MyRouter — Access Every AI Model

Model Name	Provider	Type	Input ($/1M)	Output ($/1M)	Context
claude-opus-4-5-20251101 claude-opus-4-5-20251101	Anthropic	Chat	$0.0450	$0.2250	195K
claude-opus-4-6 Most intelligent model for building agents and coding	Anthropic	Chat	$0.0500	$0.2500	977K
claude-sonnet-4-5-20250929 claude-sonnet-4-5-20250929	Anthropic	Chat	$0.0270	$0.1350	195K
claude-sonnet-4-6 Our smartest model. Best for complex agents, coding, and most advanced tasks	Anthropic	Chat	$0.0300	$0.1500	977K
gemini-2.5-pro gemini-2.5-pro	Google	Chat	$0.0112	$0.0900	1024K
gemini-3-flash-preview gemini-3-flash-preview	Google	Chat	$0.005000	$0.0300	1024K
gemini-3-pro-preview gemini-3-pro-preview	Google	Chat	$0.0180	$0.1080	1024K
gemini-3.1-flash-lite-preview gemini-3.1-flash-lite-preview	Google	Chat	$0.002500	$0.0150	1024K
gemini-3.1-pro-preview gemini-3.1-pro-preview	Google	Chat	$0.0200	$0.1200	1024K
MiniMax M2.5 MiniMax M2.1 is a cutting-edge AI model designed to revolutionize how developers build software. With enhanced multi-language programming support, it excels in generating high-quality code across popular languages like Rust, Java, Golang, C++, Kotlin, Objective-C, TypeScript, and JavaScript. Key improvements include: 22% faster response times and 30% lower token consumption for efficient workflows. Seamless integration with leading development frameworks (Claude Code, Droid Factory AI, BlackBox, etc.). Full-stack development capabilities, from mobile (Android/iOS) to web and 3D interactive prototyping. Optimized performance-to-cost ratio, making AI-assisted development more accessible. Whether you're a software engineer, app developer, or tech innovator, M2.1 empowers smarter coding with industry-leading AI.	MiniMax	Chat	$0.003000	$0.0120	200K
gpt-5.1 gpt-5.1	OpenAI	Chat	$0.0112	$0.0900	391K
gpt-5.1-codex gpt-5.1-codex	OpenAI	Chat	$0.0112	$0.0900	391K
gpt-5.2 gpt-5.2	OpenAI	Chat	$0.0158	$0.1260	391K
gpt-5.2-codex gpt-5.2-codex	OpenAI	Chat	$0.0175	$0.1400	391K
gpt-5.3-chat-latest gpt-5.3-chat-latest	OpenAI	Chat	$0.0175	$0.1400	125K
gpt-5.3-codex gpt-5.3-codex	OpenAI	Chat	$0.0175	$0.1400	391K
gpt-5.4 gpt-5.4	OpenAI	Chat	$0.0250	$0.1500	1025K
gpt-5.4-pro gpt-5.4-pro	OpenAI	Chat	$0.3000	$1.80	1025K
Qwen3 Coder Next FP8 Qwen3-Coder-Next is an open-weight language model specifically engineered for coding agents and local development environments. This highly efficient model delivers exceptional performance with only 3B activated parameters out of 80B total parameters, achieving results comparable to models with 10-20x more active parameters while maintaining remarkable cost-effectiveness for agent deployment. Through its sophisticated training methodology, Qwen3-Coder-Next excels in advanced agentic capabilities including long-horizon reasoning, complex tool usage, and robust recovery from execution failures, ensuring reliable performance across dynamic coding tasks. The model's versatility is further enhanced by its 256k context length and adaptability to various scaffold templates, enabling seamless integration with diverse CLI/IDE platforms such as Claude Code, Qwen Code, Qoder, Kilo, Trae, and Cline, making it an ideal solution for comprehensive development environments.	Qwen	Chat	$0.002000	$0.0150	256K
