Learn more about how to use AI models with TypingMind
inclusionAI: Ring-2.6-1T (free) via OpenRouterRing-2.6-1T is a 1T-parameter-scale thinking model with 63B active parameters, built for real-world agent workflows that require both strong capability and operational efficiency. It is optimized for coding agents, tool...
Google: Gemini 3.1 Flash Lite via OpenRouterGemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...
Gemini 3.1 Flash Lite from googleGemini 3.1 Flash Lite from Google - text, image, video, audio, pdf input, 1,048,576 token context
Baidu Qianfan: CoBuddy (free) via OpenRouterCoBuddy is a code generation model from Baidu, optimized for coding tasks and AI Agent workflows. It features high inference throughput and low end-to-end latency, with native support for tool...
OpenAI: GPT Chat Latest via OpenRouterGPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...
Grok 4.3 from xaiGrok 4.3 from xAI - text, image input, 1,000,000 token context
xAI: Grok 4.3 via OpenRouterGrok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...
IBM: Granite 4.1 8B via OpenRouterGranite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...
Mistral: Mistral Medium 3.5 via OpenRouterMistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...
Mistral Medium (latest) from mistralMistral Medium (latest) from Mistral - text, image input, 262,144 token context
Mistral Medium 3.5 from mistralMistral Medium 3.5 from Mistral - text, image input, 262,144 token context
Owl Alpha via OpenRouterOwl Alpha is a high-performance foundation model designed for agentic workloads. Natively supports tool use, and long-context tasks, with strong performance in code generation, automated workflows, and complex instruction execution....
NVIDIA: Nemotron 3 Nano Omni (free) via OpenRouterNVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...
Poolside: Laguna XS.2 (free) via OpenRouterLaguna XS.2 is the second-generation model in the XS size class from [Poolside](https://poolside.ai), their efficient coding agent series. It combines tool calling and reasoning capabilities with a compact footprint, offering...
Poolside: Laguna M.1 (free) via OpenRouterLaguna M.1 is the flagship coding agent model from [Poolside](https://poolside.ai), optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling and reasoning, with a 128K...
Anthropic Claude Haiku Latest via OpenRouterThis model always redirects to the latest model in the Anthropic Claude Haiku family.
OpenAI GPT Mini Latest via OpenRouterThis model always redirects to the latest model in the OpenAI GPT Mini family.
Google Gemini Pro Latest via OpenRouterThis model always redirects to the latest model in the Google Gemini Pro family.
MoonshotAI Kimi Latest via OpenRouterThis model always redirects to the latest model in the MoonshotAI Kimi family.
Google Gemini Flash Latest via OpenRouterThis model always redirects to the latest model in the Google Gemini Flash family.
Anthropic Claude Sonnet Latest via OpenRouterThis model always redirects to the latest model in the Anthropic Claude Sonnet family.
OpenAI GPT Latest via OpenRouterThis model always redirects to the latest model in the OpenAI GPT family.
Qwen: Qwen3.5 Plus 2026-04-20 via OpenRouterQwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...
Qwen: Qwen3.6 Flash via OpenRouterQwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...
Qwen: Qwen3.6 35B A3B via OpenRouterQwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...
Qwen: Qwen3.6 Max Preview via OpenRouterQwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and...
Qwen: Qwen3.6 27B via OpenRouterQwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...
OpenAI: GPT-5.5 Pro via OpenRouterGPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...
OpenAI: GPT-5.5 via OpenRouterGPT-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...
DeepSeek: DeepSeek V4 Pro via OpenRouterDeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
DeepSeek: DeepSeek V4 Flash via OpenRouterDeepSeek 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...
DeepSeek V4 Flash from deepseekDeepSeek V4 Flash from DeepSeek - text input, 1,000,000 token context
DeepSeek V4 Pro from deepseekDeepSeek V4 Pro from DeepSeek - text input, 1,000,000 token context
DeepSeek V4 Pro from fireworks-aiDeepSeek V4 Pro from Fireworks AI - text input, 1,000,000 token context
GPT-5.5 Pro from veniceGPT-5.5 Pro from Venice AI - text, image input, 1,000,000 token context
DeepSeek V4 Flash from veniceDeepSeek V4 Flash from Venice AI - text input, 1,000,000 token context
Qwen 3.6 27B from veniceQwen 3.6 27B from Venice AI - text, image, video input, 256,000 token context
DeepSeek V4 Pro from veniceDeepSeek V4 Pro from Venice AI - text input, 1,000,000 token context
DeepSeek V4 Flash from deepinfraDeepSeek V4 Flash from Deep Infra - text input, 1,000,000 token context
DeepSeek V4 Pro from deepinfraDeepSeek V4 Pro from Deep Infra - text input, 65,536 token context
DeepSeek V4 Pro from huggingfaceDeepSeek V4 Pro from Hugging Face - text input, 1,048,576 token context
inclusionAI: Ling-2.6-1T (free) via OpenRouterLing-2.6-1T is an instant (instruct) model from inclusionAI and the company’s trillion-parameter flagship, designed for real-world agents that require fast execution and high efficiency at scale. It uses a “fast...
inclusionAI: Ling-2.6-1T via OpenRouterLing-2.6-1T is an instant (instruct) model from inclusionAI and the company’s trillion-parameter flagship, designed for real-world agents that require fast execution and high efficiency at scale. It uses a “fast...
GPT-5.5 from openaiGPT-5.5 from OpenAI - text, image, pdf input, 1,050,000 token context
GPT-5.5 Pro from openaiGPT-5.5 Pro from OpenAI - text, image, pdf input, 1,050,000 token context
GPT-5.5 from veniceGPT-5.5 from Venice AI - text, image input, 1,000,000 token context
Tencent: Hy3 preview (free) via OpenRouterHy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...
Tencent: Hy3 preview via OpenRouterHy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...
Xiaomi: MiMo-V2.5-Pro via OpenRouterMiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....
Xiaomi: MiMo-V2.5 via OpenRouterMiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...
OpenAI: GPT-5.4 Image 2 via OpenRouter[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...
Get notified about new features and future giveaways by subscribing to our newsletter 👇
