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.

gemma-4-26b-a4b

Large Language Models (LLM)

Gemma 4 26B A4B is an instruction-tuned Mixture-of-Experts model from Google DeepMind with 26B total parameters and about 4B active parameters, optimized with Quantization-Aware Training and served in 4-bit. It supports tool calling and structured outputs, with a 256k context window.

Supported FeaturesFunction callingStreaming
Output Formatsraw_textjson_objectjson_schema
Pricing
₹10.09/ Mtoken input
₹39.25/ Mtoken output
Release date
2 Apr 2026
Added to the catalogue
17 Nov 2026
Context Sizes
256k
Parameters
26B
https://oai.endpoints.kepler.ai.cloud.ovh.net/v1