GLM-5 GLM-5 is an open-source foundation model engineered for complex system engineering and long-horizon Agent tasks, delivering reliable productivity for top-tier programmers. Transcending the boundary from "writing code" to "building systems," it moves beyond traditional snippet generation to offer senior-architect-level planning and execution capabilities. By rejecting the "frontend-heavy, logic-light" approach, GLM-5 demonstrates exceptional reasoning and self-healing abilities in backend refactoring, complex algorithm implementation, and deep debugging—autonomously analyzing logs and iteratively fixing persistent bugs until the system runs. As the first open-source model featuring Opus-class style and system engineering depth, GLM-5 provides extreme logic density alongside the freedom of local deployment and high cost-effectiveness, making it the ideal choice for large-scale backend development and automated Agent construction.	Zai-org	Chat	$0.0100	$0.0320	200K
GLM-OCR GLM-OCR is a lightweight professional OCR model with only 0.9B parameters, achieving SOTA performance with a score of 94.62 on OmniDocBench V1.5. Optimized for real-world business scenarios, it delivers high-precision recognition for handwritten text, stamps, and code documentation. The model supports directly rendering complex tables into HTML code and extracting structured data from IDs and receipts into standard JSON format, enabling high-accuracy document parsing with minimal resource consumption.	Zai-org	Chat	$300.00	$300.00	31.3K
Nano Banana Image Edit Google Gemini 系列强调多模态理解与指令遵循，兼顾速度与成本，适合生产级调用。Gemini 2.5 Flash 侧重低延迟与性价比，在实时场景更友好。文生图可根据提示词生成高质量图片，适合海报、素材、插画与产品概念图。即时推理 API，性能稳定，无需等待，价格亲民	Google	Images	$0.0400	$0.0400	—
Nano Banana 2 (image edit) Gemini 3.1 Flash Image 主打低延迟与高一致性生成，适合批量出图与交互式创作；对复杂指令的遵循度强，能稳定处理多主体、细节材质与光影关系，并在常见商业风格（电商、海报、插画、写实）间快速切换；同时擅长把“要求清单”落到画面结构与元素布局上，成片率高。支持极速推理 API，性能稳定，无需等待，性价比超高。	Google	Images	$0.0450	$0.0450	—
Nano Banana 2 (text to image) Gemini 3.1 Flash Image 主打低延迟与高一致性生成，适合批量出图与交互式创作；对复杂指令的遵循度强，能稳定处理多主体、细节材质与光影关系，并在常见商业风格（电商、海报、插画、写实）间快速切换；同时擅长把“要求清单”落到画面结构与元素布局上，成片率高。支持极速推理 API，性能稳定，无需等待，性价比超高。	Google	Images	$0.0450	$0.0450	—
Nano Banana Native Protocol Google Gemini 系列强调多模态理解与指令遵循，兼顾速度与成本，适合生产级调用。该系列面向生产级调用，强调稳定性与可控输出。文生图可根据提示词生成高质量图片，适合海报、素材、插画与产品概念图。即时推理 API，性能稳定，无需等待，价格亲民	Google	Images	$0.0400	$0.0400	—
Nano Banana Pro Image Edit Google Gemini 系列强调多模态理解与指令遵循，兼顾速度与成本，适合生产级调用。该系列面向生产级调用，强调稳定性与可控输出。文生图可根据提示词生成高质量图片，适合海报、素材、插画与产品概念图。即时推理 API，性能稳定，无需等待，价格亲民	Google	Images	$0.1139	$0.1139	—
Nano Banana Pro Text to Image Google Gemini 系列强调多模态理解与指令遵循，兼顾速度与成本，适合生产级调用。该系列面向生产级调用，强调稳定性与可控输出。文生图可根据提示词生成高质量图片，适合海报、素材、插画与产品概念图。即时推理 API，性能稳定，无需等待，价格亲民	Google	Images	$0.1139	$0.1139	—
Nano Banana Text to Image Google Gemini 系列强调多模态理解与指令遵循，兼顾速度与成本，适合生产级调用。Gemini 2.5 Flash 侧重低延迟与性价比，在实时场景更友好。文生图可根据提示词生成高质量图片，适合海报、素材、插画与产品概念图。即时推理 API，性能稳定，无需等待，价格亲民	Google	Images	$0.0400	$0.0400	—

