MODEL DIRECTORY
AI Model Directory
Context length, max output, modalities, reasoning support and official API pricing for Claude, GPT, Gemini, DeepSeek, Qwen and other major AI models, alongside the lowest AI gateway price. Updated continuously.
618Models
77Providers
140Relay sites
Updated 2026-11-08 08:15 (UTC+8)618 models foundPrices in USD per 1M tokens; relay prices and ≈ are converted from CNY at today's rate
| Model | Provider | Type | Relays | Context | Max output | Input | Output | Capabilities | Price (input / output) | Details | ||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
Sonar Prosonar-pro | Perplexity | Text | - | 200K | 8.2K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: Supported | 7.6 | Official$3 / $15LowestNo price | 2024-01-01 | |
Deeper Sonar search model with broader retrieval and stronger synthesis Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Sonar Reasoning Prosonar-reasoning-pro | Perplexity | Text | - | 128K | 4.1K | Text: SupportedImage: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: Not supportedJSON: UnknownTemperature: Supported | 11.8 | Official$2 / $8LowestNo price | 2024-01-01 | |
Web-grounded Sonar for multi-step research questions that need cited reasoning Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
SOLAR 10.7B Instruct v1.0solar-10.7b-instruct-v1.0 | Upstage | Text | - | 4.1K | 4.1K | Text: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2023-12-12 | |
Upstage depth-upscaled 10.7B instruction model for single-turn chat Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Mistral Embedmistral-embed | Mistral | Text | - | 8K | 3.1K | Text: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: Not supported | - | Official$0.1 / $0LowestNo price | 2023-12-11 | |
Embedding model for semantic search, retrieval, clustering, and ranking pipelines Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Mixtral 8x7B Instruct v0.1mixtral-8x7b-instruct-v0.1 | Mistral | Text | - | 32.8K | 32.8K | Text: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2023-12-11 | |
Open sparse mixture-of-experts Mistral instruction model Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
MythoMax L2 13Bmythomax-l2-13b | 格里菲 | Text | - | 4.1K | 3.2K | Text: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2023-08-10 | |
Llama 2 merge combining MythoLogic and Huginn for creative writing and roleplay Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Weaver (alpha)weaver | 曼瑟 | Text | - | 8K | 6K | Text: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: Supported | - | OfficialNo priceLowestNo price | 2023-08-02 | |
General-purpose chat model for instruction following, writing, and analysis Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
ReMM SLERP 13Bremm-slerp-l2-13b | 恩迪95 | Text | - | 6.1K | 5.5K | Text: Supported | Text: Supported | Reason: Not supportedTools: Not supportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowestNo price | 2023-07-22 | |
Open-weight instruction model for adaptable chat and self-hosted production workloads Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: Not supportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
gemini-3-pro-image-preview (nano-banana-pro)gemini-3-pro-image-preview-nano-banana-pro | Text | - | - | - | - | Text: Supported | Reason: UnknownTools: UnknownJSON: UnknownTemperature: Unknown | - | OfficialNo priceLowestNo price | - | ||
Gemini 3 Pro Image Preview is Google's image model for image generation and editing workflows. Use it to create visual content and make image adjustments. Basics
Limits
InputText: Not supportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Unknown OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: UnknownTool call: UnknownStructured output: UnknownTemperature: Unknown Pricing
| ||||||||||||
gemini-3-pro-image-preview-2k (nano-banana-pro)gemini-3-pro-image-preview-2k-nano-banana-pro | Text | - | - | - | - | Text: Supported | Reason: UnknownTools: UnknownJSON: UnknownTemperature: Unknown | - | OfficialNo priceLowestNo price | - | ||
This is a preview model in Google’s Gemini 3 Pro Image Preview family, with 2K and nano-banana-pro identifiers in its name. No additional confirmed capabilities or use cases are provided in the available information. Basics
Limits
InputText: Not supportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Unknown OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: UnknownTool call: UnknownStructured output: UnknownTemperature: Unknown Pricing
| ||||||||||||
gemini-3.1-flash-image-preview (nano-banana-2)gemini-3.1-flash-image-preview-nano-banana-2 | Text | - | - | - | - | Text: Supported | Reason: UnknownTools: UnknownJSON: UnknownTemperature: Unknown | - | OfficialNo priceLowestNo price | - | ||
Gemini 3.1 Flash Image Preview (nano-banana-2) is a preview release from Google. This entry provides the model’s basic identity for evaluation and integration workflows. Basics
