> ## Documentation Index > Fetch the complete documentation index at: https://docs.apiyi.com/llms.txt > Use this file to discover all available pages before exploring further. # Model Pricing Directory > Live pricing for all available models on APIYI: input/output/cache prices, endpoints, and groups. Auto-updated. export const MODELS = [{ "n": "MiniMax-M2.1", "b": "usage", "i": "$0.3", "o": "$1.2", "c": "—", "v": "MiniMax", "a": "minimax", "t": 0 }, { "n": "MiniMax-M2.5", "b": "usage", "i": "$0.3", "o": "$1.2", "c": "—", "v": "MiniMax", "a": "minimax", "t": 0 }, { "n": "MiniMax-M2.5-lightning", "b": "usage", "i": "$0.3", "o": "$2.4", "c": "—", "v": "MiniMax", "a": "minimax", "t": 0 }, { "n": "MiniMax-M2.7", "b": "usage", "i": "$0.3", "o": "$1.2", "c": "—", "v": "MiniMax", "a": "minimax", "t": 0 }, { "n": "MiniMax-M2.7-highspeed", "b": "usage", "i": "$0.6", "o": "$2.4", "c": "—", "v": "MiniMax", "a": "minimax", "t": 0 }, { "n": "MiniMax-M3", "b": "usage", "i": "$0.3", "o": "$1.2", "c": "$0.06", "v": "MiniMax", "a": "minimax", "t": 1 }, { "n": "bge-reranker-v2-m3", "b": "usage", "i": "$0.01", "o": "$0.01", "c": "—", "v": "BAAI", "a": "baai", "t": 0 }, { "n": "chat-latest", "b": "usage", "i": "$5", "o": "$30", "c": "$0.5", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "chatgpt-image-latest", "b": "usage", "i": "$5", "o": "$32", "c": "$1.25", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "claude-fable-5", "b": "usage", "i": "$10", "o": "$50", "c": "$1", "v": "Anthropic", "a": "anthropic", "t": 0 }, { "n": "claude-haiku-4-5-20251001", "b": "usage", "i": "$1", "o": "$5", "c": "$0.1", "v": "Anthropic", "a": "anthropic", "t": 0 }, { "n": "claude-haiku-4-5-20251001-thinking", "b": "usage", "i": "$1", "o": "$5", "c": "$0.1", "v": "Anthropic", "a": "anthropic", "t": 0 }, { "n": "claude-opus-4-1-20250805", "b": "usage", "i": "$15", "o": "$75", "c": "$1.5", "v": "Anthropic", "a": "anthropic", "t": 0 }, { "n": "claude-opus-4-1-20250805-thinking", "b": "usage", "i": "$15", "o": "$75", "c": "$1.5", "v": "Anthropic", "a": "anthropic", "t": 0 }, { "n": "claude-opus-4-5-20251101", "b": "usage", "i": "$5", "o": "$25", "c": "$0.5", "v": "Anthropic", "a": "anthropic", "t": 0 }, { "n": "claude-opus-4-5-20251101-thinking", "b": "usage", "i": "$5", "o": "$25", "c": "$0.5", "v": "Anthropic", "a": "anthropic", "t": 0 }, { "n": "claude-opus-4-6", "b": "usage", "i": "$5", "o": "$25", "c": "$0.5", "v": "Anthropic", "a": "anthropic", "t": 0 }, { "n": "claude-opus-4-6-thinking", "b": "usage", "i": "$5", "o": "$25", "c": "$0.5", "v": "Anthropic", "a": "anthropic", "t": 0 }, { "n": "claude-opus-4-7", "b": "usage", "i": "$5", "o": "$25", "c": "$0.5", "v": "Anthropic", "a": "anthropic", "t": 0 }, { "n": "claude-opus-4-7-thinking", "b": "usage", "i": "$5", "o": "$25", "c": "$0.5", "v": "Anthropic", "a": "anthropic", "t": 0 }, { "n": "claude-opus-4-8", "b": "usage", "i": "$5", "o": "$25", "c": "$0.5", "v": "Anthropic", "a": "anthropic", "t": 0 }, { "n": "claude-opus-4-8-thinking", "b": "usage", "i": "$5", "o": "$25", "c": "$0.5", "v": "Anthropic", "a": "anthropic", "t": 0 }, { "n": "claude-sonnet-4-20250514", "b": "usage", "i": "$3", "o": "$15", "c": "$0.3", "v": "Anthropic", "a": "anthropic", "t": 0 }, { "n": "claude-sonnet-4-20250514-thinking", "b": "usage", "i": "$3", "o": "$15", "c": "$0.3", "v": "Anthropic", "a": "anthropic", "t": 0 }, { "n": "claude-sonnet-4-5-20250929", "b": "usage", "i": "$3", "o": "$15", "c": "$0.3", "v": "Anthropic", "a": "anthropic", "t": 0 }, { "n": "claude-sonnet-4-5-20250929-thinking", "b": "usage", "i": "$3", "o": "$15", "c": "$0.3", "v": "Anthropic", "a": "anthropic", "t": 0 }, { "n": "claude-sonnet-4-6", "b": "usage", "i": "$3", "o": "$15", "c": "$0.3", "v": "Anthropic", "a": "anthropic", "t": 0 }, { "n": "claude-sonnet-4-6-thinking", "b": "usage", "i": "$3", "o": "$15", "c": "$0.3", "v": "Anthropic", "a": "anthropic", "t": 0 }, { "n": "claude-sonnet-5", "b": "usage", "i": "$2", "o": "$10", "c": "$0.2", "v": "Anthropic", "a": "anthropic", "t": 0 }, { "n": "claude-sonnet-5-thinking", "b": "usage", "i": "$2", "o": "$10", "c": "$0.2", "v": "Anthropic", "a": "anthropic", "t": 0 }, { "n": "dall-e-3", "b": "usage", "i": "$40", "o": "$40", "c": "—", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "deepseek-chat", "b": "usage", "i": "$0.25", "o": "$1", "c": "$0.0625", "v": "DeepSeek", "a": "deepseek", "t": 0 }, { "n": "deepseek-ocr", "b": "usage", "i": "$0.3", "o": "$0.6", "c": "—", "v": "DeepSeek", "a": "deepseek", "t": 0 }, { "n": "deepseek-r1", "b": "usage", "i": "$0.57", "o": "$2.28", "c": "$0.1425", "v": "DeepSeek", "a": "deepseek", "t": 0 }, { "n": "deepseek-r1-0528", "b": "usage", "i": "$0.57", "o": "$2.28", "c": "—", "v": "DeepSeek", "a": "deepseek", "t": 0 }, { "n": "deepseek-r1-250528", "b": "usage", "i": "$0.57", "o": "$2.28", "c": "—", "v": "DeepSeek", "a": "deepseek", "t": 0 }, { "n": "deepseek-reasoner", "b": "usage", "i": "$0.5", "o": "$2", "c": "$0.125", "v": "DeepSeek", "a": "deepseek", "t": 0 }, { "n": "deepseek-v3", "b": "usage", "i": "$0.286", "o": "$1.144", "c": "$0.0715", "v": "DeepSeek", "a": "deepseek", "t": 0 }, { "n": "deepseek-v3-0324", "b": "usage", "i": "$0.25", "o": "$1", "c": "$0.0625", "v": "DeepSeek", "a": "deepseek", "t": 0 }, { "n": "deepseek-v3-1-250821", "b": "usage", "i": "$0.5", "o": "$1.5", "c": "—", "v": "DeepSeek", "a": "deepseek", "t": 0 }, { "n": "deepseek-v3-20250324", "b": "usage", "i": "$0.25", "o": "$1", "c": "—", "v": "DeepSeek", "a": "deepseek", "t": 0 }, { "n": "deepseek-v3-250324", "b": "usage", "i": "$0.25", "o": "$1", "c": "—", "v": "DeepSeek", "a": "deepseek", "t": 0 }, { "n": "deepseek-v3.1", "b": "usage", "i": "$0.5", "o": "$1.5", "c": "—", "v": "DeepSeek", "a": "deepseek", "t": 0 }, { "n": "deepseek-v3.1-terminus", "b": "usage", "i": "$0.5", "o": "$2", "c": "—", "v": "DeepSeek", "a": "deepseek", "t": 0 }, { "n": "deepseek-v3.2", "b": "usage", "i": "$0.28", "o": "$0.42", "c": "—", "v": "DeepSeek", "a": "deepseek", "t": 0 }, { "n": "deepseek-v3.2-exp", "b": "usage", "i": "$0.28", "o": "$0.42", "c": "—", "v": "DeepSeek", "a": "deepseek", "t": 0 }, { "n": "deepseek-v4-flash", "b": "usage", "i": "$0.14", "o": "$0.28", "c": "$0.0028", "v": "DeepSeek", "a": "deepseek", "t": 0 }, { "n": "deepseek-v4-pro", "b": "usage", "i": "$0.435", "o": "$0.87", "c": "$0.003625", "v": "DeepSeek", "a": "deepseek", "t": 0 }, { "n": "dola-seed-2-1-turbo-260628", "b": "usage", "i": "$0.5", "o": "$2.5", "c": "$0.1", "v": "ByteDance", "a": "bytedance", "t": 0 }, { "n": "doubao-seed-1-6-250615", "b": "usage", "i": "$0.1", "o": "$1", "c": "—", "v": "ByteDance", "a": "bytedance", "t": 0 }, { "n": "doubao-seed-1-6-251015", "b": "usage", "i": "$0.114", "o": "$0.285", "c": "—", "v": "ByteDance", "a": "bytedance", "t": 0 }, { "n": "doubao-seed-1-8-251228", "b": "usage", "i": "$0.25", "o": "$2", "c": "—", "v": "ByteDance", "a": "bytedance", "t": 0 }, { "n": "doubao-seedance-2-0-260128", "b": "usage", "i": "$46", "o": "$46", "c": "—", "v": "ByteDance", "a": "bytedance", "t": 0 }, { "n": "doubao-seedance-2-0-fast-260128", "b": "usage", "i": "$37", "o": "$37", "c": "—", "v": "ByteDance", "a": "bytedance", "t": 0 }, { "n": "doubao-seedance-2-0-mini-260615", "b": "usage", "i": "$23", "o": "$23", "c": "—", "v": "ByteDance", "a": "bytedance", "t": 0 }, { "n": "flux-2-flex", "b": "per-call", "i": "$0.06/call", "o": "—", "c": "—", "v": "Black Forest Labs", "a": "black-forest-labs", "t": 0 }, { "n": "flux-2-klein-4b", "b": "per-call", "i": "$0.01/call", "o": "—", "c": "—", "v": "Black Forest Labs", "a": "black-forest-labs", "t": 0 }, { "n": "flux-2-klein-9b", "b": "per-call", "i": "$0.01/call", "o": "—", "c": "—", "v": "Black Forest Labs", "a": "black-forest-labs", "t": 0 }, { "n": "flux-2-max", "b": "per-call", "i": "$0.07/call", "o": "—", "c": "—", "v": "Black Forest Labs", "a": "black-forest-labs", "t": 0 }, { "n": "flux-2-pro", "b": "per-call", "i": "$0.03/call", "o": "—", "c": "—", "v": "Black Forest Labs", "a": "black-forest-labs", "t": 0 }, { "n": "flux-dev", "b": "per-call", "i": "$0.02/call", "o": "—", "c": "—", "v": "Black Forest Labs", "a": "black-forest-labs", "t": 0 }, { "n": "flux-kontext-max", "b": "per-call", "i": "$0.07/call", "o": "—", "c": "—", "v": "Black Forest Labs", "a": "black-forest-labs", "t": 0 }, { "n": "flux-kontext-pro", "b": "per-call", "i": "$0.035/call", "o": "—", "c": "—", "v": "Black Forest Labs", "a": "black-forest-labs", "t": 0 }, { "n": "flux-pro", "b": "per-call", "i": "$0.04/call", "o": "—", "c": "—", "v": "Black Forest Labs", "a": "black-forest-labs", "t": 0 }, { "n": "flux-pro-1.1", "b": "per-call", "i": "$0.035/call", "o": "—", "c": "—", "v": "Black Forest Labs", "a": "black-forest-labs", "t": 0 }, { "n": "flux-pro-1.1-ultra", "b": "per-call", "i": "$0.05/call", "o": "—", "c": "—", "v": "Black Forest Labs", "a": "black-forest-labs", "t": 0 }, { "n": "gemini-2.5-flash", "b": "usage", "i": "$0.3", "o": "$2.4", "c": "$0.03", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-2.5-flash-image", "b": "per-call", "i": "$0.02/call", "o": "—", "c": "—", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-2.5-flash-lite", "b": "usage", "i": "$0.1", "o": "$0.4", "c": "$0.01", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-2.5-pro", "b": "usage", "i": "$1.25", "o": "$10", "c": "$0.125", "v": "Google", "a": "google", "t": 1 }, { "n": "gemini-2.5-pro-preview-tts", "b": "usage", "i": "$1", "o": "$20", "c": "$0.1", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-3-flash-preview", "b": "usage", "i": "$0.44", "o": "$2.64", "c": "$0.044", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-3-flash-preview-thinking", "b": "usage", "i": "$0.44", "o": "$2.64", "c": "$0.044", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-3-pro-image", "b": "per-call", "i": "$0.09/call", "o": "—", "c": "—", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-3-pro-image-preview", "b": "per-call", "i": "$0.09/call", "o": "—", "c": "—", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-3-pro-image-preview-1k", "b": "per-call", "i": "$0.09/call", "o": "—", "c": "—", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-3-pro-image-preview-2k", "b": "per-call", "i": "$0.09/call", "o": "—", "c": "—", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-3-pro-image-preview-4k", "b": "per-call", "i": "$0.09/call", "o": "—", "c": "—", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-3-pro-preview", "b": "usage", "i": "$1.8", "o": "$10.8", "c": "$0.18", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-3.1-flash-image", "b": "per-call", "i": "$0.055/call", "o": "—", "c": "—", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-3.1-flash-image-4k", "b": "per-call", "i": "$0.055/call", "o": "—", "c": "—", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-3.1-flash-image-preview", "b": "per-call", "i": "$0.055/call", "o": "—", "c": "—", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-3.1-flash-image-preview-4k", "b": "per-call", "i": "$0.055/call", "o": "—", "c": "—", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-3.1-flash-lite", "b": "usage", "i": "$0.25", "o": "$1.5", "c": "$0.025", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-3.1-flash-lite-image", "b": "per-call", "i": "$0.025/call", "o": "—", "c": "—", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-3.1-flash-lite-preview", "b": "usage", "i": "$0.25", "o": "$1.5", "c": "$0.025", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-3.1-pro-preview", "b": "usage", "i": "$1.8", "o": "$10.8", "c": "$0.18", "v": "Google", "a": "google", "t": 1 }, { "n": "gemini-3.1-pro-preview-customtools", "b": "usage", "i": "$1.8", "o": "$10.8", "c": "$0.18", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-3.5-flash", "b": "usage", "i": "$1.5", "o": "$9", "c": "$0.15", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-3.5-flash-lite", "b": "usage", "i": "$0.3", "o": "$2.4999", "c": "$0.03", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-3.6-flash", "b": "usage", "i": "$1.5", "o": "$7.5", "c": "$0.15", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-embedding-001", "b": "usage", "i": "$0.15", "o": "$0.45", "c": "—", "v": "Google", "a": "google", "t": 0 }, { "n": "gemini-embedding-2-preview", "b": "usage", "i": "$0.3", "o": "$0.9", "c": "—", "v": "Google", "a": "google", "t": 0 }, { "n": "glm-4.5", "b": "usage", "i": "$0.5", "o": "$2", "c": "$0.05", "v": "Zhipu", "a": "zhipu", "t": 0 }, { "n": "glm-4.5-air", "b": "usage", "i": "$0.2", "o": "$1", "c": "$0.02", "v": "Zhipu", "a": "zhipu", "t": 0 }, { "n": "glm-4.5v", "b": "usage", "i": "$0.5", "o": "$1.5", "c": "$0.05", "v": "Zhipu", "a": "zhipu", "t": 0 }, { "n": "glm-4.6", "b": "usage", "i": "$0.5", "o": "$2", "c": "$0.05", "v": "Zhipu", "a": "zhipu", "t": 0 }, { "n": "glm-4.7", "b": "usage", "i": "$0.6", "o": "$2.16", "c": "$0.06", "v": "Zhipu", "a": "zhipu", "t": 0 }, { "n": "glm-5", "b": "usage", "i": "$0.56", "o": "$2.52", "c": "$0.056", "v": "Zhipu", "a": "zhipu", "t": 1 }, { "n": "glm-5.1", "b": "usage", "i": "$0.84", "o": "$3.36", "c": "$0.084", "v": "Zhipu", "a": "zhipu", "t": 1 }, { "n": "glm-5.2", "b": "usage", "i": "$1.142", "o": "$3.997", "c": "$0.2284", "v": "Zhipu", "a": "zhipu", "t": 0 }, { "n": "gpt-3.5-turbo", "b": "usage", "i": "$0.5", "o": "$1.5", "c": "$0.05", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-3.5-turbo-0125", "b": "usage", "i": "$0.5", "o": "$1.5", "c": "$0.05", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-3.5-turbo-0613", "b": "usage", "i": "$1.5", "o": "$1.95", "c": "$0.15", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-3.5-turbo-1106", "b": "usage", "i": "$1", "o": "$2", "c": "$0.1", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-3.5-turbo-16k", "b": "usage", "i": "$3", "o": "$3.9", "c": "$0.3", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-3.5-turbo-16k-0613", "b": "usage", "i": "$3", "o": "$3.9", "c": "$0.3", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-4-32k", "b": "usage", "i": "$60", "o": "$120", "c": "$6", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-4.1", "b": "usage", "i": "$2", "o": "$8", "c": "$0.5", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-4.1-2025-04-14", "b": "usage", "i": "$2", "o": "$8", "c": "$0.5", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-4.1-mini", "b": "usage", "i": "$0.4", "o": "$1.6", "c": "$0.1", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-4.1-mini-2025-04-14", "b": "usage", "i": "$0.4", "o": "$1.6", "c": "$0.1", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-4.1-nano", "b": "usage", "i": "$0.1", "o": "$0.4", "c": "$0.025", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-4.1-nano-2025-04-14", "b": "usage", "i": "$0.1", "o": "$0.4", "c": "$0.025", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-4o", "b": "usage", "i": "$2.5", "o": "$10", "c": "$1.25", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-4o-2024-05-13", "b": "usage", "i": "$5", "o": "$15", "c": "$2.5", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-4o-2024-08-06", "b": "usage", "i": "$2.5", "o": "$10", "c": "$1.25", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-4o-2024-11-20", "b": "usage", "i": "$2.5", "o": "$10", "c": "$1.25", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-4o-mini", "b": "usage", "i": "$0.15", "o": "$0.6", "c": "$0.075", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-4o-mini-2024-07-18", "b": "usage", "i": "$0.15", "o": "$0.6", "c": "$0.075", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-4o-mini-audio-preview", "b": "usage", "i": "$2", "o": "$8", "c": "$1", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-4o-mini-transcribe", "b": "usage", "i": "$1.5", "o": "$6", "c": "$0.75", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-4o-transcribe", "b": "usage", "i": "$8", "o": "$16", "c": "$4", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5", "b": "usage", "i": "$1.25", "o": "$10", "c": "$0.125", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5-2025-08-07", "b": "usage", "i": "$1.25", "o": "$10", "c": "$0.125", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5-chat-latest", "b": "usage", "i": "$1.25", "o": "$10", "c": "$0.125", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5-codex", "b": "usage", "i": "$1.25", "o": "$10", "c": "$0.125", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5-mini", "b": "usage", "i": "$0.25", "o": "$2", "c": "$0.025", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5-mini-2025-08-07", "b": "usage", "i": "$0.25", "o": "$2", "c": "$0.025", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5-nano", "b": "usage", "i": "$0.05", "o": "$0.4", "c": "$0.005", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5-nano-2025-08-07", "b": "usage", "i": "$0.05", "o": "$0.4", "c": "$0.005", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5-pro", "b": "usage", "i": "$15", "o": "$120", "c": "$1.5", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5-pro-2025-10-06", "b": "usage", "i": "$15", "o": "$120", "c": "$1.5", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5.1", "b": "usage", "i": "$1.25", "o": "$10", "c": "$0.125", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5.1-2025-11-13", "b": "usage", "i": "$1.25", "o": "$10", "c": "$0.125", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5.1-codex", "b": "per-call", "i": "$0.02/call", "o": "—", "c": "—", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5.1-codex-high", "b": "usage", "i": "$1.25", "o": "$10", "c": "$0.125", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5.1-codex-medium", "b": "usage", "i": "$1.25", "o": "$10", "c": "$0.125", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5.1-codex-mini", "b": "usage", "i": "$1.25", "o": "$3.75", "c": "$0.125", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5.2", "b": "usage", "i": "$1.75", "o": "$14", "c": "$0.175", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5.2-2025-12-11", "b": "usage", "i": "$1.75", "o": "$14", "c": "$0.175", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5.2-chat-latest", "b": "usage", "i": "$1.75", "o": "$14", "c": "$0.175", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5.2-pro", "b": "usage", "i": "$21", "o": "$168", "c": "$2.1", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5.2-pro-2025-12-11", "b": "usage", "i": "$21", "o": "$168", "c": "$2.1", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5.3-chat-latest", "b": "usage", "i": "$1.75", "o": "$14", "c": "$0.175", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5.4", "b": "usage", "i": "$2.5", "o": "$15", "c": "$0.25", "v": "OpenAI", "a": "openai", "t": 1 }, { "n": "gpt-5.4-mini", "b": "usage", "i": "$0.75", "o": "$4.5", "c": "$0.075", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5.4-nano", "b": "usage", "i": "$0.2", "o": "$1.25", "c": "$0.02", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5.4-nano-2026-03-17", "b": "usage", "i": "$0.2", "o": "$1.25", "c": "$0.02", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-5.4-pro", "b": "usage", "i": "$30", "o": "$180", "c": "$3", "v": "OpenAI", "a": "openai", "t": 1 }, { "n": "gpt-5.5", "b": "usage", "i": "$5", "o": "$30", "c": "$0.5", "v": "OpenAI", "a": "openai", "t": 1 }, { "n": "gpt-5.5-pro", "b": "usage", "i": "$30", "o": "$180", "c": "$3", "v": "OpenAI", "a": "openai", "t": 1 }, { "n": "gpt-5.6-luna", "b": "usage", "i": "$1", "o": "$6", "c": "$0.1", "v": "OpenAI", "a": "openai", "t": 1 }, { "n": "gpt-5.6-sol", "b": "usage", "i": "$5", "o": "$30", "c": "$0.5", "v": "OpenAI", "a": "openai", "t": 1 }, { "n": "gpt-5.6-terra", "b": "usage", "i": "$2.5", "o": "$15", "c": "$0.25", "v": "OpenAI", "a": "openai", "t": 1 }, { "n": "gpt-image-1", "b": "usage", "i": "$5", "o": "$40", "c": "$1.25", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-image-1-mini", "b": "usage", "i": "$2", "o": "$8", "c": "$0.2", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-image-1.5", "b": "usage", "i": "$5", "o": "$32", "c": "$1.25", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-image-1.5-2025-12-16", "b": "usage", "i": "$5", "o": "$32", "c": "$1.25", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-image-2", "b": "usage", "i": "$5", "o": "$30", "c": "$1.25", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-image-2-all", "b": "per-call", "i": "$0.03/call", "o": "—", "c": "—", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-image-2-vip", "b": "per-call", "i": "$0.03/call", "o": "—", "c": "—", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-oss-120b", "b": "usage", "i": "$0.5", "o": "$2", "c": "$0.05", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-oss-120b-1", "b": "usage", "i": "$0.5", "o": "$2", "c": "$0.05", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "gpt-oss-20b", "b": "usage", "i": "$0.1", "o": "$0.4", "c": "$0.01", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "grok-4.20-0309-non-reasoning", "b": "usage", "i": "$1.25", "o": "$2.5", "c": "$0.2", "v": "xAI", "a": "xai", "t": 0 }, { "n": "grok-4.20-0309-reasoning", "b": "usage", "i": "$1.25", "o": "$2.5", "c": "$0.2", "v": "xAI", "a": "xai", "t": 0 }, { "n": "grok-4.20-beta", "b": "usage", "i": "$1.25", "o": "$2.5", "c": "—", "v": "xAI", "a": "xai", "t": 0 }, { "n": "grok-4.20-multi-agent-0309", "b": "usage", "i": "$1.25", "o": "$2.5", "c": "$0.2", "v": "xAI", "a": "xai", "t": 0 }, { "n": "grok-4.20-multi-agent-beta-0309", "b": "usage", "i": "$1.25", "o": "$2.5", "c": "—", "v": "xAI", "a": "xai", "t": 0 }, { "n": "grok-4.3", "b": "usage", "i": "$1.25", "o": "$2.5", "c": "$0.2", "v": "xAI", "a": "xai", "t": 1 }, { "n": "grok-4.5", "b": "usage", "i": "$2", "o": "$6", "c": "$0.5", "v": "xAI", "a": "xai", "t": 1 }, { "n": "grok-build-0.1", "b": "usage", "i": "$1", "o": "$2", "c": "$0.2", "v": "xAI", "a": "xai", "t": 0 }, { "n": "grok-code-fast", "b": "usage", "i": "$0.2", "o": "$1.5", "c": "—", "v": "xAI", "a": "xai", "t": 0 }, { "n": "grok-code-fast-1", "b": "usage", "i": "$0.2", "o": "$1.5", "c": "—", "v": "xAI", "a": "xai", "t": 0 }, { "n": "happyhorse-1.0-video-edit", "b": "usage", "i": "$1.8", "o": "$1.8", "c": "—", "v": "HappyHorse", "a": "happyhorse", "t": 0 }, { "n": "happyhorse-1.1-i2v", "b": "usage", "i": "$1.8", "o": "$1.8", "c": "—", "v": "HappyHorse", "a": "happyhorse", "t": 0 }, { "n": "happyhorse-1.1-r2v", "b": "usage", "i": "$1.8", "o": "$1.8", "c": "—", "v": "HappyHorse", "a": "happyhorse", "t": 0 }, { "n": "happyhorse-1.1-t2v", "b": "usage", "i": "$1.8", "o": "$1.8", "c": "—", "v": "HappyHorse", "a": "happyhorse", "t": 0 }, { "n": "kimi-k2-0711-preview", "b": "usage", "i": "$0.8", "o": "$3.2", "c": "$0.08", "v": "Moonshot", "a": "moonshot", "t": 0 }, { "n": "kimi-k2-250711", "b": "usage", "i": "$0.8", "o": "$3.2", "c": "$0.08", "v": "Moonshot", "a": "moonshot", "t": 0 }, { "n": "kimi-k2.5", "b": "usage", "i": "$0.6", "o": "$3.15", "c": "$0.1", "v": "Moonshot", "a": "moonshot", "t": 0 }, { "n": "kimi-k2.6", "b": "usage", "i": "$0.6", "o": "$2.4", "c": "$0.101053", "v": "Moonshot", "a": "moonshot", "t": 0 }, { "n": "kimi-k2.7-code", "b": "usage", "i": "$0.95", "o": "$3.99", "c": "$0.19", "v": "Moonshot", "a": "moonshot", "t": 0 }, { "n": "kimi-k3", "b": "usage", "i": "$3", "o": "$15", "c": "$0.3", "v": "Moonshot", "a": "moonshot", "t": 0 }, { "n": "longcat-flash-chat", "b": "usage", "i": "$0.25", "o": "$0.5", "c": "—", "v": "Meituan", "a": "meituan", "t": 0 }, { "n": "mimo-v2-omni", "b": "usage", "i": "$0.4", "o": "$2", "c": "—", "v": "Xiaomi", "a": "xiaomi", "t": 0 }, { "n": "mimo-v2-pro", "b": "usage", "i": "$1", "o": "$3", "c": "—", "v": "Xiaomi", "a": "xiaomi", "t": 1 }, { "n": "multimodal-embedding-v1", "b": "per-call", "i": "$0.0001/call", "o": "—", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "nano-banana", "b": "per-call", "i": "$0.02/call", "o": "—", "c": "—", "v": "Google", "a": "google", "t": 0 }, { "n": "nano-banana-2", "b": "per-call", "i": "$0.055/call", "o": "—", "c": "—", "v": "Google", "a": "google", "t": 0 }, { "n": "nano-banana-pro", "b": "per-call", "i": "$0.09/call", "o": "—", "c": "—", "v": "Google", "a": "google", "t": 0 }, { "n": "o1", "b": "usage", "i": "$15", "o": "$60", "c": "$7.5", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "o1-2024-12-17", "b": "usage", "i": "$15", "o": "$60", "c": "$7.5", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "o1-mini", "b": "usage", "i": "$1.1", "o": "$4.4", "c": "$0.55", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "o1-mini-2024-09-12", "b": "usage", "i": "$1.1", "o": "$4.4", "c": "$0.55", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "o1-preview", "b": "usage", "i": "$15", "o": "$60", "c": "$7.5", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "o1-preview-2024-09-12", "b": "usage", "i": "$15", "o": "$60", "c": "$7.5", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "o1-pro", "b": "usage", "i": "$180", "o": "$720", "c": "$90", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "o3", "b": "usage", "i": "$3", "o": "$12", "c": "$0.75", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "o3-2025-04-16", "b": "usage", "i": "$3", "o": "$12", "c": "$0.75", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "o3-deep-research-2025-06-26", "b": "usage", "i": "$12", "o": "$48", "c": "$3", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "o3-mini", "b": "usage", "i": "$1.1", "o": "$4.4", "c": "$0.55", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "o3-mini-2025-01-31", "b": "usage", "i": "$1.1", "o": "$4.4", "c": "$0.55", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "o3-mini-2025-01-31-high", "b": "usage", "i": "$1.1", "o": "$4.4", "c": "$0.55", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "o3-mini-2025-01-31-low", "b": "usage", "i": "$1.1", "o": "$4.4", "c": "$0.55", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "o3-mini-2025-01-31-medium", "b": "usage", "i": "$1.1", "o": "$4.4", "c": "$0.55", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "o3-mini-low", "b": "usage", "i": "$1.1", "o": "$4.4", "c": "$0.55", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "o3-mini-medium", "b": "usage", "i": "$1.1", "o": "$4.4", "c": "$0.55", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "o3-pro", "b": "usage", "i": "$20", "o": "$80", "c": "$5", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "o3-pro-2025-06-10", "b": "usage", "i": "$20", "o": "$80", "c": "$5", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "o4-mini", "b": "usage", "i": "$1.1", "o": "$4.4", "c": "$0.275", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "o4-mini-2025-04-16", "b": "usage", "i": "$1.1", "o": "$4.4", "c": "$0.275", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "omni-moderation-2024-09-26", "b": "usage", "i": "$0.2", "o": "$0.2", "c": "—", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "omni-moderation-latest", "b": "usage", "i": "$0.2", "o": "$0.2", "c": "—", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "qvq-max", "b": "usage", "i": "$1.2", "o": "$4.8", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qvq-plus", "b": "usage", "i": "$0.28", "o": "$0.7", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen-long", "b": "usage", "i": "$0.07", "o": "$0.28", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen-max", "b": "usage", "i": "$1.6", "o": "$6.4", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen-max-longcontext", "b": "usage", "i": "$3.2", "o": "$3.2", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen-mt-plus", "b": "usage", "i": "$2", "o": "$8", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen-mt-turbo", "b": "usage", "i": "$0.2", "o": "$0.5", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen-plus", "b": "usage", "i": "$0.4", "o": "$1.2", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 1 }, { "n": "qwen-plus-2025-07-14", "b": "usage", "i": "$0.4", "o": "$4", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen-plus-2025-09-11", "b": "usage", "i": "$0.4", "o": "$4", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 1 }, { "n": "qwen-plus-latest", "b": "usage", "i": "$0.4", "o": "$1.2", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 1 }, { "n": "qwen-turbo", "b": "usage", "i": "$0.2", "o": "$0.6", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen-vl-max", "b": "usage", "i": "$0.2", "o": "$0.8", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen-vl-ocr", "b": "usage", "i": "$0.72", "o": "$0.72", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen-vl-ocr-2025-11-20", "b": "usage", "i": "$0.044", "o": "$0.07348", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen-vl-ocr-latest", "b": "usage", "i": "$0.044", "o": "$0.07348", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen-vl-plus", "b": "usage", "i": "$0.2", "o": "$0.6", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3-235b-a22b", "b": "usage", "i": "$1", "o": "$10", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3-235b-a22b-instruct-2507", "b": "usage", "i": "$1", "o": "$10", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3-235b-a22b-thinking-2507", "b": "usage", "i": "$1.6", "o": "$12.8", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3-30b-a3b", "b": "usage", "i": "$0.2", "o": "$2", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3-30b-a3b-instruct-2507", "b": "usage", "i": "$0.2", "o": "$0.8", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3-30b-a3b-thinking-2507", "b": "usage", "i": "$0.2", "o": "$2.4", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3-32b", "b": "usage", "i": "$0.4", "o": "$4", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3-coder-480b-a35b-instruct", "b": "usage", "i": "$3", "o": "$15", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 1 }, { "n": "qwen3-coder-flash", "b": "usage", "i": "$0.5", "o": "$5", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 1 }, { "n": "qwen3-coder-plus", "b": "usage", "i": "$5", "o": "$20", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 1 }, { "n": "qwen3-coder-plus-2025-07-22", "b": "usage", "i": "$2", "o": "$20", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 1 }, { "n": "qwen3-coder-plus-2025-09-23", "b": "usage", "i": "$2", "o": "$20", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 1 }, { "n": "qwen3-max", "b": "usage", "i": "$1.2", "o": "$6", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 1 }, { "n": "qwen3-max-2025-09-23", "b": "usage", "i": "$1.2", "o": "$6", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 1 }, { "n": "qwen3-max-preview", "b": "usage", "i": "$1.2", "o": "$6", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 1 }, { "n": "qwen3-next-80b-a3b-instruct", "b": "usage", "i": "$0.15", "o": "$1.2", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3-omni-flash", "b": "usage", "i": "$0.6", "o": "$6", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3-omni-flash-2025-09-15", "b": "usage", "i": "$2", "o": "$20", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3-vl-235b-a22b-instruct", "b": "usage", "i": "$0.3", "o": "$3", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3-vl-235b-a22b-thinking", "b": "usage", "i": "$0.3", "o": "$3", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3-vl-30b-a3b-thinking", "b": "usage", "i": "$0.12", "o": "$1.2", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3-vl-32b-thinking", "b": "usage", "i": "$0.3", "o": "$3", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3-vl-embedding", "b": "per-call", "i": "$0.0001/call", "o": "—", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3-vl-flash", "b": "usage", "i": "$0.1", "o": "$0.8", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3-vl-flash-2025-10-15", "b": "usage", "i": "$0.1", "o": "$0.8", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3-vl-plus", "b": "usage", "i": "$0.3", "o": "$2.4", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 1 }, { "n": "qwen3-vl-plus-2025-09-23", "b": "usage", "i": "$0.3", "o": "$2.4", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 1 }, { "n": "qwen3.5-122b-a10b", "b": "usage", "i": "$0.12", "o": "$0.96", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3.5-27b", "b": "usage", "i": "$0.09", "o": "$0.72", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3.5-35b-a3b", "b": "usage", "i": "$0.06", "o": "$0.48", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3.5-397b-a17b", "b": "usage", "i": "$0.18", "o": "$1.08", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3.5-flash", "b": "usage", "i": "$0.03", "o": "$0.3", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 1 }, { "n": "qwen3.5-flash-2026-02-23", "b": "usage", "i": "$0.03", "o": "$0.3", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 1 }, { "n": "qwen3.5-omni-flash", "b": "usage", "i": "$0.35", "o": "$2", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3.5-omni-plus", "b": "usage", "i": "$1.2", "o": "$6", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3.5-plus", "b": "usage", "i": "$0.114", "o": "$0.684", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 1 }, { "n": "qwen3.5-plus-2026-02-15", "b": "usage", "i": "$0.114", "o": "$0.684", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 1 }, { "n": "qwen3.6-27b", "b": "usage", "i": "$0.42", "o": "$2.52", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3.6-35b-a3b", "b": "usage", "i": "$0.26", "o": "$1.56", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3.6-flash", "b": "usage", "i": "$0.17", "o": "$1.02", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 1 }, { "n": "qwen3.6-max-preview", "b": "usage", "i": "$1.28", "o": "$7.68", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 1 }, { "n": "qwen3.6-plus", "b": "usage", "i": "$0.3", "o": "$1.8", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 1 }, { "n": "qwen3.7-max", "b": "usage", "i": "$1.714", "o": "$5.142", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "qwen3.7-plus", "b": "usage", "i": "$0.6", "o": "$2.4", "c": "$0.06", "v": "Alibaba", "a": "alibaba", "t": 1 }, { "n": "qwq-plus", "b": "usage", "i": "$0.8", "o": "$2.4", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "seed-1-6-250615", "b": "usage", "i": "$0.1", "o": "$1", "c": "—", "v": "ByteDance", "a": "bytedance", "t": 0 }, { "n": "seed-1-6-flash-250615", "b": "usage", "i": "$0.075", "o": "$0.3", "c": "—", "v": "ByteDance", "a": "bytedance", "t": 0 }, { "n": "seed-1-6-flash-250715", "b": "usage", "i": "$0.075", "o": "$0.3", "c": "—", "v": "ByteDance", "a": "bytedance", "t": 0 }, { "n": "seed-1-8-251228", "b": "usage", "i": "$0.25", "o": "$2", "c": "—", "v": "ByteDance", "a": "bytedance", "t": 0 }, { "n": "seed-2-0-code-preview-260328", "b": "usage", "i": "$0.5", "o": "$3", "c": "—", "v": "ByteDance", "a": "bytedance", "t": 0 }, { "n": "seed-2-0-lite-260228", "b": "usage", "i": "$0.25", "o": "$2", "c": "—", "v": "ByteDance", "a": "bytedance", "t": 1 }, { "n": "seed-2-0-lite-260428", "b": "usage", "i": "$0.25", "o": "$2", "c": "—", "v": "ByteDance", "a": "bytedance", "t": 0 }, { "n": "seed-2-0-mini-260215", "b": "usage", "i": "$0.1", "o": "$0.4", "c": "—", "v": "ByteDance", "a": "bytedance", "t": 1 }, { "n": "seed-2-0-mini-260428", "b": "usage", "i": "$0.1", "o": "$0.4", "c": "—", "v": "ByteDance", "a": "bytedance", "t": 0 }, { "n": "seed-2-0-pro-260328", "b": "usage", "i": "$0.5", "o": "$3", "c": "—", "v": "ByteDance", "a": "bytedance", "t": 1 }, { "n": "seedream-4-0-250828", "b": "per-call", "i": "$0.035/call", "o": "—", "c": "—", "v": "ByteDance", "a": "bytedance", "t": 0 }, { "n": "seedream-4-5-251128", "b": "per-call", "i": "$0.04/call", "o": "—", "c": "—", "v": "ByteDance", "a": "bytedance", "t": 0 }, { "n": "seedream-5-0-260128", "b": "per-call", "i": "$0.035/call", "o": "—", "c": "—", "v": "ByteDance", "a": "bytedance", "t": 0 }, { "n": "seedream-5-0-pro-260628", "b": "per-call", "i": "$0.12/call", "o": "—", "c": "—", "v": "ByteDance", "a": "bytedance", "t": 0 }, { "n": "step-3.5-flash", "b": "usage", "i": "$0.1", "o": "$0.3", "c": "—", "v": "StepFun", "a": "stepfun", "t": 0 }, { "n": "text-embedding-3-large", "b": "usage", "i": "$0.13", "o": "$0.13", "c": "—", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "text-embedding-3-small", "b": "usage", "i": "$0.02", "o": "$0.02", "c": "—", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "text-embedding-ada-002", "b": "usage", "i": "$0.1", "o": "$0.1", "c": "—", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "text-embedding-v4", "b": "usage", "i": "$0.07", "o": "$0.07", "c": "—", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "text-moderation-stable", "b": "usage", "i": "$0.2", "o": "$0.2", "c": "—", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "tts-1", "b": "usage", "i": "$30", "o": "$30", "c": "—", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "tts-1-hd", "b": "usage", "i": "$60", "o": "$60", "c": "—", "v": "OpenAI", "a": "openai", "t": 0 }, { "n": "veo-3.1-fast-generate-preview", "b": "per-call", "i": "$0.3/call", "o": "—", "c": "—", "v": "Google", "a": "google", "t": 0 }, { "n": "veo-3.1-generate-preview", "b": "per-call", "i": "$1.2/call", "o": "—", "c": "—", "v": "Google", "a": "google", "t": 0 }, { "n": "wan2.6-i2v", "b": "usage", "i": "$1.2", "o": "$1.2", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "wan2.6-r2v", "b": "usage", "i": "$75", "o": "$75", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "wan2.6-r2v-flash", "b": "usage", "i": "$75", "o": "$75", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "wan2.6-t2v", "b": "usage", "i": "$1.2", "o": "$1.2", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "wan2.7-i2v", "b": "usage", "i": "$0.1714", "o": "$0.1714", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "wan2.7-r2v", "b": "usage", "i": "$75", "o": "$75", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "wan2.7-t2v", "b": "usage", "i": "$0.1714", "o": "$0.1714", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }, { "n": "wan2.7-videoedit", "b": "usage", "i": "$75", "o": "$75", "c": "—", "v": "Alibaba", "a": "alibaba", "t": 0 }]; export const ModelSearch = () => { const [q, setQ] = useState(''); const query = q.trim().toLowerCase(); const all = query ? MODELS.filter(m => m.n.toLowerCase().includes(query)) : []; const hits = all.slice(0, 30); return
setQ(e.target.value)} placeholder="Search model name, e.g. gpt-5.2 / claude / nano-banana" className="mp-search-input" /> {query.length > 0 && all.length === 0 &&