claude-opus-4-5-20251101

Anthropic · Chat

claude-opus-4-5-20251101

Input: $0.0450
Output: $0.2250
Context: 195K

claude-opus-4-6

Anthropic · Chat

Most intelligent model for building agents and coding

Input: $0.0500
Output: $0.2500
Context: 977K

claude-sonnet-4-5-20250929

Anthropic · Chat

claude-sonnet-4-5-20250929

Input: $0.0270
Output: $0.1350
Context: 195K

claude-sonnet-4-6

Anthropic · Chat

Our smartest model. Best for complex agents, coding, and most advanced tasks

Input: $0.0300
Output: $0.1500
Context: 977K

gemini-2.5-pro

Google · Chat

gemini-2.5-pro

Input: $0.0112
Output: $0.0900
Context: 1024K

gemini-3-flash-preview

Google · Chat

gemini-3-flash-preview

Input: $0.005000
Output: $0.0300
Context: 1024K

gemini-3-pro-preview

Google · Chat

gemini-3-pro-preview

Input: $0.0180
Output: $0.1080
Context: 1024K

gemini-3.1-flash-lite-preview

Google · Chat

gemini-3.1-flash-lite-preview

Input: $0.002500
Output: $0.0150
Context: 1024K

gemini-3.1-pro-preview

Google · Chat

gemini-3.1-pro-preview

Input: $0.0200
Output: $0.1200
Context: 1024K

MiniMax M2.5

MiniMax · Chat

MiniMax M2.1 is a cutting-edge AI model designed to revolutionize how developers build software. With enhanced multi-language programming support, it excels in generating high-quality code across popular languages like Rust, Java, Golang, C++, Kotlin, Objective-C, TypeScript, and JavaScript. Key improvements include: 22% faster response times and 30% lower token consumption for efficient workflows. Seamless integration with leading development frameworks (Claude Code, Droid Factory AI, BlackBox, etc.). Full-stack development capabilities, from mobile (Android/iOS) to web and 3D interactive prototyping. Optimized performance-to-cost ratio, making AI-assisted development more accessible. Whether you're a software engineer, app developer, or tech innovator, M2.1 empowers smarter coding with industry-leading AI.

Input: $0.003000
Output: $0.0120
Context: 200K

gpt-5.1

OpenAI · Chat

gpt-5.1

Input: $0.0112
Output: $0.0900
Context: 391K

gpt-5.1-codex

OpenAI · Chat

gpt-5.1-codex

Input: $0.0112
Output: $0.0900
Context: 391K

gpt-5.2

OpenAI · Chat

gpt-5.2

Input: $0.0158
Output: $0.1260
Context: 391K

gpt-5.2-codex

OpenAI · Chat

gpt-5.2-codex

Input: $0.0175
Output: $0.1400
Context: 391K

gpt-5.3-chat-latest

OpenAI · Chat

gpt-5.3-chat-latest

Input: $0.0175
Output: $0.1400
Context: 125K

gpt-5.3-codex

OpenAI · Chat

gpt-5.3-codex

Input: $0.0175
Output: $0.1400
Context: 391K

gpt-5.4

OpenAI · Chat

gpt-5.4

Input: $0.0250
Output: $0.1500
Context: 1025K

gpt-5.4-pro

OpenAI · Chat

gpt-5.4-pro

Input: $0.3000
Output: $1.80
Context: 1025K

Qwen3 Coder Next FP8

Qwen · Chat

Qwen3-Coder-Next is an open-weight language model specifically engineered for coding agents and local development environments. This highly efficient model delivers exceptional performance with only 3B activated parameters out of 80B total parameters, achieving results comparable to models with 10-20x more active parameters while maintaining remarkable cost-effectiveness for agent deployment. Through its sophisticated training methodology, Qwen3-Coder-Next excels in advanced agentic capabilities including long-horizon reasoning, complex tool usage, and robust recovery from execution failures, ensuring reliable performance across dynamic coding tasks. The model's versatility is further enhanced by its 256k context length and adaptability to various scaffold templates, enabling seamless integration with diverse CLI/IDE platforms such as Claude Code, Qwen Code, Qoder, Kilo, Trae, and Cline, making it an ideal solution for comprehensive development environments.

