gpt-5.1-codex is a specialized member of OpenAI’s GPT-5.1 family, optimized for agentic, long-running software-engineering workflows (code generation, patching, large refactors, structured code review and multi-step agentic tasks).
Model Type: Code
GPT-5.1 API
GPT 5.1 API is what GPT-5.1 Thinking is the advanced reasoning variant of OpenAI’s GPT-5.1 family, it prioritizes adaptive, higher-quality reasoning while giving developers explicit control over the latency / compute trade-off.
Model Type: Chat
GPT-5.1-Chat-latest (GPT-5.1 Instant) API
OpenAI’s GPT-5.1 Instant is the low-latency variant of the newly released GPT-5.1 family (announced November 12, 2025). It’s designed to deliver the “most-used” ChatGPT experience with faster turn-taking, warmer conversational tone defaults, improved instruction following, and a built-in adaptive-reasoning capability that decides when to reply immediately and when to spend extra compute to “think” through harder queries.
Model Type: Chat
Qwen-image-edit API
Qwen-Image-Edit is intended for tasks where editing fidelity matters — e.g., directly changing text on signs, preserving fonts and layout, adding/removing objects while keeping semantic consistency, viewpoint/pose transforms, and fine-grained style transfers.
Model Type: Image
Qwen-image API
Qwen-Image is an image-generation and image-editing foundation model in the Qwen family designed for high-fidelity text rendering, precise editing, and general text-to-image generation.
Model Type: Image Generation
gpt-image-1-mini API
gpt-image-1-mini is a cost-optimized, multimodal image model from OpenAI that accepts text and image inputs and produces image outputs. It is positioned as a smaller, cheaper sibling to OpenAI’s full GPT-Image-1 family — designed for high-throughput production use where cost and latency are important constraints. The model is intended for tasks such as text-to-image generation, image editing / inpainting, and workflows that incorporate reference imagery.
Model Type: Image
Kimi K2 Thinking API
The model “Kimi K2 Thinking” is a new reasoning-agent variant developed by Moonshot AI (Beijing). It belongs to the broader “Kimi K2” family of large-language models but is specifically tuned for thinking—i.e., long-horizon reasoning, tool usage, planning and multi-step inference. Version are kimi-k2-thinking-turbo，kimi-k2-thinking. Basic Features Technical Details Architecture: Training / optimisation: Inference & tool-use: Benchmark […]
Model Type: Chat
Kling 2.5 Turbo API
Kling 2.5 Turbo released late September 2025 — and positioned as a fast, cinematic text-to-video / image-to-video model. The release emphasizes faster generation, improved prompt adherence, and better temporal / camera control, positioning the model as a production-oriented upgrade over earlier Kling 2.x releases.
Model Type: Video
Minimax M2 API
MiniMax M2 is an open-source, agent-native large language model (LLM) released by MiniMax on October 27, 2025. It is explicitly engineered for coding and agentic workflows (tool calling, multi-step automation), prioritizing low latency and cost-effective serving while delivering strong reasoning and tool-use capabilities.
Model Type: Chat
GLM-4.6 API
GLM-4.6 is the latest major release in Z.ai’s (formerly Zhipu AI) GLM family: a 4th-generation, large-language MoE (Mixture-of-Experts) model tuned for agentic workflows, long-context reasoning and real-world coding. The release emphasizes practical agent/tool integration, a very large context window, and open-weight availability for local deployment.
Model Type: Chat