{"object":"list","source":"live","updatedAt":"2026-10-29T02:46:58.823Z","data":[{"id":"oc-uncensored-1.0","object":"model","name":"OpenCAP Uncensored 1.0","description":"OpenCAP Uncensored 1.0 is an AI assistant designed for people who prefer honest answers over sanitized responses. Built by OpenCAP, it delivers direct, practical, and intelligent assistance without unnecessary moral lectures or artificial restrictions on discussion","kind":"llm","owned_by":"model","provider":{"id":"opencap","name":"OpenCAP"},"contextLength":262144,"maxOutput":null,"pricing":{"input":0.2,"output":0.8,"cachedInput":0.1},"modality":{"input":["text"],"output":["text"]},"tags":["Uncensored"],"discount":null,"promotionMessage":null},{"id":"glm-5.2","name":"Z.ai: GLM 5.2","description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...","kind":"llm","owned_by":"model","provider":{"id":"z-ai","name":"Z.ai"},"contextLength":1048576,"maxOutput":943718,"pricing":{"input":0.006600000000000001,"output":7.700000000000001,"cachedInput":0.0055000000000000005,"originalInput":0.006,"originalOutput":7},"modality":{"input":["text"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"gpt-5.5","name":"OpenAI: GPT-5.5","description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"OpenAI"},"contextLength":1050000,"maxOutput":128000,"pricing":{"input":5.5,"output":33,"cachedInput":0.55,"originalInput":5,"originalOutput":30},"modality":{"input":["file","image","text"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"claude-opus-4.8","name":"Anthropic: Claude Opus 4.8","description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"Anthropic"},"contextLength":1000000,"maxOutput":128000,"pricing":{"input":6.5,"output":32.5,"cachedInput":0.65,"originalInput":5,"originalOutput":25},"modality":{"input":["text","image","file"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash 0423","description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...","kind":"llm","owned_by":"model","provider":{"id":"deepseek","name":"DeepSeek"},"contextLength":1048576,"maxOutput":943717,"pricing":{"input":0.1365,"output":0.273,"cachedInput":0.0273,"originalInput":0.119,"originalOutput":0.238},"modality":{"input":["text"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"minimax-m3","name":"MiniMax: MiniMax M3","description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"MiniMax"},"contextLength":1048576,"maxOutput":512000,"pricing":{"input":0.33,"output":1.32,"cachedInput":0.066,"originalInput":0.3,"originalOutput":1.2},"modality":{"input":["text","image","video"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"qwen3.7-max","name":"Qwen: Qwen3.7 Max","description":"Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"Qwen"},"contextLength":1000000,"maxOutput":131072,"pricing":{"input":1.6225000000000003,"output":4.867500000000001,"cachedInput":0.3245,"originalInput":1.475,"originalOutput":4.425},"modality":{"input":["text"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"gemini-3.5-flash","name":"Google: Gemini 3.5 Flash","description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"Google"},"contextLength":1048576,"maxOutput":65536,"pricing":{"input":1.6500000000000001,"output":9.9,"cachedInput":0.165,"originalInput":1.5,"originalOutput":9},"modality":{"input":["text","image","video","file","audio"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"grok-4.3","name":"SpaceXAI: Grok 4.3","description":"Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...","kind":"llm","owned_by":"model","provider":{"id":"x-ai","name":"SpaceXAI"},"contextLength":1000000,"maxOutput":900000,"pricing":{"input":1.2650000000000001,"output":2.5300000000000002,"cachedInput":0.2024,"originalInput":1.25,"originalOutput":2.5},"modality":{"input":["text","image","file"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"gpt-5.4-mini","name":"OpenAI: GPT-5.4 Mini","description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"OpenAI"},"contextLength":400000,"maxOutput":128000,"pricing":{"input":0.8250000000000001,"output":4.95,"cachedInput":0.0825,"originalInput":0.75,"originalOutput":4.5},"modality":{"input":["file","image","text"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"claude-sonnet-5","name":"Anthropic: Claude Sonnet 5","description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"Anthropic"},"contextLength":1000000,"maxOutput":128000,"pricing":{"input":2.2,"output":11,"cachedInput":0.22,"originalInput":2,"originalOutput":10},"modality":{"input":["text","image","file"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"claude-sonnet-4.6","name":"Anthropic: Claude Sonnet 4.6","description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"Anthropic"},"contextLength":1000000,"maxOutput":128000,"pricing":{"input":3.3000000000000003,"output":16.5,"cachedInput":0.33,"originalInput":3,"originalOutput":15},"modality":{"input":["text","image","file"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"claude-fable-5","name":"Anthropic: Claude Fable 5","description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"Anthropic"},"contextLength":1000000,"maxOutput":128000,"pricing":{"input":13,"output":65,"cachedInput":1.3,"originalInput":10,"originalOutput":50},"modality":{"input":["text","image","file"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"kimi-k2.6","name":"MoonshotAI: