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.

New

qwen3.6-35b-a3b

Reasoning LLM

Qwen3.6-35B-A3B is a Mixture-of-Experts language model from the Qwen team with 35B total and 3B active parameters and a 256k context window. It supports reasoning, tool calling and structured outputs.

Supported FeaturesFunction callingReasoningStreaming
Output Formatsraw_textjson_objectjson_schema
Pricing
$0.20/ Mtoken input
$1.33/ Mtoken output
Release date
Apr 16, 2026
Added to the catalogue
Nov 17, 2026
Context Sizes
256k
Parameters
35B
https://oai.endpoints.kepler.ai.cloud.ovh.net/v1