Approved catalogue_
Choose the model. Keep the contract.
Provider pricing stays visible. Routing and governance stay behind one API.
OpenAI activeGPT-5.6 Sol
gpt-5.6-solGPT-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 and long-horizon problem solving.
OpenAI activeGPT-5.6 Terra
gpt-5.6-terraGPT-5.6 Terra is the 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 tasks where capability and cost need to be balanced.
OpenAI activeGPT-5.6 Luna
gpt-5.6-lunaGPT-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 its price tier.
xAI activeGrok 4.5
grok-4.5Grok 4.5 is xAI's smartest model, with frontier performance across coding, knowledge work, and STEM.
Anthropic activeClaude Sonnet 5
claude-sonnet-5Claude 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, a 1M-token context window, and text, image, and file inputs.
Anthropic activeClaude Fable 5
claude-fable-5Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports reasoning and long-running, complex, asynchronous tasks that previously required frequent human check-ins, with a 1M-token context window and text, image, and file inputs.
Anthropic activeClaude Opus 4.8
claude-opus-4-8Claude Opus 4.8 is Anthropic’s frontier Opus model for complex reasoning, software engineering, multimodal analysis, and long-running agent workflows. It supports extended context, high-output tasks, tool use, and cache-aware workflows, making it suitable for demanding research, coding, and autonomous execution scenarios.
MiniMax M2.7
minimax-m2.7MiniMax M2.7 is an agentic productivity model designed for autonomous task execution, planning, and continuous improvement across complex real-world environments. It focuses on multi-agent collaboration, coding, and business workflows that require sustained reasoning and iteration.
MiniMax M2.5
minimax-m2.5MiniMax M2.5 is a productivity-focused language model for coding, office document work, multi-step planning, and agentic workflows. It extends MiniMax’s coding strengths into broader real-world digital work such as document, spreadsheet, and presentation-oriented tasks.
Kimi K2.6
kimi-k2.6Kimi K2.6 is Moonshot AI’s next-generation multimodal model for long-horizon coding, coding-driven UI and UX generation, and multi-agent orchestration. It targets complex end-to-end tasks across languages such as Python, Rust, and Go, including production-ready interface generation from prompts and visual inputs.
Kimi K2.5
kimi-k2.5Kimi K2.5 is Moonshot AI’s multimodal model for visual coding, general reasoning, and agentic tool-calling. It is built for coding-heavy workflows, UI generation, image-grounded tasks, and self-directed multi-step problem solving.
Z.AI activeGLM 5.1
glm-5.1GLM 5.1 advances Z.AI’s coding and long-horizon task capabilities, with a focus on sustained autonomous work over extended engineering tasks. It is designed for planning, executing, and refining complex projects while maintaining reliable reasoning across long interactions.
Z.AI activeGLM 5
glm-5GLM 5 is Z.AI’s flagship open foundation model for complex system design, backend reasoning, long-horizon agent tasks, and production-grade software workflows. It is built for expert developers who need strong planning, implementation, and iterative problem-solving capability.
DeepSeek activeDeepSeek V4 Pro
deepseek-v4-proDeepSeek V4 Pro is a large-scale Mixture-of-Experts model aimed at advanced reasoning, coding, long-context analysis, and long-horizon agent workflows. It is suited for full-codebase analysis, multi-step automation, and large-scale information synthesis where capability and efficiency both matter.
DeepSeek activeDeepSeek V4 Flash
deepseek-v4-flashDeepSeek V4 Flash is an efficiency-focused Mixture-of-Experts model built for fast inference, high-throughput applications, coding assistants, chat systems, and agent workflows. It keeps strong reasoning and coding performance while prioritizing responsiveness and cost efficiency.
DeepSeek activeDeepSeek V3.2
deepseek-v3.2DeepSeek V3.2 is a reasoning-oriented DeepSeek model designed for efficient long-context processing, coding, and agentic tool-use workloads. It uses sparse-attention style optimizations to improve throughput while preserving strong performance on multi-step reasoning and software tasks.
Anthropic activeClaude Sonnet 4.5
claude-sonnet-4-5-20250929Claude Sonnet 4.5 is an advanced Anthropic Sonnet model tuned for real-world agents, coding workflows, tool use, and multimodal analysis. It balances frontier-level reasoning with practical latency and cost, making it a strong default for software engineering, automation, and complex business workflows.
OpenAI activeGPT-5.5
gpt-5.5GPT-5.5 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks.Built for broad task coverage, GPT-5.5 delivers consistent gains across math, coding, sciende, and tool calling workloads, with more coherent long-form answers and improved tool-use reliability.
Anthropic activeClaude Opus 4.7
claude-opus-4-7Claude Opus 4.6 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection. The model is designed to operate efficiently across varied effort levels, enabling developers to trade off speed, depth, and token usage depending on task requirements. It comes with a new parameter to control token efficiency, which can be accessed using the OpenRouter Verbosity parameter with low, medium, or high. Opus 4.5 supports advanced tool use, extended context management, and coordinated multi-agent setups, making it well-suited for autonomous research, debugging, multi-step planning, and spreadsheet/browser manipulation. It delivers substantial gains in structured reasoning, execution reliability, and alignment compared to prior Opus generations, while reducing token overhead and improving performance on long-running tasks.
Google activeGemini 3.1 Pro Preview
gemini-3.1-pro-previewGemini 3.1 Pro is Google’s flagship frontier model for high-precision multimodal reasoning, combining strong performance across text, image, video, audio, and code with a 1M-token context window. It delivers state-of-the-art benchmark results in general reasoning, STEM problem solving, factual QA, and multimodal understanding, including leading scores on LMArena, GPQA Diamond, MathArena Apex, MMMU-Pro, and Video-MMMU. Interactions emphasize depth and interpretability: the model is designed to infer intent with minimal prompting and produce direct, insight-focused responses.Built for advanced development and agentic workflows, Gemini 3.1 Pro provides robust tool-calling, long-horizon planning stability, and strong zero-shot generation for complex UI, visualization, and coding tasks. It excels at agentic coding (SWE-Bench Verified, Terminal-Bench 2.0), multimodal analysis, and structured long-form tasks such as research synthesis, planning, and interactive learning experiences. Suitable applications include autonomous agents, coding assistants, multimodal analytics, scientific reasoning, and high-context information processing.
Anthropic activeClaude Opus 4.6
claude-opus-4-6Claude Opus 4.6 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection. The model is designed to operate efficiently across varied effort levels, enabling developers to trade off speed, depth, and token usage depending on task requirements. It comes with a new parameter to control token efficiency, which can be accessed using the OpenRouter Verbosity parameter with low, medium, or high. Opus 4.5 supports advanced tool use, extended context management, and coordinated multi-agent setups, making it well-suited for autonomous research, debugging, multi-step planning, and spreadsheet/browser manipulation. It delivers substantial gains in structured reasoning, execution reliability, and alignment compared to prior Opus generations, while reducing token overhead and improving performance on long-running tasks.
OpenAI activeGPT-4o
gpt-4oThe 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded files, providing deeper insights & more thorough responses. GPT-4o (""o"" for ""omni"") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.
Anthropic activeClaude Haiku 4.5
claude-haiku-4-5-20251001Claude 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 across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications. It introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring >73% on SWE-bench Verified, Haiku 4.5 ranks among the world’s best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.
OpenAI activeGPT-5.4
gpt-5.4GPT-5.4 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks.Built for broad task coverage, GPT-5.4 delivers consistent gains across math, coding, sciende, and tool calling workloads, with more coherent long-form answers and improved tool-use reliability.