FLock API Platform — Unified AI API Gateway

GLM-5.3-Flash is a fast and efficient open-source model optimized for advanced reasoning, coding, and agentic tasks.

GLM-5.3 is the latest open-source SOTA model for advanced reasoning, coding, and agentic tasks.

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 high-throughput workloads, while maintaining strong reasoning and coding performance.

DeepSeek V4 Flash Vision Exp is an efficiency-optimized multimodal Mixture-of-Experts model from DeepSeek, designed to combine fast inference with strong vision, reasoning, and coding capabilities. It supports image understanding alongside text-based tasks, making it suitable for applications that require both visual and language intelligence.

DeepSeek 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, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.

Kimi K3 is Kimi's most capable flagship model to date, with 2.8 trillion parameters. It is built on Kimi Delta Attention (KDA), a hybrid linear attention mechanism, and Attention Residuals, with native visual understanding and a 1M-token context window. It is the world's first open-source model in the 3-trillion-parameter class, designed for frontier intelligence scenarios including long-horizon coding, knowledge work, and reasoning.

Kimi K2.6 is Kimi's latest and most intelligent model, possessing stronger and more stable long-term code writing capabilities, and significantly improved instruction compliance and self-correction capabilities. It features a native multimodal architecture that supports text, image, and video input, thinking and non-thinking modes, and dialogue and agent tasks.

Gemini 3.7 Flash delivers advanced intelligence at the speed and efficiency expected from the Flash series. It is designed for demanding agentic and coding workloads, combining strong reasoning, coding, and multimodal understanding with fast, responsive inference. The model is well suited for applications such as autonomous agents, software engineering, complex problem solving, multimodal analysis, and real-time AI assistants. With its balance of capability, latency, and efficiency, Gemini 3.7 Flash is optimized for high-throughput workloads that require frontier-level performance without sacrificing responsiveness.

Gemini 3.5 Flash delivers intelligence that rivals large flagship models on multiple dimensions, at the speeds you have come to expect from the Flash series. It's Google's strongest agentic and coding Flash model yet, leading in multimodal understanding and challenging coding and agentic benchmarks.

Gemini is a generative artificial intelligence chatbot and virtual assistant developed by Google, powered by the large language model of the same name.

MiniMax-M2.1 is a lightweight, state-of-the-art large language model (LLM) with only 10 billion activated parameters. It is optimized for coding, agentic workflows, and modern application development, delivering a major jump in real-world capability while maintaining exceptional latency, scalability, and cost efficiency.

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned Mixture-of-Experts language model based on the Qwen3-235B architecture.

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight MoE model optimized for complex reasoning tasks. Activating 22B of its 235B parameters, it supports up to 262,144 tokens of context and enhances structured logical reasoning, mathematics, science, and long-form generation.

Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter MoE model from Qwen, utilizing 3.3B active parameters per inference. Operating in non-thinking mode, it is designed for high-quality instruction following, multilingual understanding, and agentic tool use.