AI Models

434 모델 Free & Paid 업데이트: 3 hours trước

Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:...

by |Dec 2025 |128K context |Miễn phí input |Miễn phí output
128K tokens ⓘ

GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...

by |Dec 2025 |400K context |$1.25/M input |$10.00/M output
400K tokens ⓘ

Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...

by |Dec 2025 |1M context |$0.3000/M input |$2.50/M output
1M tokens ⓘ

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...

by |Dec 2025 |262K context |$0.2000/M input |$0.2000/M output
262K tokens ⓘ

A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

by |Dec 2025 |262K context |$0.1500/M input |$0.1500/M output
262K tokens ⓘ

The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.

by |Dec 2025 |131K context |$0.1000/M input |$0.1000/M output
131K tokens ⓘ

미스트랄 라지 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.

by |Dec 2025 |262K context |$0.5000/M input |$1.50/M output
262K tokens ⓘ

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

by |Dec 2025 |164K context |$0.2600/M input |$0.3800/M output
164K tokens ⓘ

직장 마감 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...

by |Nov 2025 |200K context |$5.00/M input |$25.00/M output
200K tokens ⓘ

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...

by |Nov 2025 |66K context |$2.00/M input |$12.00/M output
66K tokens ⓘ

GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...

by |Nov 2025 |400K context |$1.25/M input |$10.00/M output
400K tokens ⓘ

GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....

by |Nov 2025 |400K context |$1.25/M input |$10.00/M output
400K tokens ⓘ

GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex

by |Nov 2025 |400K context |$0.2500/M input |$2.00/M output
400K tokens ⓘ

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...

by |Nov 2025 |262K context |$0.6000/M input |$2.50/M output
262K tokens ⓘ

Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.

by |Oct 2025 |1M context |$2.50/M input |$12.50/M output
1M tokens ⓘ

Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...

by |Oct 2025 |200K context |$3.00/M input |$15.00/M output
200K tokens ⓘ

Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...

by |Oct 2025 |33K context |$0.1000/M input |$0.3000/M output

gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...

by |Oct 2025 |131K context |$0.0750/M input |$0.3000/M output
131K tokens ⓘ

GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...

by |Oct 2025 |400K context |$2.50/M input |$2.00/M output
400K tokens ⓘ

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...

by |Oct 2025 |200K context |$1.00/M input |$5.00/M output
200K tokens ⓘ

Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...

by |Oct 2025 |262K context |$0.2500/M input |$0.7500/M output
262K tokens ⓘ

[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...

by |Oct 2025 |400K context |$10.00/M input |$10.00/M output
400K tokens ⓘ

Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...

by |Oct 2025 |33K context |$0.3000/M input |$2.50/M output

Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...

by |Oct 2025 |262K context |$0.1500/M input |$0.6000/M output
262K tokens ⓘ

GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...

by |Oct 2025 |400K context |$15.00/M input |$120.00/M output
400K tokens ⓘ

Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...

by |9 월 2025 |205K context |$0.5000/M input |$2.00/M output
205K tokens ⓘ

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...

by |9 월 2025 |1M context |$3.00/M input |$15.00/M output
1M tokens ⓘ

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

by |9 월 2025 |164K context |$0.2700/M input |$0.4100/M output
164K tokens ⓘ

Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.

by |9 월 2025 |131K context |$0.3000/M input |$0.5000/M output
131K tokens ⓘ

Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...

by |9 월 2025 |256K context |$0.8500/M input |$1.25/M output
256K tokens ⓘ

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...

by |9 월 2025 |262K context |$0.2100/M input |$1.90/M output
262K tokens ⓘ

DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...

by |9 월 2025 |164K context |$0.2700/M input |$1.00/M output
164K tokens ⓘ

Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...

by |9 월 2025 |1M context |$0.1950/M input |$0.9750/M output
1M tokens ⓘ

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...

by |9 월 2025 |262K context |$0.0900/M input |$1.10/M output
262K tokens ⓘ

Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...

by |9 월 2025 |262K context |$0.6000/M input |$2.50/M output
262K tokens ⓘ

Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...

by |Aug 2025 |131K context |$1.00/M input |$3.00/M output
131K tokens ⓘ

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

by |Aug 2025 |164K context |$0.2500/M input |$0.9500/M output
164K tokens ⓘ

Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...

by |Aug 2025 |131K context |$0.4000/M input |$2.00/M output
131K tokens ⓘ

GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...

by |Aug 2025 |66K context |$0.6000/M input |$1.80/M output
66K tokens ⓘ

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...

by |Aug 2025 |400K context |$1.25/M input |$10.00/M output
400K tokens ⓘ

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....

by |Aug 2025 |400K context |$0.2500/M input |$2.00/M output
400K tokens ⓘ

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...

by |Aug 2025 |400K context |$0.0250/M input |$0.2000/M output
400K tokens ⓘ

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...

by |Aug 2025 |400K context |$0.0500/M input |$0.4000/M output
400K tokens ⓘ

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

by |Aug 2025 |131K context |$0.0296/M input |$0.1360/M output
131K tokens ⓘ

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

by |Aug 2025 |131K context |$0.1500/M input |$0.6000/M output
131K tokens ⓘ

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

by |Aug 2025 |131K context |$0.0240/M input |$0.1120/M output
131K tokens ⓘ

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

by |Aug 2025 |131K context |$0.0750/M input |$0.3000/M output
131K tokens ⓘ

직장 마감 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...

by |Aug 2025 |200K context |$15.00/M input |$75.00/M output
200K tokens ⓘ

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)

by |Aug 2025 |256K context |$0.3000/M input |$0.9000/M output
256K tokens ⓘ

Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...

by |Jul 2025 |262K context |$0.1500/M input |$0.6000/M output
262K tokens ⓘ