Inference and training platform for open-source AI models, frequently used for fast and cost-efficient hosted endpoints.
19 text
Z.ai's frontier reasoning model for long-context agents and software engineering.
MoonshotAI's coding-focused Kimi model for end-to-end software engineering.
NVIDIA's open frontier reasoning model for orchestration, coding, and deep research.
MiniMax's multimodal foundation model for long-horizon agentic work.
Open-source 1.6T-parameter MoE with 49B active, built for advanced reasoning and long-horizon agents.
MoonshotAI's next-generation multimodal model built for long-horizon coding and multi-agent orchestration.
Zhipu AI's most capable model with a major leap in coding and long-horizon task performance.
Google's fourth-generation open dense model with native multimodal understanding.
MiniMax's most capable model, built for autonomous real-world productivity with subagent collaboration.
Compact 9B vision-language model from the Qwen3.5 family.
Qwen's largest MoE model with 397B total parameters, 17B active.
OpenAI's budget-friendly reasoning model — fast and surprisingly capable.
OpenAI's compact open-weights model for efficient inference.
July 2025 update to Qwen3 235B A22B with improved capabilities.
Nano-efficient Gemma 3 variant optimized for mobile and edge devices.
Arcee AI's flagship model for complex enterprise tasks.
Meta's efficient 70B model matching Llama 3.1 405B on key benchmarks.
Compact 7B model from Qwen 2.5 for efficient deployment.
Meta's original Llama 3 compact model.