```json
{"data": [{"id": "route-llm", "name": "route-llm", "display_name": "RouteLLM", "description": "RouteLLM is a model that routes the user's message to the appropriate text-generation model. We will route to one of Sonnet 4.6, GPT-5.4, or Gemini 3.1 Flash models. The price shown is for the most expensive model (Sonnet 4.6) that we use.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.000003", "output_token_rate": "0.000015", "context_length": null, "max_completion_tokens": 64000, "api_formats": ["openai"], "featured": true, "top_model": true}, {"id": "claude-sonnet-5", "name": "claude-sonnet-5", "display_name": "Claude Sonnet 5", "description": "Claude Sonnet 5 from Anthropic is a balanced AI model, offering excellent performance in coding, reasoning, and general tasks with improved efficiency. It provides a strong balance between capability and cost, making it ideal for most use cases.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.000003", "output_token_rate": "0.000015", "context_length": 1000000, "max_completion_tokens": 64000, "thinking": true, "api_formats": ["openai", "anthropic"], "featured": true, "top_model": true, "agentic": true, "computer_use": true}, {"id": "gpt-5.6-terra", "name": "gpt-5.6-terra", "display_name": "GPT-5.6 Terra", "description": "GPT-5.6 Terra from OpenAI is a flagship model with advanced reasoning capabilities and a 1M context window.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.000002", "output_token_rate": "0.000012", "context_length": 1000000, "max_completion_tokens": 128000, "cached_input_token_rate": "0.0000002", "thinking": true, "api_formats": ["openai", "responses"], "featured": true, "top_model": true, "agentic": true, "computer_use": true}, {"id": "gemini-3.6-flash", "name": "gemini-3.6-flash", "display_name": "Gemini 3.6 Flash", "description": "Gemini 3.6 Flash from Google is an advanced multimodal reasoning model that delivers better coding, knowledge work, and multimodal performance with greater token efficiency than Gemini 3.5 Flash.", "model_type": "text_generation", "input_modalities": ["text", "image", "audio"], "output_modalities": ["text"], "input_token_rate": "0.0000015", "output_token_rate": "0.0000075", "context_length": 1048576, "max_completion_tokens": 65536, "cached_input_token_rate": "0.00000015", "thinking": true, "api_formats": ["openai"], "featured": true, "top_model": true, "agentic": true}, {"id": "gemini-3.5-flash", "name": "gemini-3.5-flash", "display_name": "Gemini 3.5 Flash", "description": "Gemini 3.5 Flash from Google is an advanced multimodal model designed for high-quality reasoning and efficiency. It offers strong performance across text, image, audio, and video tasks.", "model_type": "text_generation", "input_modalities": ["text", "image", "audio"], "output_modalities": ["text"], "input_token_rate": "0.0000015", "output_token_rate": "0.000009", "context_length": 1048576, "max_completion_tokens": 65536, "cached_input_token_rate": "0.00000015", "thinking": true, "api_formats": ["openai"], "featured": true, "top_model": true, "agentic": true}, {"id": "grok-4.5", "name": "grok-4.5", "display_name": "Grok 4.5", "description": "Grok 4.5, the latest frontier multimodal model from xAI with a 500K context window optimized for high-performance agentic tool calling. Reasoning is disabled.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.000002", "output_token_rate": "0.000006", "context_length": 500000, "max_completion_tokens": 32768, "cached_input_token_rate": "0.0000005", "thinking": true, "api_formats": ["openai", "responses"], "featured": true, "top_model": true, "agentic": true}, {"id": "claude-fable-5", "name": "claude-fable-5", "display_name": "Claude Fable 5", "description": "Claude Fable 5 from Anthropic is the next-generation Claude model, delivering major advances in coding, reasoning, and agentic tasks. It excels in tasks requiring long, complex reasoning chains, but is also expensive.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.00001", "output_token_rate": "0.00005", "context_length": 1000000, "max_completion_tokens": 128000, "thinking": true, "api_formats": ["openai", "anthropic"], "featured": true, "top_model": true, "agentic": true, "computer_use": true}, {"id": "gpt-5.6-sol", "name": "gpt-5.6-sol", "display_name": "GPT-5.6 Sol", "description": "GPT-5.6 Sol from OpenAI is a flagship model with advanced reasoning capabilities and a 1M context window.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.000005", "output_token_rate": "0.00003", "context_length": 1000000, "max_completion_tokens": 128000, "cached_input_token_rate": "0.0000005", "thinking": true, "api_formats": ["openai", "responses"], "featured": true, "top_model": true, "agentic": true, "computer_use": true}, {"id": "gemini-3.1-pro-preview", "name": "gemini-3.1-pro-preview", "display_name": "Gemini 3.1 Pro", "description": "Gemini 3.1 Pro", "model_type": "text_generation", "input_modalities": ["text", "image", "audio"], "output_modalities": ["text"], "input_token_rate": "0.000002", "output_token_rate": "0.000012", "context_length": 1048576, "max_completion_tokens": 65536, "cached_input_token_rate": "0.0000002", "thinking": true, "api_formats": ["openai"], "featured": true, "top_model": true, "agentic": true, "computer_use": true}, {"id": "claude-opus-5", "name": "claude-opus-5", "display_name": "Claude Opus 5", "description": "Claude Opus 5 from Anthropic is a highly capable AI model, focused on advanced coding, reasoning, and agentic tasks, with improved performance in multi-file code refactoring, debugging, and detail-oriented reasoning. It excels in tasks requiring long, complex reasoning chains, but is also expensive.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.000005", "output_token_rate": "0.000025", "context_length": 1000000, "max_completion_tokens": 128000, "thinking": true, "api_formats": ["openai", "anthropic"], "featured": true, "top_model": true, "agentic": true, "computer_use": true}, {"id": "claude-opus-4-8", "name": "claude-opus-4-8", "display_name": "Claude Opus 4.8", "description": "Claude Opus 4.8 from Anthropic is a highly capable AI model, focused on advanced coding, reasoning, and agentic tasks, with improved performance in multi-file code refactoring, debugging, and detail-oriented reasoning. It excels in tasks requiring long, complex reasoning chains, but is also expensive.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.000005", "output_token_rate": "0.000025", "context_length": 1000000, "max_completion_tokens": 128000, "thinking": true, "api_formats": ["openai", "anthropic"], "featured": true, "top_model": true, "agentic": true, "computer_use": true}, {"id": "gpt-5.5", "name": "gpt-5.5", "display_name": "GPT-5.5", "description": "GPT-5.5 from OpenAI is a flagship model with advanced reasoning capabilities and a 1M context window.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.000005", "output_token_rate": "0.00003", "context_length": 1000000, "max_completion_tokens": 128000, "cached_input_token_rate": "0.0000005", "thinking": true, "api_formats": ["openai", "responses"], "featured": true, "top_model": true, "agentic": true}, {"id": "gpt-5.6-luna", "name": "gpt-5.6-luna", "display_name": "GPT-5.6 Luna", "description": "GPT-5.6 Luna from OpenAI is a flagship model with advanced reasoning capabilities and a 1M context window.