Modelos
Todos los modelos disponibles en la API de Token360. Abre un modelo para ver su precio y cómo llamarlo.
Todos los modelos disponibles en la API de Token360. Abre un modelo para ver su precio y cómo llamarlo.
HY4
Tencent Hunyuan HY4 official model for reasoning, coding, agents and image understanding.
Actualizado 5 nov 2026
TypeSafe Jev 1.13
Jev 1.13 belongs to TypeSafe’s System One family of structured decision models. It evaluates context and predefined questions to produce typed results for application logic, including routing, classification, and other tasks that need fast, predictable decisions.
Actualizado 5 nov 2026
TypeSafe Jev 1.14
Jev 1.14 belongs to TypeSafe’s System One family of structured decision models. It evaluates context and predefined questions to produce typed results for application logic, including routing, classification, and other tasks that need fast, predictable decisions.
Actualizado 5 nov 2026
MiniMax H3 Highspeed
MiniMax H3 Highspeed balances generation quality and speed, with text-to-video, image-to-video, first-and-last-frame, and multimodal reference workflows at 768P with native audio.
Actualizado 30 oct 2026
MiniMax H3 Lite
MiniMax H3 Lite is optimized for lower-cost exploration and batch generation, with text-to-video, image-to-video, first-and-last-frame, and multimodal reference workflows at 480P or 768P with native audio.
Actualizado 30 oct 2026
GPT-6.1 Terra
GPT-6.1 Terra supports visual reasoning, computer use, and writing with text and image input. It has a 1.05M-token context window and up to 128K output tokens. Tool calling uses the Responses API.
Actualizado 26 oct 2026
Kimi K3.1 Pro
Kimi K3.1 flagship with native vision, a 1M-token context window, and strong coding, financial research, modeling, and long-horizon agent capabilities.
Actualizado 24 oct 2026
Kimi K3.1 Pro HighSpeed
Kimi K3.1 Pro high-speed variant with the same intelligence and 1M-token context at roughly 3x throughput.
Actualizado 24 oct 2026
MiniMax M3.1 Flash
MiniMax M3.1 Flash: multimodal reasoning, coding and tool use with a 1M-token context window and adjustable reasoning effort.
Actualizado 19 oct 2026
DeepSeek V4.1 Flash 1017
DeepSeek-V4.1-Flash-1017 improves benchmark performance while reducing task time and output length, with unchanged API and pricing. It natively supports a 1M context window, vision, reasoning, and tool use.
Actualizado 17 oct 2026
Gemini 4 Argon
Google Gemini 4 Argon: reasoning, multimodal input, tools, structured output, and implicit caching.
Actualizado 13 oct 2026
Qwen Image 2.1 Pro
Qwen Image 2.1 Pro is a unified 7B visual generation model for text-to-image generation and image editing, with native transparent RGBA output, up to 10 reference images, and improved typography, portrait lighting, and fine-detail fidelity.
Actualizado 9 oct 2026
Qwen Image 2.1 Turbo
Qwen Image 2.1 Turbo is the accelerated 8-step checkpoint of Qwen Image 2.1 for cost-effective text-to-image generation and image editing, using the same 7B visual architecture with native transparent RGBA output and up to 10 reference images.
Actualizado 9 oct 2026
Claude Haiku 5.5
Anthropic Claude Haiku 5.5 for fast, high-volume classification, extraction, routing, and subagent tasks.
Actualizado 7 oct 2026
Nano Banana 2.1
Google's high-efficiency image generation and conversational editing model with improved visual quality, prompt adherence, multi-turn character consistency, text rendering, Google Search grounding, and 1K, 2K, and 4K output.
Actualizado 6 oct 2026
GPT-6.1 Sol
GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. Compare it with Astra on your tasks to assess the tradeoff between quality and cost. 1.05M context window; reasoning effort from low to max.
Actualizado 29 sept 2026
Claude Sonnet 5.5
Anthropic Claude Sonnet 5.5 for fast, capable coding and everyday knowledge work.
Actualizado 28 sept 2026
Claude Opus 5.5
Anthropic Claude Opus 5.5 for long-running agentic coding and knowledge work.
Actualizado 22 sept 2026
GPT-6 Luna
GPT-6 Luna is our most efficient model for focused, high-volume tasks. It is the fastest, most cost-efficient GPT-6 tier—suited for high-volume, latency-sensitive chat, classification, and lightweight agent work; at higher reasoning effort it can handle complex software engineering and computer-use tasks. 1.05M context window; reasoning effort from none to max.
Actualizado 22 sept 2026
GPT-6 Sol
GPT-6 Sol is built for complex coding and agentic workflows. It is the flagship tier of the GPT-6 family for demanding reasoning, multi-step agents, and professional engineering work. 1.05M context window; reasoning effort from none to max.
Actualizado 22 sept 2026