AI model library — official specs, cutoffs & comparisons

1,512 matching models

TencentAvailable

Penguin-VL-2B

Penguin · Penguin-VL-2B

Open weights

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

TencentAvailable

Penguin-VL-8B

Penguin · Penguin-VL-8B

Open weights

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

MicrosoftListed by publisher

phi-1

Phi

Open weights

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

MicrosoftListed by publisher

phi-1_5

Phi

Open weights

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

MicrosoftListed by publisher

phi-2

Phi

Open weights

Context: 2,048 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

MicrosoftListed by publisher

Phi-3-mini-128k-instruct

Phi

Open weights

Context: 128,000 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

MicrosoftListed by publisher

Phi-3-mini-4k-instruct

Phi

Open weights

Context: 4,000 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

MicrosoftListed by publisher

Phi-3.5-vision-instruct

Phi

Open weights

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

MicrosoftListed by publisher

Phi-Ground

Phi

Open weights

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

MicrosoftListed by publisher

Phi-Ground-Any

Phi

Open weights

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

MicrosoftListed by publisher

Phi-mini-MoE-instruct

Phi

Open weights

Context: 4,000 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

MicrosoftListed by publisher

Phi-tiny-MoE-instruct

Phi

Open weights

Context: 4,000 tokens
Max. output: Not documented
Knowledge cutoff: Not documented

Mistral AIListed by publisher

Pixtral-12B-Base-2409

Pixtral

Open weights

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

TencentAvailable

POINTS-GUI-G

POINTS · POINTS-GUI-G

Open weights

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

TencentAvailable

POINTS-Seeker

POINTS · POINTS-Seeker

Open weights

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

BaiduAvailable

Qianfan-VL-3B

Qianfan · Qianfan-VL-3B

Open weights

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

BaiduAvailable

Qianfan-VL-70B

Qianfan · Qianfan-VL-70B

Open weights

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

BaiduAvailable

Qianfan-VL-8B

Qianfan · Qianfan-VL-8B

Open weights

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

QwenPreview

QVQ-72B-Preview

QVQ · QVQ-72B-Preview

Open weights

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

QwenAvailable

Qwen-1_8B

Qwen · Qwen-1_8B

Open weights

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

QwenAvailable

Qwen-1_8B-Chat-Int4

Qwen · Qwen-1_8B-Chat-Int4

Open weights

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

QwenAvailable

Qwen-1_8B-Chat-Int8

Qwen · Qwen-1_8B-Chat-Int8

Open weights

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

QwenAvailable

Qwen-14B

Qwen · Qwen-14B

Open weights

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

QwenAvailable

Qwen-14B-Chat

Qwen · Qwen-14B-Chat

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