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.0000002", "output_token_rate": "0.0000012", "context_length": 1000000, "max_completion_tokens": 128000, "cached_input_token_rate": "0.00000002", "thinking": true, "api_formats": ["openai", "responses"], "featured": true, "top_model": true, "agentic": true, "computer_use": true}, {"id": "muse-spark-1.1", "name": "muse-spark-1.1", "display_name": "Muse Spark 1.1", "description": "Muse Spark 1.1 is Meta's natively multimodal reasoning model with a 1,000,000 token context window, built for agentic tasks with native tool use, parallel tool calling, and strong coding performance.", "model_type": "text_generation", "input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "input_token_rate": "0.00000125", "output_token_rate": "0.00000425", "context_length": 1000000, "max_completion_tokens": 131072, "cached_input_token_rate": "0.00000015", "thinking": true, "api_formats": ["openai"], "featured": true, "top_model": true}, {"id": "gpt-5.4-mini", "name": "gpt-5.4-mini", "display_name": "GPT-5.4 Mini", "description": "GPT-5.4 Mini", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.00000075", "output_token_rate": "0.0000045", "context_length": 400000, "max_completion_tokens": 128000, "cached_input_token_rate": "0.000000075", "thinking": true, "api_formats": ["openai", "responses"], "featured": true, "top_model": true}, {"id": "grok-4.3", "name": "grok-4.3", "display_name": "Grok 4.3", "description": "Grok 4.3, the latest frontier multimodal model from xAI with a 1M context window optimized for high-performance agentic tool calling. Reasoning is disabled.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.00000125", "output_token_rate": "0.0000025", "context_length": 1000000, "max_completion_tokens": 32768, "cached_input_token_rate": "0.0000002", "thinking": true, "api_formats": ["openai", "responses"], "featured": true, "top_model": true}, {"id": "moonshotai/Kimi-K3", "name": "moonshotai/Kimi-K3", "display_name": "Kimi K3", "description": "Kimi K3 is Moonshot AI's flagship open-weight multimodal reasoning model with a 1M-token context window, built for long-horizon coding, agentic workflows, and end-to-end knowledge work.", "model_type": "text_generation", "input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "input_token_rate": "0.000003", "output_token_rate": "0.000015", "context_length": 1048576, "max_completion_tokens": 131072, "cached_input_token_rate": "0.0000003", "api_formats": ["openai"], "featured": true, "top_model": true, "agentic": true}, {"id": "moonshotai/Kimi-K2.7-Code", "name": "moonshotai/Kimi-K2.7-Code", "display_name": "Kimi K2.7 Code", "description": "Kimi K2.7 Code is Kimi's most capable coding model to date. It follows instructions more reliably in long contexts and completes coding tasks with higher success rates.", "model_type": "text_generation", "input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "input_token_rate": "0.00000095", "output_token_rate": "0.000004", "context_length": 262144, "max_completion_tokens": 262144, "cached_input_token_rate": "0.00000019", "api_formats": ["openai"], "featured": true, "top_model": true, "agentic": true}, {"id": "zai-org/GLM-5.2", "name": "zai-org/GLM-5.2", "display_name": "GLM 5.2", "description": "GLM-5.2 from Z.AI is a flagship model excelling at long-horizon autonomous tasks with a 1M token context window, strong coding and agentic capabilities.", "model_type": "text_generation", "input_modalities": ["text"], "output_modalities": ["text"], "input_token_rate": "0.0000014", "output_token_rate": "0.0000044", "context_length": 1048576, "max_completion_tokens": 131072, "cached_input_token_rate": "0.00000026", "api_formats": ["openai"], "featured": true, "top_model": true, "agentic": true}, {"id": "deepseek-ai/DeepSeek-V4-Pro", "name": "deepseek-ai/DeepSeek-V4-Pro", "display_name": "Deepseek V4 Pro", "description": "DeepSeek V4 Pro is an advanced, high-performance large language model (LLM) developed by DeepSeek.", "model_type": "text_generation", "input_modalities": ["text"], "output_modalities": ["text"], "input_token_rate": "0.00000174", "output_token_rate": "0.00000348", "context_length": 1000000, "max_completion_tokens": 384000, "cached_input_token_rate": "0.00000015", "thinking": true, "api_formats": ["openai"], "featured": true, "top_model": true, "agentic": true}, {"id": "deepseek-ai/DeepSeek-V4-Flash", "name": "deepseek-ai/DeepSeek-V4-Flash", "display_name": "Deepseek V4 Flash", "description": "DeepSeek V4 Flash is an advanced, high-performance large language model (LLM) developed by DeepSeek.", "model_type": "text_generation", "input_modalities": ["text"], "output_modalities": ["text"], "input_token_rate": "0.00000014", "output_token_rate": "0.00000028", "context_length": 1000000, "max_completion_tokens": 384000, "cached_input_token_rate": "0.00000003", "thinking": true, "api_formats": ["openai"], "featured": true, "top_model": true}, {"id": "claude-haiku-4-5-20251001", "name": "claude-haiku-4-5-20251001", "display_name": "Claude Haiku 4.5", "description": "Claude Haiku 4.5", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.000001", "output_token_rate": "0.000005", "context_length": 200000, "max_completion_tokens": 64000, "thinking": true, "api_formats": ["openai", "anthropic"], "featured": true, "top_model": true}, {"id": "gpt-5.4-nano", "name": "gpt-5.4-nano", "display_name": "GPT-5.4 Nano", "description": "GPT-5.4 Nano", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.0000002", "output_token_rate": "0.00000125", "context_length": 400000, "max_completion_tokens": 128000, "cached_input_token_rate": "0.00000002", "api_formats": ["openai"], "featured": true, "top_model": true}, {"id": "gemini-3.5-flash-lite", "name": "gemini-3.5-flash-lite", "display_name": "Gemini 3.5 Flash Lite", "description": "Gemini 3.5 Flash Lite from Google is the fastest and most cost-effective Gemini 3.5 series model, built for high-throughput, low-latency workloads like agentic search and document processing.", "model_type": "text_generation", "input_modalities": ["text", "image", "audio"], "output_modalities": ["text"], "input_token_rate": "0.0000003", "output_token_rate": "0.0000025", "context_length": 1048576, "max_completion_tokens": 65536, "cached_input_token_rate": "0.00000003", "thinking": true, "api_formats": ["openai"], "featured": true, "top_model": true}, {"id": "gemini-3.1-flash-lite", "name": "gemini-3.1-flash-lite", "display_name": "Gemini 3.1 Flash Lite", "description": "Gemini 3.1 Flash Lite from Google is a fast and cost-efficient Gemini 3 series model, built for high-volume developer workloads at scale.", "model_type": "text_generation", "input_modalities": ["text", "image", "audio"], "output_modalities": ["text"], "input_token_rate": "0.00000025", "output_token_rate": "0.0000015", "context_length": 1048576, "max_completion_tokens": 65536, "cached_input_token_rate": "0.000000025", "thinking": true, "api_formats": ["openai"], "featured": true, "top_model": true}, {"id": "gemini-3-flash-preview", "name": "gemini-3-flash-preview", "display_name": "Gemini 3 Flash", "description": "Gemini 3 Flash from Google is an advanced large language model. It is designed for efficiency while balancing reasoning capabilities.", "model_type": "text_generation", "input_modalities": ["text", "image", "audio"], "output_modalities": ["text"], "input_token_rate": "0.0000005", "output_token_rate": "0.000003", "context_length": 1048576, "max_completion_tokens": 65536, "cached_input_token_rate": "0.00000005", "thinking": true, "api_formats": ["openai"], "featured": true, "top_model": true}, {"id": "claude-sonnet-4-6", "name": "claude-sonnet-4-6", "display_name": "Claude Sonnet 4.6", "description": "Claude Sonnet 4.6 from Anthropic is a balanced AI model, offering excellent performance in coding, reasoning, and general tasks with improved efficiency. It provides a strong balance between capability and cost, making it ideal for most use cases.