Show HN: Tkcore AI – A multi-model workspace with custom knowledge grounding

Sharanxxxx1 pts0 comments

AI chat & free AI tools | TKCORE AI

TKCORE AI — Private AI chat, file analysis, and writing tools on your TKCore API.<br>Enable JavaScript to use the application.

TKCOREAI

TKCOREAI

AI chat, free AI tools, documents & writing<br>TkCore-V5.5-Pro New Fast responses and low latency — balanced quality, long context, and multimodal when you attach images.

Fast responses and low latency — balanced quality, long context, and multimodal when you attach images.

DeepSeek<br>DeepSeek-V3.2 · Chat V3.2 Chat General chat and tools — strong JSON/structured output and long 128K-class context for everyday work. General chat and tools — strong JSON/structured output and long 128K-class context for everyday work.

Deepseek-V3.2-Exp V3.2 Exp Exp Experimental V3.2 — extended reasoning and coding for complex analysis and structured output. Experimental V3.2 — extended reasoning and coding for complex analysis and structured output.

DeepSeek-V4 · Flash V4 Flash V4 Low-latency V4 — high throughput text; screenshots route to V4 Pro automatically for sharper vision. Low-latency V4 — high throughput text; screenshots route to V4 Pro automatically for sharper vision.

DeepSeek-V4 · Pro V4 Pro Pro V4 flagship — best DeepSeek balance of reasoning, coding, and multimodal detail when images are in play. V4 flagship — best DeepSeek balance of reasoning, coding, and multimodal detail when images are in play.

Qwen<br>Qwen-Max Qwen Max Max Top-tier general model — strong reasoning, coding, and agent-style tasks; multimodal-capable when enabled. Top-tier general model — strong reasoning, coding, and agent-style tasks; multimodal-capable when enabled.

Qwen-Plus Qwen Plus Balanced cost and quality — everyday chat, tools, and multimodal input when your pipeline enables images/video. Balanced cost and quality — everyday chat, tools, and multimodal input when your pipeline enables images/video.

Qwen-Turbo Qwen Turbo Fast Low-latency, high-throughput text — great for drafts, classification, and high-QPS workloads. Low-latency, high-throughput text — great for drafts, classification, and high-QPS workloads.

Qwen-Long Qwen Long Long Extended context for long documents, legal/clinical summaries, and multi-chunk retrieval. Extended context for long documents, legal/clinical summaries, and multi-chunk retrieval.

Qwen-VL-Max Qwen VL VL Vision-language flagship — screenshots, charts, OCR-style understanding, and fine-grained image QA. Vision-language flagship — screenshots, charts, OCR-style understanding, and fine-grained image QA.

GLM (Zhipu)<br>GLM-5.1 GLM 5.1 Latest flagship — strong reasoning, math, and coding; supports optional thinking mode for step-by-step analysis. Latest flagship — strong reasoning, math, and coding; supports optional thinking mode for step-by-step analysis.

GLM-5.1 · Thinking GLM 5.1T Thinking Same GLM-5.1 with thinking enabled — best for hard problems, planning, and audit-style explanations. Same GLM-5.1 with thinking enabled — best for hard problems, planning, and audit-style explanations.

Kimi (Moonshot)<br>Kimi K2.5 Kimi K2.5 Frontier generalist — long context, agents, code, and multimodal (text + image/video) when your pipeline enables it. Frontier generalist — long context, agents, code, and multimodal (text + image/video) when your pipeline enables it.

Kimi K2 · Thinking Kimi K2T CoT Reasoning-first — excels at logic, tool-style workflows, and tasks where visible reasoning traces help. Reasoning-first — excels at logic, tool-style workflows, and tasks where visible reasoning traces help.

MiniMax<br>MiniMax M2.5 M2.5 Expressive, natural tone — strong for dialogue, storytelling, and conversion-oriented marketing copy. Expressive, natural tone — strong for dialogue, storytelling, and conversion-oriented marketing copy.

Expand input to fullscreen

Add files and more

Voice input — dictate into the box

Knowledge Upload files to provide context for more informed AI-generated responses.

Knowledge

You can upload knowledge files and the AI may search content in the file if needed to generate more informed responses.

Upload files

Sign in

reasoning long qwen multimodal chat context

Related Articles