No matching model found

} {query.length > 0 && all.length > 0 &&

{all.length > 30 ? '' + all.length + ' matches' + ' — showing first 30, keep typing to narrow down' : '' + all.length + ' matches'}

{hits.map(m => )}
Model Billing Input Output Cache read Vendor
{m.n}{m.t ? ' †' : ''} {m.b} {m.i} {m.o} {m.c} {m.v}
}
; };

On this page

Discounts Other views Column reference

Vendors

OpenAI Anthropic Google xAI DeepSeek Alibaba ByteDance Moonshot Zhipu MiniMax BAAI Black Forest Labs HappyHorse Meituan StepFun Xiaomi
Tiered pricing

Model Pricing Directory

Live pricing for all available models on APIYI: input/output/cache prices, endpoints, and groups. Auto-updated.

Data updated at 2026-07-25 11:51 (UTC+8) from the live pricing API. All prices in USD. Top-ups settle at a **fixed 1:7 exchange rate**, stackable with recharge bonuses — see [Pricing](/en/pricing). 309 16 273 36

Discounts

Prices in the tables below are **default list prices** — your effective cost can be lower, since recharge promotions and group discounts **stack**: * **Recharge promotions**: with recharge bonuses your effective cost drops to 1/1.1 of list price (about 91%), up to 1/1.2 (about 83%) during campaigns — see [Recharge promotions](/en/faq/recharge-promotions). * **Group discounts**: some billing groups carry extra discounts (e.g. 0.95×, i.e. 95% of list) — see [Group overview](/en/faq/token-and-groups#group-overview). The console reflects the actual charge in real time.

Other views

Besides this page, model pricing is also available at: | Entry | Strength | Limitation | | ------------------------------------------------------------------------ | ------------------------------------------------ | --------------------------------------- | | [Model plaza (modelmak)](https://api.apiyi.com/modelmak) | Official live data with endpoint info | No cache prices or tiered-pricing notes | | [Legacy pricing page (modelPricing)](https://api.apiyi.com/modelPricing) | Simple layout | Fewer data dimensions | | [Console pricing page](https://api.apiyi.com/account/pricing) | Shows **your actual discounted price** per group | Login required |

Column reference

* **Input / Output / Cache read**: prices for usage-based models in USD per 1M tokens (\$/1M). **Cache read** is the input price on prompt-cache hits; "—" means no cache ratio is configured for the model. * **Per-call**: billed per request (image/video models), price in USD per call. * **Endpoints**: `chat` = /v1/chat/completions; `responses` = /v1/responses; `messages` = /v1/messages; `gemini` = native /v1beta API; `images` = /v1/images/generations; `embeddings` = /v1/embeddings. * **Groups**: billing groups where the model is available. Some groups carry discounts, stackable with recharge bonuses; the console is authoritative. * **†**: tiered pricing — the rate depends on per-request token volume, see "Tiered pricing" at the end of the page. * This page is a complete single-page list — besides the search box above, desktop users can also use Ctrl+F (Cmd+F on macOS) to find a model name.
**Jump to vendor**: [OpenAI](#openai) · [Anthropic](#anthropic) · [Google](#google) · [xAI](#xai) · [DeepSeek](#deepseek) · [Alibaba](#alibaba) · [ByteDance](#bytedance) · [Moonshot](#moonshot) · [Zhipu](#zhipu) · [MiniMax](#minimax) · [BAAI](#baai) · [Black Forest Labs](#black-forest-labs) · [HappyHorse](#happyhorse) · [Meituan](#meituan) · [StepFun](#stepfun) · [Xiaomi](#xiaomi)