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.000003", "output_token_rate": "0.000015", "context_length": 1000000, "max_completion_tokens": 64000, "thinking": true, "api_formats": ["openai", "anthropic"], "featured": true, "top_model": true, "agentic": true, "computer_use": true}, {"id": "gpt-5.4", "name": "gpt-5.4", "display_name": "GPT-5.4", "description": "GPT-5.4", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.0000025", "output_token_rate": "0.000015", "context_length": 400000, "max_completion_tokens": 128000, "cached_input_token_rate": "0.00000025", "thinking": true, "api_formats": ["openai", "responses"], "featured": true, "top_model": true, "agentic": true}, {"id": "thinkingmachines/Inkling", "name": "thinkingmachines/Inkling", "display_name": "Tinker Inkling", "description": "Inkling is Thinking Machines Lab's first open-weights model, a 975B-parameter mixture-of-experts (41B active) that reasons across text and images, served with a 262,144 token context window. Supports tools and streaming.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.00000374", "output_token_rate": "0.00000936", "context_length": 262144, "max_completion_tokens": 131072, "cached_input_token_rate": "0.000000748", "thinking": true, "api_formats": ["openai"], "featured": false}, {"id": "mimo-v2-pro", "name": "mimo-v2-pro", "display_name": "MiMo V2 Pro", "description": "Xiaomi MiMo V2 Pro is Xiaomi's flagship reasoning model with a 1M token context window and 128K max output. Supports reasoning via  tags, tool use, structured output, and speculative decoding for fast inference.", "model_type": "text_generation", "input_modalities": ["text"], "output_modalities": ["text"], "input_token_rate": "0.000001", "output_token_rate": "0.000003", "context_length": 1048576, "max_completion_tokens": 131072, "cached_input_token_rate": "0.0000002", "api_formats": ["openai"], "featured": false}, {"id": "MiniMaxAI/MiniMax-M3", "name": "MiniMaxAI/MiniMax-M3", "display_name": "MiniMax M3", "description": "MiniMax M3 is MiniMax's latest flagship reasoning model with a 1,000,000 token context window and 131,072 max output tokens. Supports tools, structured output, and reasoning.", "model_type": "text_generation", "input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "input_token_rate": "0.0000003", "output_token_rate": "0.0000012", "context_length": 1000000, "max_completion_tokens": 131072, "api_formats": ["openai"], "featured": false}, {"id": "MiniMaxAI/MiniMax-M2.7", "name": "MiniMaxAI/MiniMax-M2.7", "display_name": "MiniMax M2.7", "description": "MiniMax M2.7 is MiniMax's flagship text model with a 204,800 token context window. ~60 tokens/sec output. Supports tools, streaming, and JSON mode.", "model_type": "text_generation", "input_modalities": ["text"], "output_modalities": ["text"], "input_token_rate": "0.0000003", "output_token_rate": "0.0000012", "context_length": 204800, "max_completion_tokens": 131072, "api_formats": ["openai"], "featured": false}, {"id": "google/gemma-4-31b-it", "name": "google/gemma-4-31b-it", "display_name": "Gemma 4 31B IT", "description": "Gemma 4 31B IT is Google's open-weight vision-language model with a 256K context window. It supports interleaved text and image inputs, structured output, function calling, and reasoning tasks.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.00000014", "output_token_rate": "0.0000004", "context_length": 262144, "max_completion_tokens": 131072, "api_formats": ["openai"], "featured": false}, {"id": "zai-org/GLM-5.1", "name": "zai-org/GLM-5.1", "display_name": "GLM 5.1", "description": "GLM-5.1 from Z.AI is a flagship model featuring enhanced capabilities in reasoning, code generation, and agent alignment.", "model_type": "text_generation", "input_modalities": ["text"], "output_modalities": ["text"], "input_token_rate": "0.0000014", "output_token_rate": "0.0000044", "context_length": 204800, "max_completion_tokens": 131072, "cached_input_token_rate": "0.00000026", "api_formats": ["openai"], "featured": false}, {"id": "zai-org/GLM-5", "name": "zai-org/GLM-5", "display_name": "GLM 5", "description": "GLM-5 from Z.AI is a flagship model featuring enhanced capabilities in reasoning, code generation, and agent alignment.", "model_type": "text_generation", "input_modalities": ["text"], "output_modalities": ["text"], "input_token_rate": "0.000001", "output_token_rate": "0.0000032", "context_length": 204800, "max_completion_tokens": 131072, "api_formats": ["openai"], "featured": false}, {"id": "zai-org/GLM-4.7", "name": "zai-org/GLM-4.7", "display_name": "GLM 4.7", "description": "GLM-4.7 from Z.AI is a flagship model featuring enhanced programming capabilities and stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while delivering more natural conversational experiences and superior front-end aesthetics.", "model_type": "text_generation", "input_modalities": ["text"], "output_modalities": ["text"], "input_token_rate": "0.0000006", "output_token_rate": "0.0000022", "context_length": 204800, "max_completion_tokens": 131072, "api_formats": ["openai"], "featured": false}, {"id": "zai-org/GLM-4.6", "name": "zai-org/GLM-4.6", "display_name": "GLM 4.6", "description": "GLM-4.6 from Z.AI is a flagship model with a 128k context window, better coding and agentic performance and more refined writing", "model_type": "text_generation", "input_modalities": ["text"], "output_modalities": ["text"], "input_token_rate": "0.0000006", "output_token_rate": "0.0000022", "context_length": 202752, "max_completion_tokens": 131072, "api_formats": ["openai"], "featured": false}, {"id": "zai-org/GLM-4.5", "name": "zai-org/GLM-4.5", "display_name": "GLM 4.5", "description": "GLM-4.5 from Z.AI is a flagship model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly enhanced capabilities in reasoning, code generation, and agent alignment. It supports a hybrid inference mode with two options, a \"thinking mode\" designed for complex reasoning and tool use, and a \"non-thinking mode\" optimized for instant responses. ", "model_type": "text_generation", "input_modalities": ["text"], "output_modalities": ["text"], "input_token_rate": "0.0000006", "output_token_rate": "0.0000022", "context_length": 131072, "max_completion_tokens": 96000, "api_formats": ["openai"], "featured": false}, {"id": "deepseek-ai/DeepSeek-V3.2", "name": "deepseek-ai/DeepSeek-V3.2", "display_name": "Deepseek V3.2", "description": "DeepSeek-V3.2-Exp is an intermediate step toward the next-generation architecture of the DeepSeek models by introducing DeepSeek Sparse Attention - a sparse attention mechanism designed to explore and validate optimizations for training and inference efficiency in long-context scenarios.", "model_type": "text_generation", "input_modalities": ["text"], "output_modalities": ["text"], "input_token_rate": "0.00000027", "output_token_rate": "0.0000004", "context_length": 131072, "max_completion_tokens": 65536, "api_formats": ["openai"], "featured": false}, {"id": "moonshotai/Kimi-K2.6", "name": "moonshotai/Kimi-K2.6", "display_name": "Kimi K2.6", "description": "Kimi K2.6 is a natively multimodal model with