Kimi K2.6","description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"MoonshotAI"},"contextLength":262144,"maxOutput":235929,"pricing":{"input":0.7150000000000001,"output":3.7510000000000003,"cachedInput":0.165,"originalInput":0.65,"originalOutput":3.41},"modality":{"input":["text","image"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"MoonshotAI"},"contextLength":262144,"maxOutput":235929,"pricing":{"input":0.6160000000000001,"output":3.4100000000000006,"cachedInput":0.165,"originalInput":0.56,"originalOutput":3.1},"modality":{"input":["text","image"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"claude-haiku-4.5","name":"Anthropic: Claude Haiku 4.5","description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"Anthropic"},"contextLength":200000,"maxOutput":64000,"pricing":{"input":1.1,"output":5.5,"cachedInput":0.11,"originalInput":1,"originalOutput":5},"modality":{"input":["text","image","file"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"gemini-3.1-pro-preview","name":"Google: Gemini 3.1 Pro Preview","description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"Google"},"contextLength":1048576,"maxOutput":65536,"pricing":{"input":2.2,"output":13.200000000000001,"cachedInput":0.22,"originalInput":2,"originalOutput":12},"modality":{"input":["audio","file","image","text","video"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"gpt-5.6-luna","name":"OpenAI: GPT-5.6 Luna","description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"OpenAI"},"contextLength":1050000,"maxOutput":128000,"pricing":{"input":0.22,"output":1.32,"cachedInput":0.022000000000000002,"originalInput":0.19999999999999998,"originalOutput":1.2},"modality":{"input":["file","image","text"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"gpt-5.6-terra","name":"OpenAI: GPT-5.6 Terra","description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...","kind":"llm","owned_by":"model","provider":{"id":"openai","name":"OpenAI"},"contextLength":1050000,"maxOutput":128000,"pricing":{"input":2.2,"output":13.200000000000001,"cachedInput":0.22,"originalInput":2,"originalOutput":12},"modality":{"input":["file","image","text"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"gpt-5.6-sol","name":"OpenAI: GPT-5.6 Sol","description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...","kind":"llm","owned_by":"model","provider":{"id":"openai","name":"OpenAI"},"contextLength":1050000,"maxOutput":128000,"pricing":{"input":5.2,"output":26,"cachedInput":0.52,"originalInput":4,"originalOutput":20},"modality":{"input":["file","image","text"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"grok-4.5","name":"SpaceXAI: Grok 4.5","description":"Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.","kind":"llm","owned_by":"model","provider":{"id":"x-ai","name":"SpaceXAI"},"contextLength":500000,"maxOutput":450000,"pricing":{"input":2.0240000000000005,"output":6.072000000000001,"cachedInput":0.30360000000000004,"originalInput":2,"originalOutput":6},"modality":{"input":["text","image","file"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"kimi-k3","name":"MoonshotAI: Kimi K3","description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"MoonshotAI"},"contextLength":1048576,"maxOutput":943718,"pricing":{"input":0.21120000000000003,"output":22,"cachedInput":0.20020000000000002,"originalInput":0.192,"originalOutput":20},"modality":{"input":["text","image","video"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"claude-opus-5","name":"Anthropic: Claude Opus 5","description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...","kind":"llm","owned_by":"model","provider":{"id":"anthropic","name":"Anthropic"},"contextLength":1000000,"maxOutput":128000,"pricing":{"input":5.5,"output":27.500000000000004,"cachedInput":0.55,"originalInput":5,"originalOutput":25},"modality":{"input":["text","image","file"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"muse-spark-1.2","name":"Meta: Muse Spark 1.2","description":"Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window....","kind":"llm","owned_by":"model","provider":{"id":"meta","name":"Meta"},"contextLength":1048576,"maxOutput":943718,"pricing":{"input":1.75,"output":5.949999999999999,"cachedInput":0.21,"originalInput":1.25,"originalOutput":4.25},"modality":{"input":["text","image","video","file"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"grok-4.6","name":"SpaceXAI: Grok 4.6","description":"Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).","kind":"llm","owned_by":"model","provider":{"id":"x-ai","name":"SpaceXAI"},"contextLength":500000,"maxOutput":450000,"pricing":{"input":2.0240000000000005,"output":6.072000000000001,"cachedInput":0.5060000000000001,"originalInput":2,"originalOutput":6},"modality":{"input":["text","image","file"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"glm-5.3","name":"Z.ai: GLM 