Qwen/Qwen3-32B-TEE
Small and fast model with great intelligence per dollar
Discover and compare the model catalog. Enable JavaScript for filters, sorting, and live pagination.
Small and fast model with great intelligence per dollar
No description yet.
No description yet.
Small and fast model with great intelligence per dollar
GLM-5.1 is a large language model optimized for agentic tasks and coding that excels at sustained problem-solving over long horizons through iterative reasoning and tool use.
DeepSeek-V3.2 is an open-source LLM optimized for efficient reasoning and agent tasks through sparse attention and reinforcement learning, useful for complex problem-solving and tool-use applications.
No description yet.
No description yet.
No description yet.
MiniMax-M2.5 is a frontier-class LLM excelling at coding, agentic tool use, and office automation tasks, with state-of-the-art performance on benchmarks like SWE-Bench while being dramatically more cost-effective than competitors.
Structured guard classifier for Halo0.8B-guard-v1
No description yet.
No description yet.
No description yet.
HaloQwen Output Guard
No description yet.
Z-Image Turbo: fast text-to-image generation
Multimodal reasoning: video, audio, image, and text → answers, summaries, and tools
Edit images with prompts
Halo Guard Alpha 4B
Find objects in images
Four classic image models on one chute: FLUX.1-schnell + three SDXL checkpoints
One chute, 12 models, 13 endpoints — covering text-to-speech, voice cloning, voice design, transcription, denoising, source separation, speaker verification, VAD, and language detection. Including Kokoro-82M, Qwen3-TTS 1.7B, Whisper large-v3-turbo, NVIDIA Canary-Qwen 2.5B, and NVIDIA Parakeet TDT.
Lightricks LTX 2.3 distilled-1.1 FP8 on RTX 6000 Pro — cinematic T2V, I2V, and keyframe interpolation with 8-step inference, synchronized audio, and GPU prompt enhancement.
Discover and compare the full model catalog.