OpenAI

| Model | Billing | Input | Output | Cache read | Endpoints | Groups | | ----------------------------- | -------- | ----------- | ------ | ---------- | ------------------- | ------------------------------- | | `chat-latest` | usage | \$5 | \$30 | \$0.5 | `chat` | Default, SVIP | | `chatgpt-image-latest` | usage | \$5 | \$32 | \$1.25 | `chat` | Default, SVIP | | `dall-e-3` | usage | \$40 | \$40 | — | `images` `chat` | Default, SVIP | | `gpt-3.5-turbo` | usage | \$0.5 | \$1.5 | \$0.05 | `chat` | Default, SVIP | | `gpt-3.5-turbo-0125` | usage | \$0.5 | \$1.5 | \$0.05 | `chat` | Default, SVIP | | `gpt-3.5-turbo-0613` | usage | \$1.5 | \$1.95 | \$0.15 | `chat` | Default, SVIP | | `gpt-3.5-turbo-1106` | usage | \$1 | \$2 | \$0.1 | `chat` | Default, SVIP | | `gpt-3.5-turbo-16k` | usage | \$3 | \$3.9 | \$0.3 | `chat` | Default, SVIP | | `gpt-3.5-turbo-16k-0613` | usage | \$3 | \$3.9 | \$0.3 | `chat` | Default, SVIP | | `gpt-4-32k` | usage | \$60 | \$120 | \$6 | `chat` | Default, SVIP | | `gpt-4.1` | usage | \$2 | \$8 | \$0.5 | `chat` | Default, SVIP | | `gpt-4.1-2025-04-14` | usage | \$2 | \$8 | \$0.5 | `chat` | Default, SVIP | | `gpt-4.1-mini` | usage | \$0.4 | \$1.6 | \$0.1 | `chat` | Default, SVIP | | `gpt-4.1-mini-2025-04-14` | usage | \$0.4 | \$1.6 | \$0.1 | `chat` | Default, SVIP | | `gpt-4.1-nano` | usage | \$0.1 | \$0.4 | \$0.025 | `chat` | Default, SVIP | | `gpt-4.1-nano-2025-04-14` | usage | \$0.1 | \$0.4 | \$0.025 | `chat` | Default, SVIP | | `gpt-4o` | usage | \$2.5 | \$10 | \$1.25 | `chat` | Default, SVIP | | `gpt-4o-2024-05-13` | usage | \$5 | \$15 | \$2.5 | `chat` | Default, SVIP | | `gpt-4o-2024-08-06` | usage | \$2.5 | \$10 | \$1.25 | `chat` | Default, SVIP | | `gpt-4o-2024-11-20` | usage | \$2.5 | \$10 | \$1.25 | `chat` | Default, SVIP | | `gpt-4o-mini` | usage | \$0.15 | \$0.6 | \$0.075 | `chat` | Default, SVIP | | `gpt-4o-mini-2024-07-18` | usage | \$0.15 | \$0.6 | \$0.075 | `chat` | Default, SVIP | | `gpt-4o-mini-audio-preview` | usage | \$2 | \$8 | \$1 | `chat` | Default, SVIP | | `gpt-4o-mini-transcribe` | usage | \$1.5 | \$6 | \$0.75 | `chat` | Default, SVIP | | `gpt-4o-transcribe` | usage | \$8 | \$16 | \$4 | `chat` | Default, SVIP | | `gpt-5` | usage | \$1.25 | \$10 | \$0.125 | `chat` | Default, SVIP | | `gpt-5-2025-08-07` | usage | \$1.25 | \$10 | \$0.125 | `chat` | Default, SVIP | | `gpt-5-chat-latest` | usage | \$1.25 | \$10 | \$0.125 | `chat` | Default, SVIP | | `gpt-5-codex` | usage | \$1.25 | \$10 | \$0.125 | `chat` | Default, SVIP | | `gpt-5-mini` | usage | \$0.25 | \$2 | \$0.025 | `chat` | Default, SVIP | | `gpt-5-mini-2025-08-07` | usage | \$0.25 | \$2 | \$0.025 | `chat` | Default, SVIP | | `gpt-5-nano` | usage | \$0.05 | \$0.4 | \$0.005 | `chat` | Default, SVIP | | `gpt-5-nano-2025-08-07` | usage | \$0.05 | \$0.4 | \$0.005 | `chat` | Default, SVIP | | `gpt-5-pro` | usage | \$15 | \$120 | \$1.5 | `chat` | Default, SVIP | | `gpt-5-pro-2025-10-06` | usage | \$15 | \$120 | \$1.5 | `chat` | SVIP | | `gpt-5.1` | usage | \$1.25 | \$10 | \$0.125 | `chat` | Default, SVIP | | `gpt-5.1-2025-11-13` | usage | \$1.25 | \$10 | \$0.125 | `chat` | Default, SVIP | | `gpt-5.1-codex` | per-call | \$0.02/call | — | — | `chat` | Default, SVIP | | `gpt-5.1-codex-high` | usage | \$1.25 | \$10 | \$0.125 | `chat` | Default, SVIP | | `gpt-5.1-codex-medium` | usage | \$1.25 | \$10 | \$0.125 | `chat` | Default, SVIP | | `gpt-5.1-codex-mini` | usage | \$1.25 | \$3.75 | \$0.125 | `chat` | Default, SVIP | | `gpt-5.2` | usage | \$1.75 | \$14 | \$0.175 | `chat` | Default, SVIP | | `gpt-5.2-2025-12-11` | usage | \$1.75 | \$14 | \$0.175 | `chat` | Default, SVIP | | `gpt-5.2-chat-latest` | usage | \$1.75 | \$14 | \$0.175 | `chat` | Default, SVIP | | `gpt-5.2-pro` | usage | \$21 | \$168 | \$2.1 | `chat` | Default, SVIP | | `gpt-5.2-pro-2025-12-11` | usage | \$21 | \$168 | \$2.1 | `chat` | SVIP | | `gpt-5.3-chat-latest` | usage | \$1.75 | \$14 | \$0.175 | `chat` | Default, SVIP | | `gpt-5.4` † | usage | \$2.5 | \$15 | \$0.25 | `chat` | CodexReverse, Default, SVIP | | `gpt-5.4-mini` | usage | \$0.75 | \$4.5 | \$0.075 | `chat` | CodexReverse, Default, SVIP | | `gpt-5.4-nano` | usage | \$0.2 | \$1.25 | \$0.02 | `chat` | Default, SVIP | | `gpt-5.4-nano-2026-03-17` | usage | \$0.2 | \$1.25 | \$0.02 | `chat` | Default, SVIP | | `gpt-5.4-pro` † | usage | \$30 | \$180 | \$3 | `chat` | Default, SVIP | | `gpt-5.5` † | usage | \$5 | \$30 | \$0.5 | `chat` | CodexReverse, Default, SVIP | | `gpt-5.5-pro` † | usage | \$30 | \$180 | \$3 | `chat` | Default, SVIP | | `gpt-5.6-luna` † | usage | \$1 | \$6 | \$0.1 | `chat` | CodexReverse, Default, SVIP | | `gpt-5.6-sol` † | usage | \$5 | \$30 | \$0.5 | `chat` | CodexReverse, Default, SVIP | | `gpt-5.6-terra` † | usage | \$2.5 | \$15 | \$0.25 | `chat` | CodexReverse, Default, SVIP | | `gpt-image-1` | usage | \$5 | \$40 | \$1.25 | `images` `chat` | Default, image2Enterprise, SVIP | | `gpt-image-1-mini` | usage | \$2 | \$8 | \$0.2 | `images` `chat` | Default, image2Enterprise, SVIP | | `gpt-image-1.5` | usage | \$5 | \$32 | \$1.25 | `images` `chat` | Default, image2Enterprise, SVIP | | `gpt-image-1.5-2025-12-16` | usage | \$5 | \$32 | \$1.25 | `images` `chat` | Default, SVIP | | `gpt-image-2` | usage | \$5 | \$30 | \$1.25 | `images` `chat` | Default, image2Enterprise, SVIP | | `gpt-image-2-all` | per-call | \$0.03/call | — | — | `images` `chat` | Default, image2\_OSS, SVIP | | `gpt-image-2-vip` | per-call | \$0.03/call | — | — | `images` `chat` | Default, image2\_OSS, SVIP | | `gpt-oss-120b` | usage | \$0.5 | \$2 | \$0.05 | `chat` | Default, SVIP | | `gpt-oss-120b-1` | usage | \$0.5 | \$2 | \$0.05 | `chat` | Default, SVIP | | `gpt-oss-20b` | usage | \$0.1 | \$0.4 | \$0.01 | `chat` | Default, SVIP | | `o1` | usage | \$15 | \$60 | \$7.5 | `chat` | Default, SVIP | | `o1-2024-12-17` | usage | \$15 | \$60 | \$7.5 | `chat` | Default, SVIP | | `o1-mini` | usage | \$1.1 | \$4.4 | \$0.55 | `chat` | Default, SVIP | | `o1-mini-2024-09-12` | usage | \$1.1 | \$4.4 | \$0.55 | `chat` | Default, SVIP | | `o1-preview` | usage | \$15 | \$60 | \$7.5 | `chat` | Default, SVIP | | `o1-preview-2024-09-12` | usage | \$15 | \$60 | \$7.5 | `chat` | Default, SVIP | | `o1-pro` | usage | \$180 | \$720 | \$90 | `chat` | SVIP | | `o3` | usage | \$3 | \$12 | \$0.75 | `chat` | Default, SVIP | | `o3-2025-04-16` | usage | \$3 | \$12 | \$0.75 | `chat` | Default, SVIP | | `o3-deep-research-2025-06-26` | usage | \$12 | \$48 | \$3 | `responses` | Default, SVIP | | `o3-mini` | usage | \$1.1 | \$4.4 | \$0.55 | `chat` | Default, SVIP | | `o3-mini-2025-01-31` | usage | \$1.1 | \$4.4 | \$0.55 | `chat` | Default, SVIP | | `o3-mini-2025-01-31-high` | usage | \$1.1 | \$4.4 | \$0.55 | `chat` | Default, SVIP | | `o3-mini-2025-01-31-low` | usage | \$1.1 | \$4.4 | \$0.55 | `chat` | Default, SVIP | | `o3-mini-2025-01-31-medium` | usage | \$1.1 | \$4.4 | \$0.55 | `chat` | Default, SVIP | | `o3-mini-low` | usage | \$1.1 | \$4.4 | \$0.55 | `chat` | Default, SVIP | | `o3-mini-medium` | usage | \$1.1 | \$4.4 | \$0.55 | `chat` | Default, SVIP | | `o3-pro` | usage | \$20 | \$80 | \$5 | `responses` | Default, SVIP | | `o3-pro-2025-06-10` | usage | \$20 | \$80 | \$5 | `responses` | Default, SVIP | | `o4-mini` | usage | \$1.1 | \$4.4 | \$0.275 | `chat` | Default, SVIP | | `o4-mini-2025-04-16` | usage | \$1.1 | \$4.4 | \$0.275 | `chat` | Default, SVIP | | `omni-moderation-2024-09-26` | usage | \$0.2 | \$0.2 | — | `chat` | Default, SVIP | | `omni-moderation-latest` | usage | \$0.2 | \$0.2 | — | `chat` | Default, SVIP | | `text-embedding-3-large` | usage | \$0.13 | \$0.13 | — | `chat` `embeddings` | Default, SVIP | | `text-embedding-3-small` | usage | \$0.02 | \$0.02 | — | `chat` `embeddings` | Default, SVIP | | `text-embedding-ada-002` | usage | \$0.1 | \$0.1 | — | `chat` `embeddings` | Default, SVIP | | `text-embedding-v4` | usage | \$0.07 | \$0.07 | — | `chat` `embeddings` | Default, SVIP | | `text-moderation-stable` | usage | \$0.2 | \$0.2 | — | `chat` | Default, SVIP | | `tts-1` | usage | \$30 | \$30 | — | `chat` | Default, SVIP | | `tts-1-hd` | usage | \$60 | \$60 | — | `chat` | Default, SVIP |

Anthropic

| Model | Billing | Input | Output | Cache read | Endpoints | Groups | | ------------------------------------- | ------- | ----- | ------ | ---------- | ----------------- | ------------------------- | | `claude-fable-5` | usage | \$10 | \$50 | \$1 | `chat` `messages` | ClaudeCode, Default, SVIP | | `claude-haiku-4-5-20251001` | usage | \$1 | \$5 | \$0.1 | `chat` `messages` | ClaudeCode, Default, SVIP | | `claude-haiku-4-5-20251001-thinking` | usage | \$1 | \$5 | \$0.1 | `chat` `messages` | ClaudeCode, Default, SVIP | | `claude-opus-4-1-20250805` | usage | \$15 | \$75 | \$1.5 | `chat` `messages` | ClaudeCode, Default, SVIP | | `claude-opus-4-1-20250805-thinking` | usage | \$15 | \$75 | \$1.5 | `chat` `messages` | ClaudeCode, Default, SVIP | | `claude-opus-4-5-20251101` | usage | \$5 | \$25 | \$0.5 | `chat` `messages` | ClaudeCode, Default, SVIP | | `claude-opus-4-5-20251101-thinking` | usage | \$5 | \$25 | \$0.5 | `chat` `messages` | ClaudeCode, Default, SVIP | | `claude-opus-4-6` | usage | \$5 | \$25 | \$0.5 | `chat` `messages` | ClaudeCode, Default, SVIP | | `claude-opus-4-6-thinking` | usage | \$5 | \$25 | \$0.5 | `chat` `messages` | ClaudeCode, Default, SVIP | | `claude-opus-4-7` | usage | \$5 | \$25 | \$0.5 | `chat` `messages` | ClaudeCode, Default, SVIP | | `claude-opus-4-7-thinking` | usage | \$5 | \$25 | \$0.5 | `chat` `messages` | ClaudeCode, Default, SVIP | | `claude-opus-4-8` | usage | \$5 | \$25 | \$0.5 | `chat` `messages` | ClaudeCode, Default, SVIP | | `claude-opus-4-8-thinking` | usage | \$5 | \$25 | \$0.5 | `chat` `messages` | ClaudeCode, Default, SVIP | | `claude-sonnet-4-20250514` | usage | \$3 | \$15 | \$0.3 | `chat` `messages` | ClaudeCode, Default, SVIP | | `claude-sonnet-4-20250514-thinking` | usage | \$3 | \$15 | \$0.3 | `chat` `messages` | ClaudeCode, Default, SVIP | | `claude-sonnet-4-5-20250929` | usage | \$3 | \$15 | \$0.3 | `chat` `messages` | ClaudeCode, Default, SVIP | | `claude-sonnet-4-5-20250929-thinking` | usage | \$3 | \$15 | \$0.3 | `chat` `messages` | ClaudeCode, Default, SVIP | | `claude-sonnet-4-6` | usage | \$3 | \$15 | \$0.3 | `chat` `messages` | ClaudeCode, Default, SVIP | | `claude-sonnet-4-6-thinking` | usage | \$3 | \$15 | \$0.3 | `chat` `messages` | ClaudeCode, Default, SVIP | | `claude-sonnet-5` | usage | \$2 | \$10 | \$0.2 | `chat` `messages` | ClaudeCode, Default, SVIP | | `claude-sonnet-5-thinking` | usage | \$2 | \$10 | \$0.2 | `messages` `chat` | ClaudeCode, Default, SVIP |

