Best suited for
- 01
Coding and software engineering
Generate production code and resolve engineering tasks across repositories and programming languages.
- 02
Reasoning and knowledge
Choose fast answers or maximum-effort reasoning for science, maths and general knowledge questions.
- 03
Agents and long context
Run search and multi-tool agents, and work over large codebases and documents in a long context window.
Benchmarks
- 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
- 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
- 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
- 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 Completionsfrom sarvamai import SarvamAIclient = 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)
- 01 Install the Sarvam SDK
Install
sarvamaifor Python or JavaScript. Store your key inSARVAM_API_KEY. - 02 Choose your model
Use model ID
deepseekv4-pro. The SDK callshttps://api.sarvam.ai/v2/chat/completionsfor 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 - 03 Validate your application
Check output quality, supported parameters and tool behaviour on representative requests before moving production traffic.
Frequently asked questions
Explore other models
View catalogueSarvam Prism
- Sarvam
- Decisions
System-1 decision model on Sarvam 105B. Send a state and typed questions; get a calibrated probability for every option in one call, with no text to parse.
Gemma 4 31B
- Chat
- Vision
31B-parameter instruction-tuned model for text and image understanding, with tool calling and optional reasoning.
Sarvam 105B
- Sarvam
- Chat
- Indian languages
Chat and tool calling across Indian languages and English, trained from scratch by Sarvam.
Build with frontier open-weight models. Served from India.
Build with frontier open-weight models. Served from India.