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

DeepSeek-V4.1-Flash-1017

Visual LLM

DeepSeek-V4.1-Flash-1017 is a multimodal MoE (Mixture of Experts) model built on DeepSeek's Causal Encoder-Decoder architecture. It supports a 1M-token context and is designed for coding, agentic tasks, and end-to-end project development.

Supported FeaturesFunction callingVisionReasoningStreaming
Output Formatsraw_textjson_objectjson_schema
Pricing
₹30.28/ Mtoken input
₹121.10/ Mtoken output
Release date
17 Oct 2026
Added to the catalogue
12 Nov 2026
Context Sizes
1M
Parameters
748B
https://oai.endpoints.kepler.ai.cloud.ovh.net/v1