Google

| Model | Billing | Input | Output | Cache read | Endpoints | Groups | | ------------------------------------ | -------- | ------------ | -------- | ---------- | ---------------------------- | ------------------------------------------- | | `gemini-2.5-flash` | usage | \$0.3 | \$2.4 | \$0.03 | `gemini` `chat` | Default, SVIP | | `gemini-2.5-flash-image` | per-call | \$0.02/call | — | — | `gemini` `chat` | NB-OSS, NanoBananaEnterprise, Default, SVIP | | `gemini-2.5-flash-lite` | usage | \$0.1 | \$0.4 | \$0.01 | `gemini` `chat` | Default, SVIP | | `gemini-2.5-pro` † | usage | \$1.25 | \$10 | \$0.125 | `gemini` `chat` | Default, SVIP | | `gemini-2.5-pro-preview-tts` | usage | \$1 | \$20 | \$0.1 | `gemini` `chat` | Default, SVIP | | `gemini-3-flash-preview` | usage | \$0.44 | \$2.64 | \$0.044 | `gemini` `chat` | Default, SVIP | | `gemini-3-flash-preview-thinking` | usage | \$0.44 | \$2.64 | \$0.044 | `gemini` `chat` | Default, SVIP | | `gemini-3-pro-image` | per-call | \$0.09/call | — | — | `gemini` `chat` | NB-OSS, NanoBananaEnterprise, Default, SVIP | | `gemini-3-pro-image-preview` | per-call | \$0.09/call | — | — | `gemini` `chat` | NB-OSS, NanoBananaEnterprise, Default, SVIP | | `gemini-3-pro-image-preview-1k` | per-call | \$0.09/call | — | — | `gemini` `chat` | NB-OSS, NanoBananaEnterprise, Default, SVIP | | `gemini-3-pro-image-preview-2k` | per-call | \$0.09/call | — | — | `gemini` `chat` | NB-OSS, NanoBananaEnterprise, Default, SVIP | | `gemini-3-pro-image-preview-4k` | per-call | \$0.09/call | — | — | `gemini` `chat` | NB-OSS, NanoBananaEnterprise, Default, SVIP | | `gemini-3-pro-preview` | usage | \$1.8 | \$10.8 | \$0.18 | `gemini` `chat` | Default, SVIP | | `gemini-3.1-flash-image` | per-call | \$0.055/call | — | — | `gemini` `chat` | NB-OSS, NanoBananaEnterprise, Default, SVIP | | `gemini-3.1-flash-image-4k` | per-call | \$0.055/call | — | — | `gemini` `chat` | NB-OSS, NanoBananaEnterprise, Default, SVIP | | `gemini-3.1-flash-image-preview` | per-call | \$0.055/call | — | — | `gemini` `chat` | NB-OSS, NanoBananaEnterprise, Default, SVIP | | `gemini-3.1-flash-image-preview-4k` | per-call | \$0.055/call | — | — | `gemini` `chat` | NB-OSS, NanoBananaEnterprise, Default, SVIP | | `gemini-3.1-flash-lite` | usage | \$0.25 | \$1.5 | \$0.025 | `gemini` `chat` | Default, SVIP | | `gemini-3.1-flash-lite-image` | per-call | \$0.025/call | — | — | `gemini` `chat` | NB-OSS, NanoBananaEnterprise, Default, SVIP | | `gemini-3.1-flash-lite-preview` | usage | \$0.25 | \$1.5 | \$0.025 | `gemini` `chat` | Default, SVIP | | `gemini-3.1-pro-preview` † | usage | \$1.8 | \$10.8 | \$0.18 | `gemini` `chat` | Default, SVIP | | `gemini-3.1-pro-preview-customtools` | usage | \$1.8 | \$10.8 | \$0.18 | `gemini` `chat` | Default, SVIP | | `gemini-3.5-flash` | usage | \$1.5 | \$9 | \$0.15 | `gemini` `chat` | Default, SVIP | | `gemini-3.5-flash-lite` | usage | \$0.3 | \$2.4999 | \$0.03 | `gemini` `chat` | Default, SVIP | | `gemini-3.6-flash` | usage | \$1.5 | \$7.5 | \$0.15 | `gemini` `chat` | Default, SVIP | | `gemini-embedding-001` | usage | \$0.15 | \$0.45 | — | `gemini` `chat` `embeddings` | Default, SVIP | | `gemini-embedding-2-preview` | usage | \$0.3 | \$0.9 | — | `gemini` `chat` `embeddings` | Default, SVIP | | `nano-banana` | per-call | \$0.02/call | — | — | `gemini` `chat` | NanoBananaEnterprise, Default, SVIP | | `nano-banana-2` | per-call | \$0.055/call | — | — | `gemini` `chat` | NB-OSS, NanoBananaEnterprise, Default, SVIP | | `nano-banana-pro` | per-call | \$0.09/call | — | — | `gemini` `chat` | NB-OSS, NanoBananaEnterprise, Default, SVIP | | `veo-3.1-fast-generate-preview` | per-call | \$0.3/call | — | — | `chat` | Default, SVIP | | `veo-3.1-generate-preview` | per-call | \$1.2/call | — | — | `chat` | Default, SVIP |

xAI

| Model | Billing | Input | Output | Cache read | Endpoints | Groups | | --------------------------------- | ------- | ------ | ------ | ---------- | --------- | ------------- | | `grok-4.20-0309-non-reasoning` | usage | \$1.25 | \$2.5 | \$0.2 | `chat` | Default, SVIP | | `grok-4.20-0309-reasoning` | usage | \$1.25 | \$2.5 | \$0.2 | `chat` | Default, SVIP | | `grok-4.20-beta` | usage | \$1.25 | \$2.5 | — | `chat` | Default, SVIP | | `grok-4.20-multi-agent-0309` | usage | \$1.25 | \$2.5 | \$0.2 | `chat` | Default, SVIP | | `grok-4.20-multi-agent-beta-0309` | usage | \$1.25 | \$2.5 | — | `chat` | Default, SVIP | | `grok-4.3` † | usage | \$1.25 | \$2.5 | \$0.2 | `chat` | Default, SVIP | | `grok-4.5` † | usage | \$2 | \$6 | \$0.5 | `chat` | Default, SVIP | | `grok-build-0.1` | usage | \$1 | \$2 | \$0.2 | `chat` | Default, SVIP | | `grok-code-fast` | usage | \$0.2 | \$1.5 | — | `chat` | Default, SVIP | | `grok-code-fast-1` | usage | \$0.2 | \$1.5 | — | `chat` | Default, SVIP |

DeepSeek

| Model | Billing | Input | Output | Cache read | Endpoints | Groups | | ------------------------ | ------- | ------- | ------- | ---------- | ----------------- | ------------------------- | | `deepseek-chat` | usage | \$0.25 | \$1 | \$0.0625 | `chat` | Default, SVIP | | `deepseek-ocr` | usage | \$0.3 | \$0.6 | — | `chat` | Default, SVIP | | `deepseek-r1` | usage | \$0.57 | \$2.28 | \$0.1425 | `chat` | Default, SVIP | | `deepseek-r1-0528` | usage | \$0.57 | \$2.28 | — | `chat` | Default, SVIP | | `deepseek-r1-250528` | usage | \$0.57 | \$2.28 | — | `chat` | Default, SVIP | | `deepseek-reasoner` | usage | \$0.5 | \$2 | \$0.125 | `chat` | Default, SVIP | | `deepseek-v3` | usage | \$0.286 | \$1.144 | \$0.0715 | `chat` | Default, SVIP | | `deepseek-v3-0324` | usage | \$0.25 | \$1 | \$0.0625 | `chat` | Default, SVIP | | `deepseek-v3-1-250821` | usage | \$0.5 | \$1.5 | — | `chat` | Default, SVIP | | `deepseek-v3-20250324` | usage | \$0.25 | \$1 | — | `chat` | Default, SVIP | | `deepseek-v3-250324` | usage | \$0.25 | \$1 | — | `chat` | Default, SVIP | | `deepseek-v3.1` | usage | \$0.5 | \$1.5 | — | `chat` | Default, SVIP | | `deepseek-v3.1-terminus` | usage | \$0.5 | \$2 | — | `chat` | Default, SVIP | | `deepseek-v3.2` | usage | \$0.28 | \$0.42 | — | `chat` | Default, SVIP | | `deepseek-v3.2-exp` | usage | \$0.28 | \$0.42 | — | `chat` | Default, SVIP | | `deepseek-v4-flash` | usage | \$0.14 | \$0.28 | \$0.0028 | `chat` `messages` | ClaudeCode, Default, SVIP | | `deepseek-v4-pro` | usage | \$0.435 | \$0.87 | \$0.003625 | `chat` `messages` | ClaudeCode, Default, SVIP |

