AI model library — official specs, cutoffs & comparisons · Headless Thrones

1,512 matching models

Z.aiAvailable

WebVIA-Agent

WebVIA · WebVIA-Agent

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

QwenAvailable

WebWorld-14B

WebWorld · WebWorld-14B

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

QwenAvailable

WebWorld-32B

WebWorld · WebWorld-32B

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

QwenAvailable

WebWorld-8B

WebWorld · WebWorld-8B

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

TencentAvailable

WeDLM-7B-Base

WeDLM · WeDLM-7B-Base

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

TencentAvailable

WeDLM-7B-Instruct

WeDLM · WeDLM-7B-Instruct

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

TencentAvailable

WeDLM-8B-Base

WeDLM · WeDLM-8B-Base

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

TencentAvailable

WeDLM-8B-Instruct

WeDLM · WeDLM-8B-Instruct

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

TencentAvailable

WeVisOne-VL-2B

WeVisOne · WeVisOne-VL-2B

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

TencentAvailable

WeVisOne-VL-4B

WeVisOne · WeVisOne-VL-4B

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

Arcee AIListed by publisher

WitchLM-1.5B

WitchLM

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

Nous ResearchListed by publisher

Yarn-Llama-2-13b-128k

Yarn

Open weights

Context: 128k tokens
Max. output: Not documented
Knowledge cutoff: Not documented

Nous ResearchListed by publisher

Yarn-Llama-2-13b-64k

Yarn

Open weights

Context: 64k tokens
Max. output: Not documented
Knowledge cutoff: Not documented

Nous ResearchListed by publisher

Yarn-Llama-2-70b-32k

Yarn

Open weights

Context: 32k tokens
Max. output: Not documented
Knowledge cutoff: Not documented

Nous ResearchListed by publisher

Yarn-Llama-2-7b-128k

Yarn

Open weights

Context: 128K tokens
Max. output: Not documented
Knowledge cutoff: Not documented

Nous ResearchListed by publisher

Yarn-Llama-2-7b-64k

Yarn

Open weights

Context: 64k tokens
Max. output: Not documented
Knowledge cutoff: Not documented

Nous ResearchListed by publisher

Yarn-Mistral-7b-128k

Mistral

Open weights

Context: 128k tokens
Max. output: Not documented
Knowledge cutoff: Not documented

Nous ResearchListed by publisher

Yarn-Mistral-7b-64k

Mistral

Open weights

Context: 64k tokens
Max. output: Not documented
Knowledge cutoff: Not documented

Nous ResearchListed by publisher

Yarn-Solar-10b-32k

Yarn

Open weights

Context: 32k tokens
Max. output: Not documented
Knowledge cutoff: Not documented

Nous ResearchListed by publisher

Yarn-Solar-10b-64k

Yarn

Open weights

Context: 64k tokens
Max. output: Not documented
Knowledge cutoff: Not documented

01.AIAvailable

Yi-1.5-34B

Yi · Yi-1.5-34B

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

01.AIAvailable

Yi-1.5-34B-32K

Yi · Yi-1.5-34B-32K

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

01.AIAvailable

Yi-1.5-34B-Chat

Yi · Yi-1.5-34B-Chat

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

01.AIAvailable

Yi-1.5-34B-Chat-16K

Yi · Yi-1.5-34B-Chat-16K

Open weights

Context: Not documented
Max. output: Not documented
Knowledge cutoff: Not documented

Go beyond the spec sheet

The decisions behind the numbers.

Source-checked guides to pricing, usable context, and access restrictions.

Claude Sonnet 4.6 pricing: API costs, caching and real workload math GPT-5.4 context window: the 1.05M limit, output budget and cost threshold Gemini 2.5 Pro context window: input limits, access and long-document costs GPT-5.4 mini context window: 400K capacity and practical task budgets