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)、Nemotron 3.5 Super VL (free)和ERNIE-5.5-Flash-Preview (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 (free)
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.
NVIDIA: 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 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.
Baidu: ERNIE-5.5-Flash-Preview (free)
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.
NVIDIA: Nemotron 3.5 Lightning (free)
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.
Thinking Machines: Inkling 2 Small (free)
Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total. It is the first model in the second Inkling generation. It was trained with reinforcement learning on long-horizon coding tasks across many agent harnesses, and is suited for agentic coding, autonomous research, agentic knowledge work and retrieval-augmented generation, with English and general multilingual support. It accepts text and image input (no audio), supports tool calling and variable reasoning effort, and has a 1M-token context window.

Dots Studio: Dots3-Note Preview (free)
Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is suited for reasoning, coding, multimodal understanding, long-context processing, and multi-step agent workflows.
Particle AI: Particle-1 (free)
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.

Cohere: North Mini Code (free)
North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized for code generation, agentic software engineering, and terminal tasks, and is trained to generalize across agent harnesses such as OpenCode and SWE-Agent.
It offers a 256K-token context window with up to 64K tokens of output, supports interleaved reasoning and tool use via JSON schema, and is released open-weight under the Apache 2.0 license. Its small active-parameter footprint enables low-latency inference, including on local hardware.
Recursive: Flint (free)
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.
inclusionAI: Ling 3.2 Flash (free)
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.

Perplexity: Decider V1.3 (free)
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.
NVIDIA: Nemotron 3 Nano Omni (free)
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.

LiquidAI: LFM3-1.7B (free)
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.

Perplexity: Decider Flash V1.3 (free)
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.
Respan: Span-01 Lite
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.
Llama Nemotron Rerank VL 1B V2 is a 1.7B multimodal reranking model from NVIDIA. It evaluates the relevance of document images and text against user queries, designed for vision RAG pipelines handling charts, tables, infographics, and mixed-media documents. Functions as a cross-encoder that accepts text queries paired with image, text, or combined document inputs, delivering approximately 6-7% recall improvements over embedding-only baselines on visual document retrieval benchmarks.
常见问题
是的。此页面上每个模型的模型定价均为 $0,因此其用量不计费。ID 以 :free 结尾的免费变体无需购买额度,而其他 $0 模型仍可能要求账户已充值。免费用量受速率限制。
ID 以 :free 结尾的免费变体,每分钟上限为 20 次请求,每天上限为 50 次请求,当您的账户累计购买 $10 的额度后,每天上限将提高至 1,000 次请求(为抵消充值费用,较高上限从 $9 起生效)。失败的尝试计入每日上限。其他 $0 模型不受这些上限约束,但仍可能触及 OpenRouter 或提供商为各模型设置的限制。请参阅速率限制文档。
对于聊天模型,请向您用于付费模型的同一个兼容 OpenAI 的 Chat Completions 端点发送请求,并在 model 字段中填入免费模型 ID。其他模型类型使用各自的 API,例如重排序模型使用 /api/v1/rerank,决策模型使用 /api/alpha/decisions,因此请查看模型页面以获取正确的端点。付费模型的免费版本以 :free 结尾。
可以。将模型设为 openrouter/free,每个请求就会被路由到适合它的免费模型,因此您无需跟踪当前有哪些免费模型可用。
不需要。一个 OpenRouter API 密钥即可同时用于免费和付费模型——在您的 API 密钥页面创建密钥,即可在所有模型中复用。