Alibaba

| Model | Billing | Input | Output | Cache read | Endpoints | Groups | | ---------------------------------- | -------- | ------------- | --------- | ---------- | ------------------- | ------------------------- | | `multimodal-embedding-v1` | per-call | \$0.0001/call | — | — | `chat` `embeddings` | Default, SVIP | | `qvq-max` | usage | \$1.2 | \$4.8 | — | `chat` | Default, SVIP | | `qvq-plus` | usage | \$0.28 | \$0.7 | — | `chat` | Default, SVIP | | `qwen-long` | usage | \$0.07 | \$0.28 | — | `chat` | Default, SVIP | | `qwen-max` | usage | \$1.6 | \$6.4 | — | `chat` | Default, SVIP | | `qwen-max-longcontext` | usage | \$3.2 | \$3.2 | — | `chat` | Default, SVIP | | `qwen-mt-plus` | usage | \$2 | \$8 | — | `chat` | Default, SVIP | | `qwen-mt-turbo` | usage | \$0.2 | \$0.5 | — | `chat` | Default, SVIP | | `qwen-plus` † | usage | \$0.4 | \$1.2 | — | `chat` | Default, SVIP | | `qwen-plus-2025-07-14` | usage | \$0.4 | \$4 | — | `chat` | Default, SVIP | | `qwen-plus-2025-09-11` † | usage | \$0.4 | \$4 | — | `chat` | Default, SVIP | | `qwen-plus-latest` † | usage | \$0.4 | \$1.2 | — | `chat` | Default, SVIP | | `qwen-turbo` | usage | \$0.2 | \$0.6 | — | `chat` | Default, SVIP | | `qwen-vl-max` | usage | \$0.2 | \$0.8 | — | `chat` | Default, SVIP | | `qwen-vl-ocr` | usage | \$0.72 | \$0.72 | — | `chat` | Default, SVIP | | `qwen-vl-ocr-2025-11-20` | usage | \$0.044 | \$0.07348 | — | `chat` | Default, SVIP | | `qwen-vl-ocr-latest` | usage | \$0.044 | \$0.07348 | — | `chat` | Default, SVIP | | `qwen-vl-plus` | usage | \$0.2 | \$0.6 | — | `chat` | Default, SVIP | | `qwen3-235b-a22b` | usage | \$1 | \$10 | — | `chat` | Default, SVIP | | `qwen3-235b-a22b-instruct-2507` | usage | \$1 | \$10 | — | `chat` | Default, SVIP | | `qwen3-235b-a22b-thinking-2507` | usage | \$1.6 | \$12.8 | — | `chat` | Default, SVIP | | `qwen3-30b-a3b` | usage | \$0.2 | \$2 | — | `chat` | Default, SVIP | | `qwen3-30b-a3b-instruct-2507` | usage | \$0.2 | \$0.8 | — | `chat` | Default, SVIP | | `qwen3-30b-a3b-thinking-2507` | usage | \$0.2 | \$2.4 | — | `chat` | Default, SVIP | | `qwen3-32b` | usage | \$0.4 | \$4 | — | `chat` | Default, SVIP | | `qwen3-coder-480b-a35b-instruct` † | usage | \$3 | \$15 | — | `chat` | Default, SVIP | | `qwen3-coder-flash` † | usage | \$0.5 | \$5 | — | `chat` | Default, SVIP | | `qwen3-coder-plus` † | usage | \$5 | \$20 | — | `chat` | Default, SVIP | | `qwen3-coder-plus-2025-07-22` † | usage | \$2 | \$20 | — | `chat` | Default, SVIP | | `qwen3-coder-plus-2025-09-23` † | usage | \$2 | \$20 | — | `chat` | Default, SVIP | | `qwen3-max` † | usage | \$1.2 | \$6 | — | `chat` | Default, SVIP | | `qwen3-max-2025-09-23` † | usage | \$1.2 | \$6 | — | `chat` | Default, SVIP | | `qwen3-max-preview` † | usage | \$1.2 | \$6 | — | `chat` | Default, SVIP | | `qwen3-next-80b-a3b-instruct` | usage | \$0.15 | \$1.2 | — | `chat` | Default, SVIP | | `qwen3-omni-flash` | usage | \$0.6 | \$6 | — | `chat` | Default, SVIP | | `qwen3-omni-flash-2025-09-15` | usage | \$2 | \$20 | — | `chat` | Default, SVIP | | `qwen3-vl-235b-a22b-instruct` | usage | \$0.3 | \$3 | — | `chat` | Default, SVIP | | `qwen3-vl-235b-a22b-thinking` | usage | \$0.3 | \$3 | — | `chat` | Default, SVIP | | `qwen3-vl-30b-a3b-thinking` | usage | \$0.12 | \$1.2 | — | `chat` | Default, SVIP | | `qwen3-vl-32b-thinking` | usage | \$0.3 | \$3 | — | `chat` | Default, SVIP | | `qwen3-vl-embedding` | per-call | \$0.0001/call | — | — | `chat` `embeddings` | Default, SVIP | | `qwen3-vl-flash` | usage | \$0.1 | \$0.8 | — | `chat` | Default, SVIP | | `qwen3-vl-flash-2025-10-15` | usage | \$0.1 | \$0.8 | — | `chat` | Default, SVIP | | `qwen3-vl-plus` † | usage | \$0.3 | \$2.4 | — | `chat` | Default, SVIP | | `qwen3-vl-plus-2025-09-23` † | usage | \$0.3 | \$2.4 | — | `chat` | Default, SVIP | | `qwen3.5-122b-a10b` | usage | \$0.12 | \$0.96 | — | `chat` | Default, SVIP | | `qwen3.5-27b` | usage | \$0.09 | \$0.72 | — | `chat` | Default, SVIP | | `qwen3.5-35b-a3b` | usage | \$0.06 | \$0.48 | — | `chat` | Default, SVIP | | `qwen3.5-397b-a17b` | usage | \$0.18 | \$1.08 | — | `chat` | Default, SVIP | | `qwen3.5-flash` † | usage | \$0.03 | \$0.3 | — | `chat` | Default, SVIP | | `qwen3.5-flash-2026-02-23` † | usage | \$0.03 | \$0.3 | — | `chat` | Default, SVIP | | `qwen3.5-omni-flash` | usage | \$0.35 | \$2 | — | `chat` | Default, SVIP | | `qwen3.5-omni-plus` | usage | \$1.2 | \$6 | — | `chat` | Default, SVIP | | `qwen3.5-plus` † | usage | \$0.114 | \$0.684 | — | `chat` | Default, SVIP | | `qwen3.5-plus-2026-02-15` † | usage | \$0.114 | \$0.684 | — | `chat` | Default, SVIP | | `qwen3.6-27b` | usage | \$0.42 | \$2.52 | — | `chat` | Default, SVIP | | `qwen3.6-35b-a3b` | usage | \$0.26 | \$1.56 | — | `chat` | Default, SVIP | | `qwen3.6-flash` † | usage | \$0.17 | \$1.02 | — | `chat` | Default, SVIP | | `qwen3.6-max-preview` † | usage | \$1.28 | \$7.68 | — | `chat` | Default, SVIP | | `qwen3.6-plus` † | usage | \$0.3 | \$1.8 | — | `chat` `messages` | ClaudeCode, Default, SVIP | | `qwen3.7-max` | usage | \$1.714 | \$5.142 | — | `chat` `messages` | ClaudeCode, Default, SVIP | | `qwen3.7-plus` † | usage | \$0.6 | \$2.4 | \$0.06 | `chat` `messages` | ClaudeCode, Default, SVIP | | `qwq-plus` | usage | \$0.8 | \$2.4 | — | `chat` | Default, SVIP | | `wan2.6-i2v` | usage | \$1.2 | \$1.2 | — | `chat` | Wan\&HappyHorse | | `wan2.6-r2v` | usage | \$75 | \$75 | — | `chat` | Wan\&HappyHorse | | `wan2.6-r2v-flash` | usage | \$75 | \$75 | — | `chat` | Wan\&HappyHorse | | `wan2.6-t2v` | usage | \$1.2 | \$1.2 | — | `chat` | Wan\&HappyHorse | | `wan2.7-i2v` | usage | \$0.1714 | \$0.1714 | — | `chat` | Wan\&HappyHorse | | `wan2.7-r2v` | usage | \$75 | \$75 | — | `chat` | Wan\&HappyHorse | | `wan2.7-t2v` | usage | \$0.1714 | \$0.1714 | — | `chat` | Wan\&HappyHorse | | `wan2.7-videoedit` | usage | \$75 | \$75 | — | `chat` | Wan\&HappyHorse |

ByteDance

| Model | Billing | Input | Output | Cache read | Endpoints | Groups | | --------------------------------- | -------- | ------------ | ------- | ---------- | --------- | ------------- | | `dola-seed-2-1-turbo-260628` | usage | \$0.5 | \$2.5 | \$0.1 | `chat` | Default, SVIP | | `doubao-seed-1-6-250615` | usage | \$0.1 | \$1 | — | `chat` | Default, SVIP | | `doubao-seed-1-6-251015` | usage | \$0.114 | \$0.285 | — | `chat` | Default, SVIP | | `doubao-seed-1-8-251228` | usage | \$0.25 | \$2 | — | `chat` | Default, SVIP | | `doubao-seedance-2-0-260128` | usage | \$46 | \$46 | — | `chat` | SeeDance2 | | `doubao-seedance-2-0-fast-260128` | usage | \$37 | \$37 | — | `chat` | SeeDance2 | | `doubao-seedance-2-0-mini-260615` | usage | \$23 | \$23 | — | `chat` | SeeDance2 | | `seed-1-6-250615` | usage | \$0.1 | \$1 | — | `chat` | Default, SVIP | | `seed-1-6-flash-250615` | usage | \$0.075 | \$0.3 | — | `chat` | Default, SVIP | | `seed-1-6-flash-250715` | usage | \$0.075 | \$0.3 | — | `chat` | Default, SVIP | | `seed-1-8-251228` | usage | \$0.25 | \$2 | — | `chat` | Default, SVIP | | `seed-2-0-code-preview-260328` | usage | \$0.5 | \$3 | — | `chat` | Default, SVIP | | `seed-2-0-lite-260228` † | usage | \$0.25 | \$2 | — | `chat` | Default, SVIP | | `seed-2-0-lite-260428` | usage | \$0.25 | \$2 | — | `chat` | Default, SVIP | | `seed-2-0-mini-260215` † | usage | \$0.1 | \$0.4 | — | `chat` | Default, SVIP | | `seed-2-0-mini-260428` | usage | \$0.1 | \$0.4 | — | `chat` | Default, SVIP | | `seed-2-0-pro-260328` † | usage | \$0.5 | \$3 | — | `chat` | Default, SVIP | | `seedream-4-0-250828` | per-call | \$0.035/call | — | — | `chat` | Default, SVIP | | `seedream-4-5-251128` | per-call | \$0.04/call | — | — | `chat` | Default, SVIP | | `seedream-5-0-260128` | per-call | \$0.035/call | — | — | `chat` | Default, SVIP | | `seedream-5-0-pro-260628` | per-call | \$0.12/call | — | — | `chat` | Default, SVIP |

Moonshot

| Model | Billing | Input | Output | Cache read | Endpoints | Groups | | ---------------------- | ------- | ------ | ------ | ---------- | ----------------- | ------------------------- | | `kimi-k2-0711-preview` | usage | \$0.8 | \$3.2 | \$0.08 | `chat` | Default, SVIP | | `kimi-k2-250711` | usage | \$0.8 | \$3.2 | \$0.08 | `chat` | Default, SVIP | | `kimi-k2.5` | usage | \$0.6 | \$3.15 | \$0.1 | `chat` `messages` | ClaudeCode, Default, SVIP | | `kimi-k2.6` | usage | \$0.6 | \$2.4 | \$0.101053 | `chat` `messages` | ClaudeCode, Default, SVIP | | `kimi-k2.7-code` | usage | \$0.95 | \$3.99 | \$0.19 | `chat` | ClaudeCode, Default, SVIP | | `kimi-k3` | usage | \$3 | \$15 | \$0.3 | `chat` | Default, SVIP |

Zhipu

| Model | Billing | Input | Output | Cache read | Endpoints | Groups | | ------------- | ------- | ------- | ------- | ---------- | ----------------- | ------------------------- | | `glm-4.5` | usage | \$0.5 | \$2 | \$0.05 | `chat` | Default, SVIP | | `glm-4.5-air` | usage | \$0.2 | \$1 | \$0.02 | `chat` | Default, SVIP | | `glm-4.5v` | usage | \$0.5 | \$1.5 | \$0.05 | `chat` | Default, SVIP | | `glm-4.6` | usage | \$0.5 | \$2 | \$0.05 | `chat` | Default, SVIP | | `glm-4.7` | usage | \$0.6 | \$2.16 | \$0.06 | `chat` `messages` | ClaudeCode, Default, SVIP | | `glm-5` † | usage | \$0.56 | \$2.52 | \$0.056 | `chat` `messages` | ClaudeCode, Default, SVIP | | `glm-5.1` † | usage | \$0.84 | \$3.36 | \$0.084 | `chat` `messages` | ClaudeCode, Default, SVIP | | `glm-5.2` | usage | \$1.142 | \$3.997 | \$0.2284 | `chat` | ClaudeCode, Default, SVIP |