powerful coding capabilities and enhanced agent performance. It builds on the K2.5 foundation with improved reasoning depth, cleaner agent planning, and faster multi-step tool call reliability.", "model_type": "text_generation", "input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "input_token_rate": "0.00000095", "output_token_rate": "0.000004", "context_length": 262144, "max_completion_tokens": 262144, "cached_input_token_rate": "0.00000019", "thinking": true, "api_formats": ["openai"], "featured": false}, {"id": "moonshotai/Kimi-K2-Instruct", "name": "moonshotai/Kimi-K2-Instruct", "display_name": "Kimi K2 Turbo", "description": "Context length 256k. High-speed version of kimi-k2, always aligned with the latest kimi-k2 (kimi-k2-0905-preview). Same model parameters as kimi-k2, output speed up to 60 tokens/sec (max 100 tokens/sec)", "model_type": "text_generation", "input_modalities": ["text"], "output_modalities": ["text"], "input_token_rate": "0.00000015", "output_token_rate": "0.000008", "context_length": 262144, "max_completion_tokens": 65536, "thinking": true, "api_formats": ["openai"], "featured": false}, {"id": "Qwen/Qwen3.6-27B", "name": "Qwen/Qwen3.6-27B", "display_name": "Qwen3.6 27B", "description": "Qwen3.6 27B is an open-weight dense 27B-parameter model from Alibaba's Qwen3.6 series, delivering flagship-level coding and reasoning performance in a compact package. It supports a 256K context window and is well suited for software development, multilingual tasks, and tool-calling workflows.", "model_type": "text_generation", "input_modalities": ["text"], "output_modalities": ["text"], "input_token_rate": "0.00000032", "output_token_rate": "0.0000032", "context_length": 262144, "max_completion_tokens": 8192, "api_formats": ["openai"], "featured": false}, {"id": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "name": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "display_name": "Qwen3 Coder", "description": "Qwen3-Coder is a powerful, open-source, agentic coding model by Alibaba, known for its great ability to generate code from natural language, debug code, and interact with tools", "model_type": "text_generation", "input_modalities": ["text"], "output_modalities": ["text"], "input_token_rate": "0.00000029", "output_token_rate": "0.0000012", "context_length": 262144, "max_completion_tokens": 16384, "api_formats": ["openai"], "featured": false}, {"id": "Qwen/Qwen3-32B", "name": "Qwen/Qwen3-32B", "display_name": "Qwen3 32B", "description": "Qwen3-32B is a dense 32.8 billion parameter model by Alibaba. The model shows strong performance in reasoning tasks and is optimized for agentic applications, supporting tool-calling and external tool integration.", "model_type": "text_generation", "input_modalities": ["text"], "output_modalities": ["text"], "input_token_rate": "0.00000009", "output_token_rate": "0.00000029", "context_length": 131072, "max_completion_tokens": 8192, "api_formats": ["openai"], "featured": false}, {"id": "gemini-3.1-flash-image", "name": "gemini-3.1-flash-image", "display_name": "Nano Banana 2 (Gemini 3.1 Flash Image)", "description": "Nano Banana 2 (Gemini 3.1 Flash Image)", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text", "image"], "input_token_rate": "0.0000005", "output_token_rate": "0.000003", "context_length": 1048576, "max_completion_tokens": 32768, "api_formats": ["openai"], "featured": false}, {"id": "gemini-3-pro-image", "name": "gemini-3-pro-image", "display_name": "Nano Banana (Gemini 3 Pro Image)", "description": "Nano Banana (Gemini 3 Pro Image)", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text", "image"], "input_token_rate": "0.000002", "output_token_rate": "0.000012", "context_length": 65536, "max_completion_tokens": 32768, "cached_input_token_rate": "0.0000002", "api_formats": ["openai"], "featured": false}, {"id": "gemini-2.5-flash-image", "name": "gemini-2.5-flash-image", "display_name": "Nano Banana (Gemini 2.5 Flash Image)", "description": "Nano Banana (Gemini 2.5 Flash Image)", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text", "image"], "input_token_rate": "0.0000003", "output_token_rate": "0.00003", "context_length": 32768, "max_completion_tokens": 32768, "api_formats": ["openai"], "featured": false}, {"id": "gemini-2.5-flash", "name": "gemini-2.5-flash", "display_name": "Gemini 2.5 Flash", "description": "Gemini 2.5 Flash is a large multimodal language model from Google. It is designed for speed, efficiency, and cost-effectiveness in AI tasks that require high volume and frequency.", "model_type": "text_generation", "input_modalities": ["text", "image", "audio"], "output_modalities": ["text"], "input_token_rate": "0.0000003", "output_token_rate": "0.0000025", "context_length": 1048576, "max_completion_tokens": 65536, "cached_input_token_rate": "0.00000003", "thinking": true, "api_formats": ["openai"], "featured": false}, {"id": "gemini-2.5-pro", "name": "gemini-2.5-pro", "display_name": "Gemini 2.5 Pro", "description": "Gemini 2.5 Pro is Google's advanced large language model. It is designed for complex tasks that require deep reasoning, advanced coding, and multimodal understanding.", "model_type": "text_generation", "input_modalities": ["text", "image", "audio"], "output_modalities": ["text"], "input_token_rate": "0.00000125", "output_token_rate": "0.00001", "context_length": 1048576, "max_completion_tokens": 65536, "cached_input_token_rate": "0.000000125", "thinking": true, "api_formats": ["openai"], "featured": false}, {"id": "meta-llama/Meta-Llama-3.3-70B-Instruct", "name": "meta-llama/Meta-Llama-3.3-70B-Instruct", "display_name": "Llama 3.3 70B", "description": "Llama 3.3 70B", "model_type": "text_generation", "input_modalities": ["text"], "output_modalities": ["text"], "input_token_rate": "0.00000059", "output_token_rate": "0.00000079", "context_length": 131072, "max_completion_tokens": 8192, "api_formats": ["openai"], "featured": false}, {"id": "meta-llama/Meta-Llama-3.1-8B-Instruct", "name": "meta-llama/Meta-Llama-3.1-8B-Instruct", "display_name": "Llama 3.1 8B", "description": "Llama 3.1 8B is a powerful, multilingual open-source large language model developed by Meta. It is very fast and cheap.", "model_type": "text_generation", "input_modalities": ["text"], "output_modalities": ["text"], "input_token_rate": "0.00000002", "output_token_rate": "0.00000005", "context_length": 131072, "max_completion_tokens": 8192, "api_formats": ["openai"], "featured": false}, {"id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "name": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "display_name": "Llama 4 Maverick", "description": "Llama 4 Maverick is a is an advanced, natively multimodal large language model (LLM) developed by Meta. It delivers strong performance across tasks like natural language processing, coding, image recognition, and multimodal reasoning.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.00000014", "output_token_rate": "0.00000059", "context_length": 1048576, "max_completion_tokens": 8192, "api_formats": ["openai"], "featured": false}, {"id": "claude-opus-4-7", "name": "claude-opus-4-7", "display_name": "Claude Opus 4.7", "description": "Claude Opus 4.7 from Anthropic is a highly capable AI model, focused on advanced coding, reasoning, and agentic tasks, with improved performance in multi-file code refactoring, debugging, and detail-oriented reasoning. It excels in tasks requiring long, complex reasoning chains, but is also expensive.