模型 · NovaRouter

Pareto LatestThis model always redirects to the latest model in the Pareto family.by Unbiased · 2026年10月13日262K 上下文$2.5 输入$7.5 输出

Pareto 26.9Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad r…by Unbiased · 2026年10月13日262K 上下文$2.5 输入$7.5 输出

HeyGen: HeyGen VoiceHeyGen Voice is a text-to-speech model from HeyGen. It comes with 10 default voices, or bring your own HeyGen key to use voice clones from your own ac…by HeyGen · 2026年10月13日— 上下文$15 输入$0 输出

HeyGen: HeyGen Voice TurboHeyGen Voice Turbo is a lower-latency version of HeyGen Voice, HeyGen's text-to-speech model. It has the same 10 default voices, or bring your own Hey…by HeyGen · 2026年10月13日— 上下文$7.5 输入$0 输出

LiquidAI: LFM2.5-24B-A2BLFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering a…by Liquid · 2026年10月13日128K 上下文$0.05 输入$0.7 输出

Fish Audio: Drama 3Drama 3 is a text-to-speech model from Fish Audio built for directed voice performances. You write the direction in plain language in square brackets…by Fish Audio · 2026年10月13日— 上下文$2 输入$0 输出

Google: Gemini 4 ArgonGemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and aut…by Google · 2026年10月13日1M 上下文$2 输入$10 输出

Google: Gemini 4 Argon (batch)Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and aut…by Google · 2026年10月13日1M 上下文$1 输入$5 输出

ScaleDown: SummarizeSummarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifti…by ScaleDown · 2026年10月13日1M 上下文$0.04 输入$0 输出

ScaleDown: ExtractExtract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want…by ScaleDown · 2026年10月13日1M 上下文$0.04 输入$0 输出

ScaleDown: Classify-1Classify-1 is a structured decision model from ScaleDown, served through OpenRouter's Decisions API. It scores text or a document against caller-defin…by ScaleDown · 2026年10月13日1M 上下文$0.04 输入$0 输出

Perplexity: Decider 27B LatestThis model always redirects to the latest model in the Decider 27B family.by Perplexity · 2026年10月12日262K 上下文$0.02 输入$0 输出

Nace.AI: Drex v2.0Drex v2.0 is a 35B mixture-of-experts decision model (3B active) from Nace.AI, the larger successor to Drex v1.5 (https://openrouter.ai/nace-ai/drex-v…by Nace · 2026年10月12日131K 上下文$0.06 输入$0 输出

Meta: Muse WonderMuse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, aud…by Meta · 2026年10月12日1M 上下文$4 输入$20 输出

Microsoft: Microsoft-Decision-1Microsoft-Decision-1 is a small model built for fast decision-making. Instead of generating text, it reads the provided content and returns a calibrat…by Microsoft · 2026年10月9日33K 上下文$0.042 输入$0 输出

Nace.AI: Drex v1.5Drex v1.5 is a 9B decision model from Nace.AI. Given a state (text or JSON) and typed questions (yes/no, multiple choice, or ordinal score), it return…by Nace · 2026年10月9日131K 上下文$0.04 输入$0 输出

Cloudflare: Clef OmniClef Omni is the mixture-of-experts member of Cloudflare's open-source Clef decision model family, a fine-tune of Qwen3-Omni-30B-A3B (30B total, 3B ac…by Cloudflare · 2026年10月9日66K 上下文$0.15 输入$0 输出

StepFun: Step 5 PreviewStep 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). I…by 阶跃星辰 · 2026年10月8日1M 上下文$1 输入$2.7 输出

Upstage: Solar Decide FlashSolar Decide Flash is Upstage's low-latency structured decision model, a faster variant of Solar Decide (/upstage/solar-decide) built on Solar Mini 4…by Upstage · 2026年10月8日524K 上下文$0.05 输入$0 输出

Anthropic: Claude Haiku 5.5Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds…by Anthropic · 2026年10月7日1M 上下文$0.1 输入$0.5 输出

Anthropic: Claude Haiku 5.5 (batch)Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds…by Anthropic · 2026年10月7日1M 上下文$0.05 输入$0.25 输出

Perplexity: Decider V1.1 27BDecider V1.1 27B is a new checkpoint of Perplexity's decision model, succeeding Decider V1 27B (/perplexity/pplx-decider-v1-27b) with the same API con…by Perplexity · 2026年10月7日262K 上下文$0.02 输入$0 输出