MiniMax

| Model | Billing | Input | Output | Cache read | Endpoints | Groups | | ------------------------ | ------- | ----- | ------ | ---------- | ----------------- | ------------------------- | | `MiniMax-M2.1` | usage | \$0.3 | \$1.2 | — | `chat` | Default, SVIP | | `MiniMax-M2.5` | usage | \$0.3 | \$1.2 | — | `chat` | Default, SVIP | | `MiniMax-M2.5-lightning` | usage | \$0.3 | \$2.4 | — | `chat` | Default, SVIP | | `MiniMax-M2.7` | usage | \$0.3 | \$1.2 | — | `chat` `messages` | ClaudeCode, Default, SVIP | | `MiniMax-M2.7-highspeed` | usage | \$0.6 | \$2.4 | — | `chat` `messages` | ClaudeCode, Default, SVIP | | `MiniMax-M3` † | usage | \$0.3 | \$1.2 | \$0.06 | `chat` `messages` | ClaudeCode, Default, SVIP |

BAAI

| Model | Billing | Input | Output | Cache read | Endpoints | Groups | | -------------------- | ------- | ------ | ------ | ---------- | --------- | ------------- | | `bge-reranker-v2-m3` | usage | \$0.01 | \$0.01 | — | `chat` | Default, SVIP |

Black Forest Labs

| Model | Billing | Input | Output | Cache read | Endpoints | Groups | | -------------------- | -------- | ------------ | ------ | ---------- | --------------- | ------------- | | `flux-2-flex` | per-call | \$0.06/call | — | — | `images` `chat` | Default, SVIP | | `flux-2-klein-4b` | per-call | \$0.01/call | — | — | `images` `chat` | Default, SVIP | | `flux-2-klein-9b` | per-call | \$0.01/call | — | — | `images` `chat` | Default, SVIP | | `flux-2-max` | per-call | \$0.07/call | — | — | `images` `chat` | Default, SVIP | | `flux-2-pro` | per-call | \$0.03/call | — | — | `images` `chat` | Default, SVIP | | `flux-dev` | per-call | \$0.02/call | — | — | `images` `chat` | Default, SVIP | | `flux-kontext-max` | per-call | \$0.07/call | — | — | `images` `chat` | Default, SVIP | | `flux-kontext-pro` | per-call | \$0.035/call | — | — | `images` `chat` | Default, SVIP | | `flux-pro` | per-call | \$0.04/call | — | — | `images` `chat` | Default, SVIP | | `flux-pro-1.1` | per-call | \$0.035/call | — | — | `images` `chat` | Default, SVIP | | `flux-pro-1.1-ultra` | per-call | \$0.05/call | — | — | `images` `chat` | Default, SVIP |

HappyHorse

| Model | Billing | Input | Output | Cache read | Endpoints | Groups | | --------------------------- | ------- | ----- | ------ | ---------- | --------- | --------------- | | `happyhorse-1.0-video-edit` | usage | \$1.8 | \$1.8 | — | `chat` | Wan\&HappyHorse | | `happyhorse-1.1-i2v` | usage | \$1.8 | \$1.8 | — | `chat` | Wan\&HappyHorse | | `happyhorse-1.1-r2v` | usage | \$1.8 | \$1.8 | — | `chat` | Wan\&HappyHorse | | `happyhorse-1.1-t2v` | usage | \$1.8 | \$1.8 | — | `chat` | Wan\&HappyHorse |

Meituan

| Model | Billing | Input | Output | Cache read | Endpoints | Groups | | -------------------- | ------- | ------ | ------ | ---------- | --------- | ------------- | | `longcat-flash-chat` | usage | \$0.25 | \$0.5 | — | `chat` | Default, SVIP |

StepFun

| Model | Billing | Input | Output | Cache read | Endpoints | Groups | | ---------------- | ------- | ----- | ------ | ---------- | --------- | ------------- | | `step-3.5-flash` | usage | \$0.1 | \$0.3 | — | `chat` | Default, SVIP |

Xiaomi

| Model | Billing | Input | Output | Cache read | Endpoints | Groups | | --------------- | ------- | ----- | ------ | ---------- | --------- | ------------- | | `mimo-v2-omni` | usage | \$0.4 | \$2 | — | `chat` | Default, SVIP | | `mimo-v2-pro` † | usage | \$1 | \$3 | — | `chat` | Default, SVIP |

Tiered pricing

The following models are priced by per-request token volume (output price = tier input price × output multiplier): * **`gemini-2.5-pro`**: 0 – 200,000 tokens, input \$1.25/1M; above 200,000 tokens, input \$2.5/1M * **`gemini-3.1-pro-preview`**: 0 – 200,000 tokens, input \$1.8/1M; above 200,000 tokens, input \$3.6/1M (includes a standing discount — 90% of the nominal list tiers) * **`glm-5`**: 0 – 32,000 tokens, input \$0.56/1M; above 32,000 tokens, input \$0.86/1M * **`glm-5.1`**: 0 – 32,768 tokens, input \$0.84/1M; above 32,768 tokens, input \$1.14/1M * **`gpt-5.4`**: 0 – 278,528 tokens, input \$2.5/1M; above 278,528 tokens, input \$5/1M * **`gpt-5.4-pro`**: 0 – 278,528 tokens, input \$30/1M; above 278,528 tokens, input \$60/1M * **`gpt-5.5`**: 0 – 278,528 tokens, input \$5/1M; above 278,528 tokens, input \$10/1M * **`gpt-5.5-pro`**: 0 – 278,528 tokens, input \$30/1M; above 278,528 tokens, input \$60/1M * **`gpt-5.6-luna`**: 0 – 272,000 tokens, input \$1/1M; above 272,000 tokens, input \$2/1M * **`gpt-5.6-sol`**: 0 – 272,000 tokens, input \$5/1M; above 272,000 tokens, input \$10/1M * **`gpt-5.6-terra`**: 0 – 272,000 tokens, input \$2.5/1M; above 272,000 tokens, input \$5/1M * **`grok-4.3`**: 0 – 204,800 tokens, input \$1.25/1M; above 204,800 tokens, input \$2.5/1M * **`grok-4.5`**: 0 – 204,800 tokens, input \$2/1M; above 204,800 tokens, input \$4/1M * **`mimo-v2-pro`**: 0 – 262,144 tokens, input \$1/1M; 262,145 – 1,024,000 tokens, input \$2/1M * **`MiniMax-M3`**: 0 – 524,288 tokens, input \$0.3/1M; above 524,288 tokens, input \$0.6/1M (includes a standing discount — 50% of the nominal list tiers) * **`qwen-plus`**: 0 – 128,000 tokens, input \$0.4/1M; 128,001 – 256,000 tokens, input \$1.2/1M; 256,001 – 1,000,000 tokens, input \$2.4/1M (includes a standing discount — 50% of the nominal list tiers) * **`qwen-plus-2025-09-11`**: 0 – 128,000 tokens, input \$0.4/1M; 128,001 – 256,000 tokens, input \$1.2/1M; 256,001 – 1,000,000 tokens, input \$2.4/1M (includes a standing discount — 50% of the nominal list tiers) * **`qwen-plus-latest`**: 0 – 128,000 tokens, input \$0.4/1M; 128,001 – 256,000 tokens, input \$1.2/1M; 256,001 – 1,000,000 tokens, input \$2.4/1M (includes a standing discount — 50% of the nominal list tiers) * **`qwen3-coder-480b-a35b-instruct`**: 0 – 32,768 tokens, input \$3/1M; 32,769 – 131,072 tokens, input \$5.4/1M; 131,073 – 204,800 tokens, input \$9/1M * **`qwen3-coder-flash`**: 0 – 32,000 tokens, input \$0.5/1M; 32,001 – 128,000 tokens, input \$0.75/1M; 128,001 – 256,000 tokens, input \$1.25/1M; 256,001 – 1,000,000 tokens, input \$2.5/1M (includes a standing discount — 50% of the nominal list tiers) * **`qwen3-coder-plus`**: 0 – 32,000 tokens, input \$5/1M; 32,001 – 128,000 tokens, input \$7.5/1M; 128,001 – 256,000 tokens, input \$12.5/1M; 256,001 – 1,000,000 tokens, input \$25/1M * **`qwen3-coder-plus-2025-07-22`**: 0 – 32,000 tokens, input \$2/1M; 32,001 – 128,000 tokens, input \$3/1M; 128,001 – 256,000 tokens, input \$5/1M; 256,001 – 1,000,000 tokens, input \$10/1M (includes a standing discount — 50% of the nominal list tiers) * **`qwen3-coder-plus-2025-09-23`**: 0 – 32,000 tokens, input \$2/1M; 32,001 – 128,000 tokens, input \$3/1M; 128,001 – 256,000 tokens, input \$5/1M; 256,001 – 1,000,000 tokens, input \$10/1M (includes a standing discount — 50% of the nominal list tiers) * **`qwen3-max`**: 0 – 32,000 tokens, input \$1.2/1M; 32,001 – 128,000 tokens, input \$1.92/1M; 128,001 – 256,000 tokens, input \$3.36/1M (includes a standing discount — 48% of the nominal list tiers) * **`qwen3-max-2025-09-23`**: 0 – 32,000 tokens, input \$1.2/1M; 32,001 – 128,000 tokens, input \$2/1M; 128,001 – 256,000 tokens, input \$3/1M (includes a standing discount — 20% of the nominal list tiers) * **`qwen3-max-preview`**: 0 – 32,000 tokens, input \$1.2/1M; 32,001 – 128,000 tokens, input \$2/1M; 128,001 – 256,000 tokens, input \$3/1M (includes a standing discount — 20% of the nominal list tiers) * **`qwen3-vl-plus`**: 0 – 32,000 tokens, input \$0.3/1M; 32,001 – 128,000 tokens, input \$0.45/1M; 128,001 – 256,000 tokens, input \$0.9/1M (includes a standing discount — 30% of the nominal list tiers) * **`qwen3-vl-plus-2025-09-23`**: 0 – 32,000 tokens, input \$0.3/1M; 32,001 – 128,000 tokens, input \$0.45/1M; 128,001 – 256,000 tokens, input \$0.9/1M (includes a standing discount — 30% of the nominal list tiers) * **`qwen3.5-flash`**: 0 – 131,072 tokens, input \$0.03/1M; 131,073 – 262,144 tokens, input \$0.122143/1M; above 262,144 tokens, input \$0.182143/1M * **`qwen3.5-flash-2026-02-23`**: 0 – 131,072 tokens, input \$0.03/1M; 131,073 – 262,144 tokens, input \$0.122143/1M; above 262,144 tokens, input \$0.182143/1M * **`qwen3.5-plus`**: 0 – 131,072 tokens, input \$0.114/1M; 131,073 – 262,144 tokens, input \$0.28/1M; above 262,144 tokens, input \$0.56/1M * **`qwen3.5-plus-2026-02-15`**: 0 – 131,072 tokens, input \$0.114/1M; 131,073 – 262,144 tokens, input \$0.28/1M; above 262,144 tokens, input \$0.56/1M * **`qwen3.6-flash`**: 0 – 262,144 tokens, input \$0.17/1M; 262,145 – 1,024,000 tokens, input \$0.68/1M * **`qwen3.6-max-preview`**: 0 – 131,072 tokens, input \$1.28/1M; 131,073 – 262,144 tokens, input \$2.12/1M * **`qwen3.6-plus`**: 0 – 262,144 tokens, input \$0.3/1M; 262,145 – 1,024,000 tokens, input \$1.2/1M * **`qwen3.7-plus`**: 0 – 256,000 tokens, input \$0.6/1M; 256,001 – 1,000,000 tokens, input \$1.8/1M (includes a standing discount — 30% of the nominal list tiers) * **`seed-2-0-lite-260228`**: 0 – 131,072 tokens, input \$0.25/1M; 131,073 – 262,144 tokens, input \$0.5/1M * **`seed-2-0-mini-260215`**: 0 – 131,072 tokens, input \$0.1/1M; 131,073 – 262,144 tokens, input \$0.2/1M * **`seed-2-0-pro-260328`**: 0 – 131,072 tokens, input \$0.5/1M; 131,073 – 262,144 tokens, input \$1/1M Prices are subject to change; the console reflects live rates. See the API Capabilities section for per-model usage guides.