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.000005", "output_token_rate": "0.000025", "context_length": 1000000, "max_completion_tokens": 128000, "thinking": true, "api_formats": ["openai", "anthropic"], "featured": false, "agentic": true, "computer_use": true}, {"id": "claude-opus-4-6", "name": "claude-opus-4-6", "display_name": "Claude Opus 4.6", "description": "Claude Opus 4.6 from Anthropic is a highly capable AI model, focused on advanced coding, reasoning, and agentic tasks, with improved performance in multi-file code refactoring, debugging, and detail-oriented reasoning. It excels in tasks requiring long, complex reasoning chains, but is also expensive.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.000005", "output_token_rate": "0.000025", "context_length": 1000000, "max_completion_tokens": 128000, "thinking": true, "api_formats": ["openai", "anthropic"], "featured": false, "agentic": true, "computer_use": true}, {"id": "claude-opus-4-5-20251101", "name": "claude-opus-4-5-20251101", "display_name": "Claude Opus 4.5", "description": "Claude Opus 4.5 from Anthropic is an AI model focused on advanced coding, reasoning, and agentic tasks, with improved performance in multi-file code refactoring, debugging, and detail-oriented reasoning. It excels in tasks requiring long, complex reasoning chains, but is also expensive.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.000005", "output_token_rate": "0.000025", "context_length": 200000, "max_completion_tokens": 64000, "thinking": true, "api_formats": ["openai", "anthropic"], "featured": false}, {"id": "claude-sonnet-4-5-20250929", "name": "claude-sonnet-4-5-20250929", "display_name": "Claude Sonnet 4.5", "description": "Claude Sonnet 4.5 advances over its predecessor, Sonnet 4, delivering stronger coding and reasoning performance with greater precision and control. Makes agentic programming better. It excels in tasks requiring long, complex reasoning chains, but is also expensive.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.000003", "output_token_rate": "0.000015", "context_length": 200000, "max_completion_tokens": 64000, "thinking": true, "api_formats": ["openai", "anthropic"], "featured": false}, {"id": "openai/gpt-oss-120b", "name": "openai/gpt-oss-120b", "display_name": "GPT-OSS 120B", "description": "GPT-OSS from OpenAI is a powerful, open-weight language model designed for high-reasoning, agentic tasks. It supports advanced capabilities like configurable reasoning effort levels, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.", "model_type": "text_generation", "input_modalities": ["text"], "output_modalities": ["text"], "input_token_rate": "0.00000008", "output_token_rate": "0.00000044", "context_length": 128000, "max_completion_tokens": 16384, "api_formats": ["openai"], "featured": false}, {"id": "gpt-5.3-codex", "name": "gpt-5.3-codex", "display_name": "GPT-5.3 Codex", "description": "GPT-5.3 Codex", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.00000175", "output_token_rate": "0.000014", "context_length": 400000, "max_completion_tokens": 128000, "cached_input_token_rate": "0.00000018", "api_formats": ["openai", "responses"], "featured": false}, {"id": "gpt-5.2", "name": "gpt-5.2", "display_name": "GPT-5.2", "description": "GPT-5.2", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.00000175", "output_token_rate": "0.000014", "context_length": 400000, "max_completion_tokens": 128000, "cached_input_token_rate": "0.000000175", "thinking": true, "api_formats": ["openai", "responses"], "featured": false}, {"id": "gpt-5.1", "name": "gpt-5.1", "display_name": "GPT-5.1", "description": "GPT-5.1", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.00000125", "output_token_rate": "0.00001", "context_length": 400000, "max_completion_tokens": 128000, "cached_input_token_rate": "0.000000125", "thinking": true, "api_formats": ["openai", "responses"], "featured": false}, {"id": "gpt-5-nano", "name": "gpt-5-nano", "display_name": "GPT-5 Nano", "description": "GPT-5 Nano is the fastest and cheapest model in the GPT-5 family. It is a good model for summarization and classification tasks.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.00000005", "output_token_rate": "0.0000004", "context_length": 400000, "max_completion_tokens": 128000, "cached_input_token_rate": "0.000000005", "api_formats": ["openai", "responses"], "featured": false}, {"id": "gpt-5-mini", "name": "gpt-5-mini", "display_name": "GPT-5 Mini", "description": "GPT-5 Mini is a streamlined variant of GPT-5 built for lighter reasoning workloads. It delivers GPT-5 instruction adherence and safety tuning while offering lower latency and cost.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.00000025", "output_token_rate": "0.000002", "context_length": 400000, "max_completion_tokens": 128000, "cached_input_token_rate": "0.000000025", "api_formats": ["openai", "responses"], "featured": false}, {"id": "gpt-5", "name": "gpt-5", "display_name": "GPT-5", "description": "GPT-5 from OpenAI is an advanced model, delivering significant gains in reasoning, code generation quality, and overall user experience. It is a very good model for coding and agentic tasks across industries.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.00000125", "output_token_rate": "0.00001", "context_length": 400000, "max_completion_tokens": 128000, "cached_input_token_rate": "0.000000125", "api_formats": ["openai", "responses"], "featured": false}, {"id": "gpt-4.1-nano", "name": "gpt-4.1-nano", "display_name": "GPT-4.1 Nano", "description": "GPT-4.1 Nano is the smallest and cheapest model in the GPT-4.1 family, ideal for basic tasks and low-resource applications.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.0000001", "output_token_rate": "0.0000004", "context_length": 1047576, "max_completion_tokens": 32768, "cached_input_token_rate": "0.000000025", "api_formats": ["openai"], "featured": false}, {"id": "gpt-4.1-mini", "name": "gpt-4.1-mini", "display_name": "GPT-4.1 Mini", "description": "GPT-4.1 Mini is a smaller, faster, and cheaper version of GPT-4.1, designed for lightweight tasks and lower latency requirements.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.0000004", "output_token_rate": "0.0000016", "context_length": 1047576, "max_completion_tokens": 32768, "cached_input_token_rate": "0.0000001", "api_formats": ["openai"], "featured": false}, {"id": "gpt-4.1", "name": "gpt-4.1", "display_name": "GPT-4.1", "description": "GPT-4.1 is designed to be faster, cheaper, and more reliable for specific tasks compared to the o-series models, especially for coding and tool-based operations.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.000002", "output_token_rate": "0.000008", "context_length": 1047576, "max_completion_tokens": 32768, "cached_input_token_rate": "0.0000005", "api_formats": ["openai"], "featured": false}, {"id": "o3-mini", "name": "o3-mini", "display_name": "o3 Mini", "description": "o3 Mini", "model_type": "text_generation", "input_modalities": ["text"], "output_modalities": ["text"], "input_token_rate": "0.0000011", "output_token_rate": "0.0000044", "context_length": 200000, "max_completion_tokens": 100000, "cached_input_token_rate": "0.00000055", "api_formats": ["openai", "responses"], "featured": false}, {"id": "o3", "name": "o3", "display_name": "o3", "description": "O3 is  advance reasoning models, designed for tackling complex tasks requiring deep analytical thinking and problem-solving.