Limits
InputText: Not supportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Unknown OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: UnknownTool call: UnknownStructured output: UnknownTemperature: Unknown Pricing
| ||||||||||||
grok-video-3grok-video-3 | xAI | Text | - | - | - | - | Text: Supported | Reason: UnknownTools: UnknownJSON: UnknownTemperature: Unknown | - | OfficialNo priceLowestNo price | - | |
Grok Video 3 is an artificial intelligence model developed by xAI. No specific capabilities, use cases, or technical specifications are provided in the available information. Basics
Limits
InputText: Not supportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Unknown OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: UnknownTool call: UnknownStructured output: UnknownTemperature: Unknown Pricing
| ||||||||||||
Hy3hy3-preview-20260421 | Tencent | Text | - | - | - | - | Text: Supported | Reason: UnknownTools: UnknownJSON: UnknownTemperature: Unknown | - | OfficialNo priceLowestNo price | - | |
Hy3 is a preview AI model developed by Tencent. Public information currently does not specify its capabilities or intended use cases, so further evaluation is recommended when more details become available. Basics
Limits
InputText: Not supportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Unknown OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: UnknownTool call: UnknownStructured output: UnknownTemperature: Unknown Pricing
| ||||||||||||
Qwen3 235B A22Bqwen-3-235b-a22b | Alibaba Cloud | Text | - | - | - | - | Text: Supported | Reason: UnknownTools: UnknownJSON: UnknownTemperature: Unknown | 9.5 | OfficialNo priceLowestNo price | - | |
Qwen3 235B A22B is a general AI model developed by Alibaba for language-focused applications, including content creation and information processing. Basics
Limits
InputText: Not supportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Unknown OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: UnknownTool call: UnknownStructured output: UnknownTemperature: Unknown Pricing
| ||||||||||||
veo-3.1-audio-1080pveo-3.1-audio-1080p | Text | - | - | - | - | Text: Supported | Reason: UnknownTools: UnknownJSON: UnknownTemperature: Unknown | - | OfficialNo priceLowestNo price | - | ||
Google Veo 3.1 Audio 1080p is a model positioned for audio and video creation workflows. Its name indicates an audio-related focus and a 1080p output specification for related content production. Basics
Limits
InputText: Not supportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Unknown OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: UnknownTool call: UnknownStructured output: UnknownTemperature: Unknown Pricing
| ||||||||||||
veo-3.1-fast-audioveo-3.1-fast-audio | Text | - | - | - | - | Text: Supported | Reason: UnknownTools: UnknownJSON: UnknownTemperature: Unknown | - | OfficialNo priceLowestNo price | - | ||
veo-3.1-fast-audio is a Google AI model whose name emphasizes fast response and an audio focus. It can be considered for AI application scenarios where efficient processing is important. Basics
Limits
InputText: Not supportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Unknown OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: UnknownTool call: UnknownStructured output: UnknownTemperature: Unknown Pricing
| ||||||||||||
happyhorse-1.0happyhorse-1.0 | Alibaba ATH | Text | - | - | - | - | Text: Supported | Reason: UnknownTools: UnknownJSON: UnknownTemperature: Unknown | - | OfficialNo priceLowestNo price | - | |
happyhorse-1.0 is an AI model released by Alibaba-ATH. The available information does not specify its capabilities, supported modalities, or intended use cases, so consult the official documentation before deployment. Basics
Limits
InputText: Not supportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Unknown OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: UnknownTool call: UnknownStructured output: UnknownTemperature: Unknown Pricing
| ||||||||||||
veo-3.1-audioveo-3.1-audio | Text | - | - | - | - | Text: Supported | Reason: UnknownTools: UnknownJSON: UnknownTemperature: Unknown | - | OfficialNo priceLowestNo price | - | ||
Google Veo 3.1 Audio is a model for exploring audio-focused AI creation and applications. It can support research into audio workflows, content ideation, and related use cases. Basics
Limits
InputText: Not supportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Unknown OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: UnknownTool call: UnknownStructured output: UnknownTemperature: Unknown Pricing
| ||||||||||||
Capabilities and limits come from public sources. “Unknown” means no reliable data yet, not “not supported”. Relay counts include only sites with a current public price, de-duplicated per site.
Data source: models.dev · OpenRouter
Intelligence scores come from the OpenRouter benchmark rankings (Intelligence Index); higher is smarter.