  • Claude Opus 5 53.0
  • GPT-5.6 Sol 47.0
  • Grok 4.5 40.0
  • GPT-5.6 Luna 37.0
  • Qwen 3.8 27B 30.8

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="qwen38-27b",    messages=[        {"role": "user", "content": "Explain the difference between TCP and UDP in three bullet points."}    ],    max_tokens=2000,)​print(response.choices[0].message.content.strip())
  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 qwen38-27b. The SDK calls https://api.sarvam.ai/v2/chat/completions for this example.

    V2 Chat Completions. Max 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.