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.000002", "output_token_rate": "0.000008", "context_length": 200000, "max_completion_tokens": 100000, "cached_input_token_rate": "0.0000005", "api_formats": ["openai", "responses"], "featured": false}, {"id": "o3-pro", "name": "o3-pro", "display_name": "o3 Pro", "description": "o3 Pro", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.00002", "output_token_rate": "0.00004", "context_length": 200000, "max_completion_tokens": 100000, "api_formats": ["openai", "responses"], "featured": false}, {"id": "o4-mini", "name": "o4-mini", "display_name": "o4 Mini", "description": "OpenAI o4-mini is a compact, efficient, and cost-effective model in the OpenAI o-series, which emphasizes reasoning capabilities.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.0000011", "output_token_rate": "0.0000044", "context_length": 200000, "max_completion_tokens": 100000, "api_formats": ["openai"], "featured": false}, {"id": "gpt-realtime-whisper", "name": "gpt-realtime-whisper", "display_name": "GPT Realtime Whisper", "description": "GPT Realtime Whisper", "model_type": "text_generation", "input_modalities": ["text"], "output_modalities": ["text"], "input_token_rate": "0.0002833333", "output_token_rate": "0", "context_length": 16000, "max_completion_tokens": 2000, "api_formats": ["openai"], "featured": false}, {"id": "gpt-4o-mini-transcribe", "name": "gpt-4o-mini-transcribe", "display_name": "GPT 4o Mini Transcribe", "description": "GPT 4o Mini Transcribe", "model_type": "text_generation", "input_modalities": ["text"], "output_modalities": ["text"], "input_token_rate": "0.00000125", "output_token_rate": "0.000005", "context_length": 16000, "max_completion_tokens": 2000, "api_formats": ["openai"], "featured": false}, {"id": "gpt-4o-mini", "name": "gpt-4o-mini", "display_name": "GPT-4o Mini", "description": "GPT-4o mini is a highly efficient and cost-effective small language model. t excels in instruction following, multimodal reasoning, and supports a 128k context window.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.00000015", "output_token_rate": "0.0000006", "context_length": 128000, "max_completion_tokens": 16384, "api_formats": ["openai"], "featured": false}, {"id": "gpt-4o", "name": "gpt-4o", "display_name": "GPT-4o", "description": "GPT-4o from OpenAI is an advanced multimodal AI model that can seamlessly process and generate content across text, images, and audio. This allows for more natural human-computer interaction, as users can engage with it through talking, typing, showing images, and even videos.", "model_type": "text_generation", "input_modalities": ["text", "image"], "output_modalities": ["text"], "input_token_rate": "0.0000025", "output_token_rate": "0.00001", "context_length": 128000, "max_completion_tokens": 16384, "cached_input_token_rate": "0.00000125", "api_formats": ["openai"], "featured": false}, {"id": "gpt_image15", "name": "gpt_image15", "display_name": "GPT Image 1.5", "description": "GPT Image 1.5", "model_type": "image_generation", "input_modalities": ["text", "image"], "output_modalities": ["image"], "text_input_rate": "0.0005", "image_input_rate": "0.0008", "text_output_rate": "0.001", "image_output_rate": "0.0032"}, {"id": "gpt_image2", "name": "gpt_image2", "display_name": "GPT Image 2", "description": "GPT Image 2", "model_type": "image_generation", "input_modalities": ["text", "image"], "output_modalities": ["image"], "text_input_rate": "0.0005", "image_input_rate": "0.0008", "text_output_rate": "0.001", "image_output_rate": "0.003"}, {"id": "gpt_image2_edit", "name": "gpt_image2_edit", "display_name": "GPT Image 2 [Edit]", "description": "GPT Image 2 [Edit]", "model_type": "image_generation", "input_modalities": ["text", "image"], "output_modalities": ["image"], "text_input_rate": "0.0005", "image_input_rate": "0.0008", "text_output_rate": "0.001", "image_output_rate": "0.003"}, {"id": "flux_kontext", "name": "flux_kontext", "display_name": "FLUX.1 Kontext", "description": "FLUX.1 Kontext", "model_type": "image_generation", "input_modalities": ["text", "image"], "output_modalities": ["image"], "pro_rate": 4, "max_rate": 8}, {"id": "flux_kontext_edit", "name": "flux_kontext_edit", "display_name": "FLUX.1 Kontext [Edit]", "description": "FLUX.1 Kontext [Edit]", "model_type": "image_generation", "input_modalities": ["text", "image"], "output_modalities": ["image"], "pro_rate": 4, "max_rate": 8}, {"id": "flux_pro", "name": "flux_pro", "display_name": "FLUX 1.1 [pro]", "description": "FLUX 1.1 [pro]", "model_type": "image_generation", "input_modalities": ["text"], "output_modalities": ["image"], "rate": 4}, {"id": "flux_pro_ultra", "name": "flux_pro_ultra", "display_name": "FLUX 1.1 [pro] Ultra", "description": "FLUX 1.1 [pro] Ultra", "model_type": "image_generation", "input_modalities": ["text"], "output_modalities": ["image"], "rate": 6}, {"id": "ideogram", "name": "ideogram", "display_name": "Ideogram 3.0", "description": "Ideogram 3.0", "model_type": "image_generation", "input_modalities": ["text"], "output_modalities": ["image"], "rate": 6}, {"id": "ideogram_character", "name": "ideogram_character", "display_name": "Ideogram Character", "description": "Ideogram Character", "model_type": "image_generation", "input_modalities": ["text", "image"], "output_modalities": ["image"], "TURBO_rate": 10, "BALANCED_rate": 15, "QUALITY_rate": 20}, {"id": "recraft", "name": "recraft", "display_name": "Recraft", "description": "Recraft", "model_type": "image_generation", "input_modalities": ["text"], "output_modalities": ["image"], "rate": 4}, {"id": "recraft_svg", "name": "recraft_svg", "display_name": "Recraft SVG", "description": "Recraft SVG", "model_type": "image_generation", "input_modalities": ["text"], "output_modalities": ["image"], "rate": 8}, {"id": "recraft_vectorize", "name": "recraft_vectorize", "display_name": "Recraft Vectorize", "description": "Recraft Vectorize", "model_type": "image_generation", "input_modalities": ["image"], "output_modalities": ["image"], "rate": 1}, {"id": "dalle", "name": "dalle", "display_name": "DALL-E", "description": "DALL-E", "model_type": "image_generation", "input_modalities": ["text"], "output_modalities": ["image"], "default_standard": 4, "high_res_standard": 8, "default_hd": 8, "high_res_hd": 12}, {"id": "magnific", "name": "magnific", "display_name": "Magnific Upscaler", "description": "Magnific Upscaler", "model_type": "image_generation", "input_modalities": ["image"], "output_modalities": ["image"], "2k_rate": "11.9", "4k_rate": "23.8", "8k_rate": "142.7", "10k_rate": "142.7"}, {"id": "flux_pro_canny", "name": "flux_pro_canny", "display_name": "FLUX 1.1 [pro] Canny [Edit]", "description": "FLUX 1.1 [pro] Canny [Edit]", "model_type": "image_generation", "input_modalities": ["text", "image"], "output_modalities": ["image"], "rate": 5}, {"id": "flux_pro_depth", "name": "flux_pro_depth", "display_name": "FLUX 1.1 [pro] Depth [Edit]", "description": "FLUX 1.1 [pro] Depth [Edit]", "model_type": "image_generation", "input_modalities": ["text", "image"], "output_modalities": ["image"], "rate": 5}, {"id": "gpt_image_edit", "name": "gpt_image_edit", "display_name": "GPT Image [Edit]", "description": "GPT Image [Edit]", "model_type": "image_generation", "input_modalities": ["text", "image"], "output_modalities": ["image"], "text_input_rate": "0.0005", "image_input_rate": "0.001", "image_output_rate": "0.004"}, {"id": "midjourney", "name": "midjourney", "display_name": "Midjourney", "description": "Midjourney", "model_type": "image_generation", "input_modalities": ["text", "image"], "output_modalities": ["image"], "v7_turbo_rate": 