Find the model for your next build.

The Live entries are DeepSeek V4.1 Flash, DeepSeek V4.1 Flash 1M, GLM-5.3 Flash, GLM-5.3 Flash 1M, GLM-5.3, Qwen3.8-27B, Gemma 4 31B IT, Gemma 4 26B A4B IT, Nemotron 3.5 Super VL 120B A12B, Perplexity Decider v1.1 (27B). All of these run on GPUs in India. Decider handles typed decisions rather than generating chat responses.

Filter by use case and modality, then use India‑hosted only if the workload needs that location. Open a model page to review its inputs and intended applications.

India‑hosted models run on GPUs in India. Global models run outside India on partner infrastructure; check the hosting label for the route you select.

Launching soon entries are not live API endpoints. On-request entries are deployed on GPUs in India for your workload and priced per deployment.

The pricing page lists published input and output rates by model, in rupees per 1M tokens before GST. Perplexity Decider is billed on input tokens only. The calculator covers models with input and output token rates.

The tag describes model capability. The context column and each model page show confirmed served limits. On-request deployments have workload-specific requirements, so no token limit is published for them.

Tell us which open-weight model your application needs. Dedicated GPU deployments in India are available on request.

Sign up in the console, create a key, and configure your server's OpenAI SDK with https://api.indicstack.ai/v1 and your IndicStack key.