ElevenLabs: Eleven v4Eleven v4 is a text-to-speech model from ElevenLabs. It is ElevenLabs' most expressive model, with inline audio tags for emotional and delivery contro…by ElevenLabs · 2026年10月7日— 上下文$40 输入$0 输出

ElevenLabs: Eleven v4 TurboEleven v4 Turbo is a low-latency text-to-speech model from ElevenLabs. It keeps Eleven v4's expressive delivery and audio tags while being tuned for f…by ElevenLabs · 2026年10月7日— 上下文$20 输入$0 输出

ElevenLabs: Eleven v3Eleven v3 is a text-to-speech model from ElevenLabs. It produces emotionally rich, highly expressive speech with inline audio tags, supports 70+ langu…by ElevenLabs · 2026年10月7日— 上下文$40 输入$0 输出

ElevenLabs: Eleven v3 ConversationalEleven v3 Conversational is a text-to-speech model from ElevenLabs, a variant of Eleven v3 optimized for natural dialogue in conversational agents. It…by ElevenLabs · 2026年10月7日— 上下文$20 输入$0 输出

ElevenLabs: Eleven Flash v2.5Eleven Flash v2.5 is an ultra-low-latency text-to-speech model from ElevenLabs. It is suited for conversational and real-time use cases, supports 32 l…by ElevenLabs · 2026年10月7日— 上下文$20 输入$0 输出

ElevenLabs: Eleven Turbo v2Eleven Turbo v2 is an English-only, low-latency text-to-speech model from ElevenLabs. It is suited for developer use cases where speed matters and onl…by ElevenLabs · 2026年10月7日— 上下文$20 输入$0 输出

ElevenLabs: Eleven Multilingual v2Eleven Multilingual v2 is a text-to-speech model from ElevenLabs. It is suited for lifelike, consistent long-form narration such as voice-overs and au…by ElevenLabs · 2026年10月7日— 上下文$40 输入$0 输出

ElevenLabs: Eleven Turbo v2.5Eleven Turbo v2.5 is a low-latency text-to-speech model from ElevenLabs. It balances quality and speed for developer use cases that need non-English l…by ElevenLabs · 2026年10月7日— 上下文$20 输入$0 输出

ElevenLabs: Eleven Flash v2Eleven Flash v2 is an English-only, ultra-low-latency text-to-speech model from ElevenLabs. It is suited for conversational and real-time English use…by ElevenLabs · 2026年10月7日— 上下文$20 输入$0 输出

ElevenLabs: Scribe v2ElevenLabs Scribe v2 is a speech-to-text model that transcribes audio in 90+ languages with word-level timestamps, optional speaker diarization, and a…by ElevenLabs · 2026年10月7日— 上下文$30.56 输入$0 输出

ElevenLabs: Scribe v2 MedicalElevenLabs Scribe v2 Medical is a speech-to-text model tuned for clinical and medical terminology, with word-level timestamps, optional speaker diariz…by ElevenLabs · 2026年10月7日— 上下文$30.56 输入$0 输出

OpenAI: GPT-6 Luna DecisionsGPT-6 Luna Decisions is GPT-6 Luna (/openai/gpt-6-luna) served through OpenAI's Decisions API. Instead of generating text, it reads the content passed…by OpenAI · 2026年10月6日1.1M 上下文$0.1 输入$0 输出

SpaceXAI: Grok Imagine Video 1.5 LiteGrok Imagine Video 1.5 Lite is a faster, lower-cost video generation model from SpaceXAI, distilled from Grok Imagine Video 1.5 (/x-ai/grok-imagine-vi…by xAI · 2026年10月6日— 上下文免费输入免费输出

Google: Nano Banana 2.1Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pr…by Google · 2026年10月6日66K 上下文$1.5 输入$7.5 输出

Mistral: Mistral Large 4Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a…by Mistral · 2026年10月6日1M 上下文$0.68 输入$2.09 输出

Tencent: Hy Image 3.5 PreviewHy Image 3.5 Preview is a unified image generation and editing model from Tencent. It handles text-to-image, image-to-image, and multi-turn editing th…by 腾讯 · 2026年10月5日100K 上下文$1.60 / 百万图像 token 输入— 输出

inclusionAI: Ling 3.1 FlashLing 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.by InclusionAI · 2026年10月2日262K 上下文$0.075 输入$0.225 输出

ByteDance Seed: Seedream 5.0 FlashSeedream 5.0 Flash is an image generation and editing model from ByteDance Seed. It is the fast, cost-efficient tier of the Seedream 5.0 family, suite…by ByteDance Seed · 2026年10月1日— 上下文$4.31 / 百万图像 token 输入— 输出