12, "v6_turbo_rate": 14, "fast_rate": 7, "relax_rate": 4}, {"id": "seedream", "name": "seedream", "display_name": "Seedream 4.5", "description": "Seedream 4.5", "model_type": "image_generation", "input_modalities": ["text", "image"], "output_modalities": ["image"], "rate": 4}, {"id": "seedream5_lite", "name": "seedream5_lite", "display_name": "Seedream 5 Lite", "description": "Seedream 5 Lite", "model_type": "image_generation", "input_modalities": ["text", "image"], "output_modalities": ["image"], "rate": "3.5"}, {"id": "seedream5_pro", "name": "seedream5_pro", "display_name": "Seedream 5 Pro", "description": "Seedream 5 Pro", "model_type": "image_generation", "input_modalities": ["text", "image"], "output_modalities": ["image"], "rate": "6.75", "high_res_rate": "13.5", "additional_image_rate": "0.45"}, {"id": "dreamina", "name": "dreamina", "display_name": "Dreamina", "description": "Dreamina", "model_type": "image_generation", "input_modalities": ["text"], "output_modalities": ["image"], "rate": 3}, {"id": "nano_banana", "name": "nano_banana", "display_name": "Nano Banana", "description": "Nano Banana", "model_type": "image_generation", "input_modalities": ["text", "image"], "output_modalities": ["text", "image"], "rate": "3.9", "input_rate": "0.00003", "output_rate": "0.0030232558"}, {"id": "nano_banana_pro", "name": "nano_banana_pro", "display_name": "Nano Banana Pro", "description": "Nano Banana Pro", "model_type": "image_generation", "input_modalities": ["text", "image"], "output_modalities": ["text", "image"], "rate": 15, "input_rate": "0.0002", "text_output_rate": "0.0012", "image_output_rate": "0.012", "grounding_rate": "1.5"}, {"id": "nano_banana2", "name": "nano_banana2", "display_name": "Nano Banana 2", "description": "Nano Banana 2", "model_type": "image_generation", "input_modalities": ["text", "image"], "output_modalities": ["text", "image"], "rate": 6, "input_rate": "0.000025", "text_output_rate": "0.00015", "image_output_rate": "0.006", "grounding_rate": "1.5"}, {"id": "nano_banana_lite", "name": "nano_banana_lite", "display_name": "Nano Banana Lite", "description": "Nano Banana Lite", "model_type": "image_generation", "input_modalities": ["text", "image"], "output_modalities": ["text", "image"], "rate": 3, "input_rate": "0.000025", "text_output_rate": "0.00015", "image_output_rate": "0.003", "grounding_rate": "1.5"}, {"id": "qwen_image_edit", "name": "qwen_image_edit", "display_name": "Qwen Image Edit", "description": "Qwen Image Edit", "model_type": "image_generation", "input_modalities": ["text", "image"], "output_modalities": ["image"], "rate": 3, "unit": "megapixel"}, {"id": "imagine_art", "name": "imagine_art", "display_name": "Imagineart 1.5", "description": "Imagineart 1.5", "model_type": "image_generation", "input_modalities": ["text"], "output_modalities": ["image"], "rate": 3}, {"id": "hunyuan_image", "name": "hunyuan_image", "display_name": "Hunyuan Image 3.0", "description": "Hunyuan Image 3.0", "model_type": "image_generation", "input_modalities": ["text", "image"], "output_modalities": ["image"], "rate": 10}, {"id": "flux2", "name": "flux2", "display_name": "FLUX.2", "description": "FLUX.2", "model_type": "image_generation", "input_modalities": ["text"], "output_modalities": ["image"], "rate": "0.96", "edit_rate": "1.2"}, {"id": "flux2_pro", "name": "flux2_pro", "display_name": "FLUX.2 [Pro]", "description": "FLUX.2 [Pro]", "model_type": "image_generation", "input_modalities": ["text", "image"], "output_modalities": ["image"], "rate": 3, "input_rate": "1.5"}, {"id": "grok_imagine_image", "name": "grok_imagine_image", "display_name": "Grok Imagine Image", "description": "Grok Imagine Image", "model_type": "image_generation", "input_modalities": ["text", "image"], "output_modalities": ["image"], "rate": 2, "image_input_rate": "0.2"}, {"id": "grok_imagine_image_quality", "name": "grok_imagine_image_quality", "display_name": "Grok Imagine Quality", "description": "Grok Imagine Quality", "model_type": "image_generation", "input_modalities": ["text", "image"], "output_modalities": ["image"], "_1k_rate": 5, "_2k_rate": 7, "image_input_rate": 1}, {"id": "wan27", "name": "wan27", "display_name": "Wan 2.7", "description": "Wan 2.7", "model_type": "image_generation", "input_modalities": ["text", "image"], "output_modalities": ["image"], "rate": 3}, {"id": "gpt-audio-1.5", "name": "gpt-audio-1.5", "display_name": "GPT Audio 1.5", "description": "GPT Audio 1.5 supports audio input and output via the chat completions API, enabling speech understanding and generation in a single model call.", "model_type": "audio_generation", "input_modalities": ["text", "audio"], "output_modalities": ["text", "audio"], "input_token_rate": "0.0000025", "output_token_rate": "0.00001", "context_length": 128000, "max_completion_tokens": 16384, "api_formats": ["openai"], "featured": false}, {"id": "gpt-audio-mini", "name": "gpt-audio-mini", "display_name": "GPT Audio Mini", "description": "GPT Audio Mini is a cost-efficient model supporting audio input and output via the chat completions API, ideal for high-volume speech applications.", "model_type": "audio_generation", "input_modalities": ["text", "audio"], "output_modalities": ["text", "audio"], "input_token_rate": "0.0000006", "output_token_rate": "0.0000024", "context_length": 128000, "max_completion_tokens": 16384, "api_formats": ["openai"], "featured": false}, {"id": "gemini-2.5-flash-preview-tts", "name": "gemini-2.5-flash-preview-tts", "display_name": "Gemini 2.5 Flash TTS", "description": "Gemini 2.5 Flash TTS is a dedicated text-to-speech model from Google, supporting audio output generation via the Gemini API.", "model_type": "audio_generation", "input_modalities": ["text"], "output_modalities": ["text", "audio"], "input_token_rate": "0.0000005", "output_token_rate": "0", "context_length": 1048576, "max_completion_tokens": 65536, "api_formats": ["openai"], "featured": false}, {"id": "gemini-2.5-pro-preview-tts", "name": "gemini-2.5-pro-preview-tts", "display_name": "Gemini 2.5 Pro TTS", "description": "Gemini 2.5 Pro TTS is a high-quality dedicated text-to-speech model from Google, supporting audio output generation via the Gemini API.", "model_type": "audio_generation", "input_modalities": ["text"], "output_modalities": ["text", "audio"], "input_token_rate": "0.000001", "output_token_rate": "0", "context_length": 2097152, "max_completion_tokens": 65536, "api_formats": ["openai"], "featured": false}, {"id": "hume", "name": "hume", "display_name": "Hume", "description": "Hume", "model_type": "audio_generation", "input_modalities": ["text"], "output_modalities": ["audio"]}, {"id": "elevenlabs", "name": "elevenlabs", "display_name": "ElevenLabs", "description": "ElevenLabs", "model_type": "audio_generation", "input_modalities": ["text"], "output_modalities": ["audio"]}, {"id": "openai_tts", "name": "openai_tts", "display_name": "OpenAI", "description": "OpenAI", "model_type": "audio_generation", "input_modalities": ["text"], "output_modalities": ["audio"]}, {"id": "minimax_tts", "name": "minimax_tts", "display_name": "MiniMax Speech 2.8 HD", "description": "MiniMax Speech 2.8 HD", "model_type": "audio_generation", "input_modalities": ["text"], "output_modalities": ["audio"]}, {"id": "vibevoice", "name": "vibevoice", "display_name": "VibeVoice", "description": "VibeVoice", "model_type": "audio_generation", "input_modalities": ["text"], "output_modalities": ["audio"]}, {"id": "seed_speech", "name": "seed_speech", "display_name": "Seed