AI Models

434 models Free & Paid Cập nhật: 3 giờ trước

Hy4 flash is a cost-efficient variant of [Hy4](https://openrouter.ai/tencent/hy4) from Tencent, served with roughly a quarter of the flagship's parameter count for lower latency and cost. It targets code assistance, agent...

by |Th11 2026 |1M context |$0.0350/M input |$0.1405/M output
1M tokens ⓘ

Qwen4 Max is the flagship model in Alibaba's Qwen4 series. It accepts text, image, and video input and returns text, with a 1M-token context window and reasoning enabled by default....

by |Th11 2026 |1M context |$1.43/M input |$4.28/M output
1M tokens ⓘ

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...

by |Th11 2026 |1M context |Miễn phí input |Miễn phí output
1M tokens ⓘ

Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than...

by |Th11 2026 |1M context |$1.50/M input |$7.50/M output
1M tokens ⓘ

Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than...

by |Th11 2026 |1M context |$0.7500/M input |$3.75/M output
1M tokens ⓘ

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...

by |Th11 2026 |1M context |Miễn phí input |Miễn phí output
1M tokens ⓘ

ERNIE-Light-DT-1.0 is based on open-source GLM models and includes research findings from Baidu Search's Lightning large model. It features Baidu Sparse Attention (BSA), a unique sparse attention mechanism developed by...

by |Th11 2026 |1M context |$1.13/M input |$3.94/M output
1M tokens ⓘ

Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. It takes text, image, audio, video and file input, supports long decode...

by |Th11 2026 |1M context |$2.00/M input |$10.00/M output
1M tokens ⓘ

Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. It takes text, image, audio, video and file input, supports long decode...

by |Th11 2026 |1M context |$1.00/M input |$5.00/M output
1M tokens ⓘ

Nex-N2.6 is an agentic model from Nex AGI, built on [GLM-5.3-Flash](https://huggingface.co/zai-org/GLM-5.3-Flash-BF16) with about 321B parameters. It is suited for computer use, coding, and long-horizon tasks that involve tools. Compared with...

by |Th11 2026 |262K context |$0.1200/M input |$0.4000/M output
262K tokens ⓘ

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...

by |Th11 2026 |1M context |Miễn phí input |Miễn phí output
1M tokens ⓘ

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...

by |Th11 2026 |1M context |$0.3000/M input |$1.00/M output
1M tokens ⓘ

Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. In prerelease testing it completed otherwise-infeasible...

by |Th11 2026 |1M context |$8.00/M input |$40.00/M output
1M tokens ⓘ

Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. In prerelease testing it completed otherwise-infeasible...

by |Th11 2026 |1M context |$4.00/M input |$20.00/M output
1M tokens ⓘ

Muse Ember is the smallest and most efficient model from Meta that’s designed for complex reasoning execution and the work agents repeat all day: tool calls, coding agent subtasks, routing,...

by |Th11 2026 |1M context |$0.1000/M input |$0.5000/M output
1M tokens ⓘ

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...

by |Th11 2026 |262K context |$0.0800/M input |$0.2000/M output
262K tokens ⓘ

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...

by |Th11 2026 |262K context |Miễn phí input |Miễn phí output
262K tokens ⓘ

Gemini Omni 1.2 Flash is Google's native multimodal video generation and editing model, the successor to Gemini Omni 1.1 Flash. It generates clips up to 15 seconds long with native...

by |Th11 2026 |131K context |$1.50/M input |$9.00/M output
131K tokens ⓘ

Mi:dm K 3.0 Pro is a Mixture-of-Experts reasoning model from KT, with 120B total and 12B active parameters. It uses a hybrid architecture that mixes Mamba, MoE and attention layers.

by |Th11 2026 |262K context |$0.2000/M input |$0.8000/M output
262K tokens ⓘ

Auto is OpenRouter’s flagship model router, built for general-purpose usage. It adapts to each request, choosing cost-optimal models and adjusting reasoning effort. It balances task difficulty, benchmark results, live prices,...

