AI 模型雷达
把 AI 模型放在一起比较
收录 OpenRouter 当前公开的全部模型，统一呈现模态、上下文窗口、价格、配置与提供方信息，并持续增量更新。
- 目录范围
- 全部公开
- 个模型
- 688
- 个提供方
- 97
- 最近同步
- 2026年10月29日
mistralaiMistral: Voxtral Mini Transcribe 3
Voxtral Mini Transcribe 3 is Mistral's compact speech-to-text model. It takes audio input and returns a transcript with timestamps and speaker diarization. It also supports context biasing for domain terms....
- 上下文
- 66K
- 输入
- audio
- 输出
- transcription
minimaxMiniMax: MiniMax M3.1 Flash
MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...
- 上下文
- 1.0M
- 输入
- text · image · video
- 输出
- text
deepseekDeepSeek: DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. V4.1 Flash is a sparse mixture-of-experts model...
- 上下文
- 1.0M
- 输入
- text · image
- 输出
- text
elorianElorian: Glimpse
Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...
- 上下文
- 262K
- 输入
- text · image · video
- 输出
- text
qwenQwen: Qwen Image 2.1 Turbo
Qwen Image 2.1 Turbo is the fast, lower-cost tier of the Qwen Image 2.1 series from Qwen, for image generation and editing where throughput and price matter more than peak...
- 上下文
- 66K
- 输入
- text · image
- 输出
- image
qwenQwen: Qwen Image 2.1 Pro
Qwen Image 2.1 Pro is an image generation and editing model from Qwen, the higher-quality tier of the Qwen Image 2.1 series. Choose it over Qwen Image 2.1 Turbo when...
- 上下文
- 66K
- 输入
- text · image
- 输出
- image
perplexityPerplexity: Decider Flash V1.2
Decider Flash V1.2 is a 4B-parameter decision model from Perplexity, a smaller, lower-cost sibling of Decider V1.2 with the same API contract. Instead of generating text, it reads content passed...
- 上下文
- 262K
- 输入
- text · image
- 输出
- decisions
perplexityPerplexity: Decider V1.2
Decider V1.2 is a new 27B checkpoint of Perplexity's decision model, succeeding Decider V1.1 27B with the same API contract. Instead of generating text, it reads content passed as state...
- 上下文
- 262K
- 输入
- text · image
- 输出
- decisions
xingchen-agiXingChen: Xing4.0 29B A4B (free)
Xing4.0-29B-A4B is an open-weight mixture-of-experts language model from China Telecom's AI team (TeleAI) and the successor to the TeleChat series. It has 29B total parameters with 4B active per token...
- 上下文
- 262K
- 输入
- text
- 输出
- text
~perplexityPerplexity: Decider Flash Latest
This model always redirects to the latest model in the Decider Flash family.
- 上下文
- 262K
- 输入
- text · image
- 输出
- decisions
reflectionReflection: Beam 1.0 501B A23B
Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...
- 上下文
- 1.0M
- 输入
- text
- 输出
- text
inceptionInception: Mercury 3
Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...
- 上下文
- 1M
- 输入
- text
- 输出
- text
prism-mlPrismML: Ternary Bonsai 2 9B
Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient...
- 上下文
- 262K
- 输入
- text · image
- 输出
- text
respanRespan: Span-02
Span-02 is an open-weight decision model from Respan. It reads a state of text and images and answers the questions you define about it: picking one of several options, a...
- 上下文
- 131K
- 输入
- text · image
- 输出
- decisions
liquidLiquidAI: d1-ultra
d1-ultra is Liquid AI's largest decision model, served as a System One endpoint. Send a state of text and images along with typed questions, and it returns a choice, a...
- 上下文
- 33K
- 输入
- text · image
- 输出
- decisions
kreaKrea: K3 Edit
Krea K3 Edit is an image-to-image editing model from Krea. It takes one to eight reference images plus a text prompt and returns a single edited image, following instructions that...
- 上下文
- 66K
- 输入
- text · image
- 输出
- image
moondreamMoondream: Moondream 3 Preview
Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...
- 上下文
- 32K
- 输入
- text · image
- 输出
- text
moondreamMoondream: Moondream 3.1
Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...
- 上下文
- 32K
- 输入
- text · image
- 输出
- text
metaMeta: Muse Spark Open
Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...
- 上下文
- 1.0M
- 输入
- text · image · video · file · audio
- 输出
- text
black-forest-labsBlack Forest Labs: FLUX 3 Image Klein
FLUX 3 Image Klein is an open-weights image generation and editing model from Black Forest Labs. It is suited for text-to-image, multi-reference editing that keeps characters and subjects consistent across...
- 上下文
- 47K
- 输入
- text · image
- 输出
- image
nvidiaNVIDIA: Nemotron 3.5 Super VL
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...
- 上下文
- 1.0M
- 输入
- text · image · video
- 输出
- text
nvidiaNVIDIA: Nemotron 3.5 Super VL (free)
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...
- 上下文
- 1M
- 输入
- text · image · video
- 输出
- text
unbiasedPareto 26.10
Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.
- 上下文
- 1.0M
- 输入
- text · image
- 输出
- text
typesafeTypeSafe: Jev 1.14
Jev 1.14 is the latest version of Jev, TypeSafe's structured decision model and the first of its System One models. System One models make fast, structured decisions for software, returning...
- 上下文
- 262K
- 输入
- text · image
- 输出
- decisions