Speech", "description": "Seed Speech", "model_type": "audio_generation", "input_modalities": ["text"], "output_modalities": ["audio"]}, {"id": "seed_audio", "name": "seed_audio", "display_name": "Seed Audio 1.0", "description": "Seed Audio 1.0", "model_type": "audio_generation", "input_modalities": ["text"], "output_modalities": ["audio"]}, {"id": "runway", "name": "runway", "display_name": "Runway", "description": "Runway", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "_5_sec_rate": 25, "_10_sec_rate": 50}, {"id": "luma_labs", "name": "luma_labs", "display_name": "Luma Labs", "description": "Luma Labs", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "rate": 40}, {"id": "kling_ai", "name": "kling_ai", "display_name": "Kling AI v1.6", "description": "Kling AI v1.6", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "_5_sec_rate_pro": "47.5", "_10_sec_rate_pro": 95, "_5_sec_rate_std": "22.5", "_10_sec_rate_std": 45}, {"id": "kling_ai_v2", "name": "kling_ai_v2", "display_name": "Kling AI v2", "description": "Kling AI v2", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "_5_sec_rate": 140, "_10_sec_rate": 280}, {"id": "kling_ai_v21", "name": "kling_ai_v21", "display_name": "Kling AI v2.1", "description": "Kling AI v2.1", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "_5_sec_rate": 140, "_10_sec_rate": 280}, {"id": "minimax", "name": "minimax", "display_name": "Hailuo 2", "description": "Hailuo 2", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "_6_sec_standard_rate": 27, "_10_sec_standard_rate": 45, "_6_sec_pro_rate": 48, "_10_sec_pro_rate": 80}, {"id": "veo", "name": "veo", "display_name": "Veo 2", "description": "Veo 2", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "_5_sec_rate": 250, "_6_sec_rate": 300, "_7_sec_rate": 350, "_8_sec_rate": 400}, {"id": "hunyuan", "name": "hunyuan", "display_name": "Hunyuan Video", "description": "Hunyuan Video", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "rate": 40}, {"id": "wan", "name": "wan", "display_name": "Wan 2.2", "description": "Wan 2.2", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "rate": 8, "_480p_fast_rate": "1.25", "_580p_fast_rate": "1.875", "_720p_fast_rate": "2.5"}, {"id": "wan25", "name": "wan25", "display_name": "Wan 2.5", "description": "Wan 2.5", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "_480p_rate": 5, "_720p_rate": 10, "_1080p_rate": 15}, {"id": "topaz", "name": "topaz", "display_name": "Topaz Upscaler", "description": "Topaz Upscaler", "model_type": "video_generation", "input_modalities": ["image", "video"], "output_modalities": ["video"], "rate": 10}, {"id": "veo3", "name": "veo3", "display_name": "Veo 3", "description": "Veo 3", "model_type": "video_generation", "input_modalities": ["text"], "output_modalities": ["video", "audio"], "_8_sec_rate_standard_audio": 600, "_8_sec_rate_standard_no_audio": 400, "_8_sec_rate_fast_audio": 320, "_8_sec_rate_fast_no_audio": 200}, {"id": "seedance", "name": "seedance", "display_name": "Seedance", "description": "Seedance", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "rate": 18, "token_rate": "0.00018"}, {"id": "seedance_pro", "name": "seedance_pro", "display_name": "Seedance Pro", "description": "Seedance Pro", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "rate": 74, "token_rate": "0.0003"}, {"id": "kling_ai_v25", "name": "kling_ai_v25", "display_name": "Kling AI v2.5", "description": "Kling AI v2.5", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "_5_sec_standard_rate": 21, "_10_sec_standard_rate": 42, "_5_sec_pro_rate": 35, "_10_sec_pro_rate": 70}, {"id": "sora", "name": "sora", "display_name": "Sora 2", "description": "Sora 2", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "standard_rate": 10, "pro_rate": 30}, {"id": "veo31", "name": "veo31", "display_name": "Veo 3.1", "description": "Veo 3.1", "model_type": "video_generation", "input_modalities": ["text"], "output_modalities": ["video", "audio"], "fast_rate": 120, "standard_rate": 320}, {"id": "veo31_lite", "name": "veo31_lite", "display_name": "Veo 3.1 Lite", "description": "Veo 3.1 Lite", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video", "audio"], "rate": 7}, {"id": "kling_ai_v26", "name": "kling_ai_v26", "display_name": "Kling AI v2.6", "description": "Kling AI v2.6", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "audio_rate": 14, "rate": 7}, {"id": "kling_ai_v26_motion", "name": "kling_ai_v26_motion", "display_name": "Kling v2.6 Motion Control", "description": "Kling v2.6 Motion Control", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "rate": "11.2"}, {"id": "kling_ai_v3", "name": "kling_ai_v3", "display_name": "Kling AI v3", "description": "Kling AI v3", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "standard_rate": "16.8", "standard_audio_rate": "25.2", "pro_rate": "22.4", "pro_audio_rate": "33.6"}, {"id": "kling_ai_v3_motion", "name": "kling_ai_v3_motion", "display_name": "Kling v3 Motion Control", "description": "Kling v3 Motion Control", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "standard_rate": "12.6", "pro_rate": "16.8"}, {"id": "kling_ai_o1", "name": "kling_ai_o1", "display_name": "Kling AI O1", "description": "Kling AI O1", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "_5_sec_standard_rate": 42, "_10_sec_standard_rate": 84, "_5_sec_pro_rate": 56, "_10_sec_pro_rate": 112}, {"id": "kling_ai_o3", "name": "kling_ai_o3", "display_name": "Kling AI O3", "description": "Kling AI O3", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "standard_rate": "16.8", "standard_audio_rate": "22.4", "pro_rate": "22.4", "pro_audio_rate": 28, "standard_v2v_rate": "25.2", "pro_v2v_rate": "33.6"}, {"id": "seedance15_pro", "name": "seedance15_pro", "display_name": "Seedance 1.5 Pro", "description": "Seedance 1.5 Pro", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "rate": 26, "audio_token_rate": "0.00024", "token_rate": "0.00012"}, {"id": "seedance20", "name": "seedance20", "display_name": "Seedance 2.0", "description": "Seedance 2.0", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video", "audio"], "fast_480p_rate": "10.76", "fast_720p_rate": "24.19", "fast_1080p_rate": "54.43", "standard_480p_rate": "13.45", "standard_720p_rate": "30.24", "standard_1080p_rate": "68.04"}, {"id": "seedance20_mini", "name": "seedance20_mini", "display_name": "Seedance 2.0 Mini", "description": "Seedance 2.0 Mini", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video", "audio"], "_480p_rate": "7.21", "_720p_rate": "15.47"}, {"id": "grok_imagine_video", "name": "grok_imagine_video", "display_name": "Grok Imagine Video", "description": "Grok Imagine Video", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "rate": 5, "image_input_rate": "0.2", "video_input_rate": 1}, {"id": "grok_imagine_video15", "name": "grok_imagine_video15", "display_name": "Grok Imagine Video 1.5", "description": "Grok Imagine Video 1.5", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "_480p_rate": 8, "_720p_rate": 14, "image_input_rate": 1}, {"id": "gemini_omni_flash", "name": "gemini_omni_flash", "display_name": "Gemini Omni Flash", "description": "Gemini Omni Flash", "model_type": "video_generation", "input_modalities": ["text", "image"], "output_modalities": ["video"], "input_token_rate": "0.00015", "text_output_rate": "0.0009", "video_output_rate": "0.00175"}]}
```