Input: $0.002000
Output: $0.0150
Context: 256K

GLM-5

Zai-org · Chat

GLM-5 is an open-source foundation model engineered for complex system engineering and long-horizon Agent tasks, delivering reliable productivity for top-tier programmers. Transcending the boundary from "writing code" to "building systems," it moves beyond traditional snippet generation to offer senior-architect-level planning and execution capabilities. By rejecting the "frontend-heavy, logic-light" approach, GLM-5 demonstrates exceptional reasoning and self-healing abilities in backend refactoring, complex algorithm implementation, and deep debugging—autonomously analyzing logs and iteratively fixing persistent bugs until the system runs. As the first open-source model featuring Opus-class style and system engineering depth, GLM-5 provides extreme logic density alongside the freedom of local deployment and high cost-effectiveness, making it the ideal choice for large-scale backend development and automated Agent construction.

Input: $0.0100
Output: $0.0320
Context: 200K

GLM-OCR

Zai-org · Chat

GLM-OCR is a lightweight professional OCR model with only 0.9B parameters, achieving SOTA performance with a score of 94.62 on OmniDocBench V1.5. Optimized for real-world business scenarios, it delivers high-precision recognition for handwritten text, stamps, and code documentation. The model supports directly rendering complex tables into HTML code and extracting structured data from IDs and receipts into standard JSON format, enabling high-accuracy document parsing with minimal resource consumption.

Input: $300.00
Output: $300.00
Context: 31.3K

Nano Banana Image Edit

Google · Images

Google Gemini 系列强调多模态理解与指令遵循，兼顾速度与成本，适合生产级调用。Gemini 2.5 Flash 侧重低延迟与性价比，在实时场景更友好。文生图可根据提示词生成高质量图片，适合海报、素材、插画与产品概念图。即时推理 API，性能稳定，无需等待，价格亲民

Input: $0.0400
Output: $0.0400
Context: —

Nano Banana 2 (image edit)

Google · Images

Gemini 3.1 Flash Image 主打低延迟与高一致性生成，适合批量出图与交互式创作；对复杂指令的遵循度强，能稳定处理多主体、细节材质与光影关系，并在常见商业风格（电商、海报、插画、写实）间快速切换；同时擅长把“要求清单”落到画面结构与元素布局上，成片率高。支持极速推理 API，性能稳定，无需等待，性价比超高。

Input: $0.0450
Output: $0.0450
Context: —

Nano Banana 2 (text to image)

Google · Images

Gemini 3.1 Flash Image 主打低延迟与高一致性生成，适合批量出图与交互式创作；对复杂指令的遵循度强，能稳定处理多主体、细节材质与光影关系，并在常见商业风格（电商、海报、插画、写实）间快速切换；同时擅长把“要求清单”落到画面结构与元素布局上，成片率高。支持极速推理 API，性能稳定，无需等待，性价比超高。

Input: $0.0450
Output: $0.0450
Context: —

Nano Banana Native Protocol

Google · Images

Google Gemini 系列强调多模态理解与指令遵循，兼顾速度与成本，适合生产级调用。该系列面向生产级调用，强调稳定性与可控输出。文生图可根据提示词生成高质量图片，适合海报、素材、插画与产品概念图。即时推理 API，性能稳定，无需等待，价格亲民

Input: $0.0400
Output: $0.0400
Context: —

Nano Banana Pro Image Edit

Google · Images

Google Gemini 系列强调多模态理解与指令遵循，兼顾速度与成本，适合生产级调用。该系列面向生产级调用，强调稳定性与可控输出。文生图可根据提示词生成高质量图片，适合海报、素材、插画与产品概念图。即时推理 API，性能稳定，无需等待，价格亲民

Input: $0.1139
Output: $0.1139
Context: —

Nano Banana Pro Text to Image

Google · Images

Google Gemini 系列强调多模态理解与指令遵循，兼顾速度与成本，适合生产级调用。该系列面向生产级调用，强调稳定性与可控输出。文生图可根据提示词生成高质量图片，适合海报、素材、插画与产品概念图。即时推理 API，性能稳定，无需等待，价格亲民

Input: $0.1139
Output: $0.1139
Context: —

Nano Banana Text to Image

Google · Images

Google Gemini 系列强调多模态理解与指令遵循，兼顾速度与成本，适合生产级调用。Gemini 2.5 Flash 侧重低延迟与性价比，在实时场景更友好。文生图可根据提示词生成高质量图片，适合海报、素材、插画与产品概念图。即时推理 API，性能稳定，无需等待，价格亲民

Input: $0.0400
Output: $0.0400
Context: —

Models