5.3","description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"Z.ai"},"contextLength":1048576,"maxOutput":943718,"pricing":{"input":0.0745833,"output":1.4938,"cachedInput":0.0735163,"originalInput":0.0745833,"originalOutput":1.4938},"modality":{"input":["text"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"Z.ai"},"contextLength":1048576,"maxOutput":131072,"pricing":{"input":0.04576000000000001,"output":0.08481000000000001,"cachedInput":0.033,"originalInput":0.041600000000000005,"originalOutput":0.0771},"modality":{"input":["text","image","video"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"claude-fable-5.1","name":"Anthropic: Claude Fable 5.1","description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"Anthropic"},"contextLength":1000000,"maxOutput":128000,"pricing":{"input":13,"output":65,"cachedInput":0.325,"originalInput":10,"originalOutput":50},"modality":{"input":["text","image","file"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"gpt-6-astra","name":"OpenAI: GPT-6 Astra","description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"OpenAI"},"contextLength":1050000,"maxOutput":128000,"pricing":{"input":13.5,"output":67.5,"cachedInput":1.35,"originalInput":10,"originalOutput":50},"modality":{"input":["file","image","text"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"DeepSeek"},"contextLength":1048576,"maxOutput":943718,"pricing":{"input":0.0495,"output":0.55,"cachedInput":0.006600000000000001,"originalInput":0.0495,"originalOutput":0.55},"modality":{"input":["text","image"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"grok-4.7","name":"SpaceXAI: Grok 4.7","description":"Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"SpaceXAI"},"contextLength":500000,"maxOutput":450000,"pricing":{"input":2.2,"output":6.6000000000000005,"cachedInput":0.55,"originalInput":2,"originalOutput":6},"modality":{"input":["text","image","file"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"claude-opus-5.5","name":"Anthropic: Claude Opus 5.5","description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"Anthropic"},"contextLength":1000000,"maxOutput":128000,"pricing":{"input":5.4,"output":27,"cachedInput":0.27,"originalInput":4,"originalOutput":20},"modality":{"input":["text","image","file"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"gpt-6-luna","name":"OpenAI: GPT-6 Luna","description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...","kind":"llm","owned_by":"model","provider":{"id":"openai","name":"OpenAI"},"contextLength":1050000,"maxOutput":128000,"pricing":{"input":0.11,"output":0.55,"cachedInput":0.011000000000000001,"originalInput":0.09999999999999999,"originalOutput":0.5},"modality":{"input":["file","image","text"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"gpt-6-sol","name":"OpenAI: GPT-6 Sol","description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...","kind":"llm","owned_by":"model","provider":{"id":"openai","name":"OpenAI"},"contextLength":1050000,"maxOutput":128000,"pricing":{"input":2.2,"output":11,"cachedInput":0.22,"originalInput":2,"originalOutput":10},"modality":{"input":["file","image","text"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"claude-sonnet-5.5","name":"Anthropic: Claude Sonnet 5.5","description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"Anthropic"},"contextLength":1000000,"maxOutput":128000,"pricing":{"input":2.2,"output":11,"cachedInput":0.11,"originalInput":2,"originalOutput":10},"modality":{"input":["text","image","file"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"gpt-6.1-sol","name":"OpenAI: GPT-6.1 Sol","description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"OpenAI"},"contextLength":1050000,"maxOutput":128000,"pricing":{"input":2.7,"output":13.5,"cachedInput":0.135,"originalInput":2,"originalOutput":10},"modality":{"input":["file","image","text"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"muse-wonder","name":"Meta: Muse Wonder","description":"Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"Meta"},"contextLength":1048576,"maxOutput":943718,"pricing":{"input":4.4,"output":22,"cachedInput":0.22,"originalInput":4,"originalOutput":20},"modality":{"input":["text","image","video","file","audio"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"kimi-k3.1-pro","name":"MoonshotAI: Kimi K3.1 Pro","description":"Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"MoonshotAI"},"contextLength":1048576,"maxOutput":943718,"pricing":{"input":2.2,"output":11,"cachedInput":0.22,"originalInput":2,"originalOutput":10},"modality":{"input":["text","image","video"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"gemini-3.8-flash","name":"Google: Gemini 3.8 Flash","description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"Google"},"contextLength":1048576,"maxOutput":65536,"pricing":{"input":0.9075000000000002,"output":4.5375000000000005,"cachedInput":0.09075000000000001,"originalInput":0.8250000000000001,"originalOutput":4.125},"modality":{"input":["text","image","video","file","audio"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null},{"id":"gemini-4-argon","name":"Google: Gemini 4 Argon","description":"Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...","kind":"llm","owned_by":"model","provider":{"id":"surplus","name":"Google"},"contextLength":1048576,"maxOutput":943718,"pricing":{"input":2.2,"output":11,"cachedInput":0.11,"originalInput":2,"originalOutput":10},"modality":{"input":["audio","file","image","text","video"],"output":["text"]},"tags":["Anon"],"discount":null,"promotionMessage":null}]}