AI Endpoints: catalogue and playground

Compare and test open-weight models for text, code, voice and vision, no sign-up required. Then move to production with the same OpenAI-compatible API.

laguna-xs-2.1

Reasoning LLM

Laguna XS 2.1 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token, designed for agentic coding and long-horizon work. It uses Sliding Window Attention with per-head gating for fast inference and low KV cache requirements, and supports reasoning and tool calling.

Supported FeaturesFunction callingReasoningStreaming
Output Formatsraw_textjson_objectjson_schema
Pricing
₹5.61/ Mtoken input
₹11.21/ Mtoken output
Release date
2 Jul 2026
Added to the catalogue
17 Nov 2026
Context Sizes
128k
Parameters
33B
https://oai.endpoints.kepler.ai.cloud.ovh.net/v1