Meet changing demand
Serving capacity scales automatically with your traffic, with dedicated GPUs ready for sustained volume.
Sarvam runs the serving infrastructure behind your applications so capacity, reliability and integration stay out of your way.
Serving capacity scales automatically with your traffic, with dedicated GPUs ready for sustained volume.
Active fleet monitoring and staged rollouts catch faults early and roll back changes before they hit traffic.
Use your existing tools and frameworks, and switch between models with minimal changes to your application.
Earlier first tokens and faster generation mean less waiting inside your application.
Keep critical applications available with 99.95% uptime guaranteed by an SLA.
Backed by contractual uptime commitments for enterprise deployments.
Workers scale automatically to hold your latency targets.
Active health checks detect and isolate faults across the fleet.
Rollouts happen in stages with automated checks and instant rollback.
From multi-step code edits to live voice streams, run every workload on one API.
Read repo context, reason through bugs and run tools to ship working patches.
Connect models to your APIs and business systems with structured JSON outputs.
Pass whole documents, instructions and chat history together in a 1M-token window.
Read pages, tables and charts alongside text to pull out structured data.
Tackle complex analysis and planning with adjustable reasoning effort.
Stream tokens straight into chat UIs and voice pipelines as they generate.
Explore open models for reasoning, coding, vision and Indian languages on Token Factory.
Run leading models through an OpenAI-compatible API. Sarvam manages the serving infrastructure in India.
pip install --upgrade sarvamaiV2 · Chat Completions · Sarvam SDKimport osfrom sarvamai import SarvamAIclient = SarvamAI(api_subscription_key=os.environ["SARVAM_API_KEY"])stream = client.chat.completions_v2(model="glm5.3",messages=[{"role": "user", "content": "Explain serverless inference briefly."}],max_tokens=8000,stream=True,)for chunk in stream:if not chunk.choices:continuetext = chunk.choices[0].delta.contentif text:print(text, end="", flush=True)
V2 Chat Completions. Max reasoning is the default. Reasoning tokens count toward the 8,000-token output budget.
Access supported models on Sarvam’s GPUs in India, with serving capacity that adapts to your traffic.
ISO 27001:2022 certified and SOC 2 Type II attested by independent assessors for information security and operational controls.
Prompts run on Sarvam GPUs in India and are not sent to foreign model providers.
Every request is encrypted, isolated to your account and scoped to your team.
Enable zero data retention on request, and set clear rules for logs.
Answers for teams evaluating models, moving applications and planning production.
Build with frontier open-weight models. Served from India.
Build with frontier open-weight models. Served from India.