by |Th11 2026 |2M context |Miễn phí input |Miễn phí output
2M tokens ⓘ

Auto Code is OpenRouter’s router built specifically for coding agents and harnesses. It uses the same routing engine as the [Auto Router](https://openrouter.ai/openrouter/auto), with every request treated as part of an...

by |Th11 2026 |2M context |Miễn phí input |Miễn phí output
2M tokens ⓘ

Gemini Omni 1.1 Flash is Google's native multimodal video generation and editing model, the generally available successor to Gemini Omni Flash Preview. It is suited for text-to-video, image-to-video, first and...

by |Th11 2026 |131K context |$1.50/M input |$9.00/M output
131K tokens ⓘ

Ripple-65B-Preview by ricursiveAI, a 65B model with native tool calling, served in BF16.

by |Th11 2026 |1M context |$0.1000/M input |$0.3000/M output
1M tokens ⓘ

The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity...

by |Th11 2026 |1M context |$0.4170/M input |$1.25/M output
1M tokens ⓘ

Motif 3 is a Mixture-of-Experts language model from Motif Technologies, with 314B total and 13.2B active parameters. It is a general-purpose multilingual model for English and Korean, particularly strong at...

by |Th11 2026 |262K context |$0.3000/M input |$1.20/M output
262K tokens ⓘ

GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. It adds legal-domain mid-training and post-training with reinforcement...

by |Th11 2026 |1M context |$0.3700/M input |$1.25/M output
1M tokens ⓘ

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...

by |Th10 2026 |1M context |$0.0600/M input |$0.5000/M output
1M tokens ⓘ

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...

by |Th10 2026 |1M context |Miễn phí input |Miễn phí output
1M tokens ⓘ

GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

by |Th10 2026 |1.1M context |$0.5000/M input |$2.50/M output
1.1M tokens ⓘ

GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

by |Th10 2026 |1.1M context |$1.00/M input |$5.00/M output
1.1M tokens ⓘ

GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...

by |Th10 2026 |1.1M context |$1.00/M input |$5.00/M output
1.1M tokens ⓘ

GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...

by |Th10 2026 |1.1M context |$0.5000/M input |$2.50/M output
1.1M tokens ⓘ

Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...

by |Th10 2026 |1M context |$0.3780/M input |$5.67/M output
1M tokens ⓘ

Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...

by |Th10 2026 |1M context |$0.2403/M input |$8.40/M output
1M tokens ⓘ

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...

by |Th10 2026 |262K context |Miễn phí input |Miễn phí output
262K tokens ⓘ

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,...

by |Th10 2026 |1M context |$0.0750/M input |$0.3000/M output
1M tokens ⓘ

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...

by |Th10 2026 |1M context |$0.0360/M input |$0.5000/M output
1M tokens ⓘ

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...

by |Th10 2026 |1M context |$0.0350/M input |$0.3140/M output
1M tokens ⓘ

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...

by |Th10 2026 |262K context |$0.6000/M input |$3.00/M output
262K tokens ⓘ

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...

by |Th10 2026 |1M context |$0.3000/M input |$1.00/M output
1M tokens ⓘ

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...

by |Th10 2026 |262K context |$0.0800/M input |$0.1300/M output
262K tokens ⓘ

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...

by |Th10 2026 |32K context |$0.3000/M input |$2.50/M output

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...

by |Th10 2026 |32K context |$0.3000/M input |$2.50/M output

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...

by |Th10 2026 |1M context |$1.25/M input |$4.25/M output
1M tokens ⓘ

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...

by |Th10 2026 |1M context |$0.1500/M input |$0.5000/M output
1M tokens ⓘ

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...

by |Th10 2026 |1M context |Miễn phí input |Miễn phí output
1M tokens ⓘ

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.

by |Th10 2026 |1M context |$0.8000/M input |$3.20/M output
1M tokens ⓘ

This model always redirects to the latest model in the Pareto family.

by |Th10 2026 |1M context |$0.8000/M input |$3.20/M output
1M tokens ⓘ

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.

by |Th10 2026 |262K context |$2.50/M input |$7.50/M output
262K tokens ⓘ

LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...

by |Th10 2026 |128K context |$0.0500/M input |$0.7000/M output
128K tokens ⓘ