Best suited for
- 01
Multilingual business workflows
Process instructions and business content across Indian languages, English and code-mixed conversations.
- 02
Language-aware agents
Connect multilingual reasoning to your application tools for workflows that require structured actions.
- 03
Flexible reasoning depth
Use hybrid reasoning to match the depth of analysis to the task, from direct responses to more involved problem solving.
Benchmarks
Artificial Analysis does not currently publish quality scores for Sarvam 105B.
The Sarvam 105B comparison page has no Intelligence Index result.
The page compares Sarvam 105B (High) with GPT-5.4 Pro (Xhigh) on price, speed and context. It does not include an Intelligence Index or exam score.
See GLM 5.3 benchmarksBuild with the Sarvam SDK
pip install --upgrade sarvamaiV2 · Sarvam SDK · Streamingimport osfrom sarvamai import SarvamAIclient = SarvamAI(api_subscription_key=os.environ["SARVAM_API_KEY"])stream = client.chat.completions_v2(model="sarvam-105b",messages=[{"role": "user", "content": "Explain how solar panels work in Hindi briefly."}],max_tokens=8000,reasoning_effort="low",stream=True,)for chunk in stream:if not chunk.choices:continuetext = chunk.choices[0].delta.contentif text:print(text, end="", flush=True)
- 01 Install the Sarvam SDK
Install
sarvamaifor Python or JavaScript. Store your key inSARVAM_API_KEY. - 02 Choose your model
Use model ID
sarvam-105b. The SDK callshttps://api.sarvam.ai/v2for this example.V2 Chat Completions. Low reasoning effort is selected for this example. Reasoning and answer tokens share the 8,000-token output budget.
- 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 catalogueGLM 5.3
- Z.ai
- Reasoning and coding
- 1M context
Large-scale reasoning model built for complex software engineering and long-horizon agent tasks.
GLM 5.3 Flash
- Z.ai
- Reasoning and coding
- 1M context
Faster open-weight reasoning model for agents and image understanding.
DeepSeek V4.1 Flash 1017
- DeepSeek
- Reasoning and coding
- 1M context
General-purpose open-weight model for long-document analysis and agentic workflows.
From model choice to production. Bring your workload, traffic expectations and latency targets. Build on Sarvam’s serving stack in India.
From model choice to production.
Bring your workload, traffic expectations and latency targets. Build on Sarvam’s serving stack in India.