LTX-Video-0.9.8-13B-distilled
Lightricks基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Image→ Output Video
Price not verifiedCheck multimodal and channel pricing separately
View details ↗DISCOVER & COMPARE
Explore AI models 85001
LTX-Video-ICLoRA-canny-13b-0.9.7
Lightricks基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Video
Price not verifiedCheck multimodal and channel pricing separately
View details ↗LTX-Video-ICLoRA-depth-13b-0.9.7
Lightricks基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Video
Price not verifiedCheck multimodal and channel pricing separately
View details ↗LTX-Video-ICLoRA-detailer-13b-0.9.8
LightricksThis is a video detailer model on top of `LTXV_13B_098_DEV` trained on custom data. IC LoRA is a method that enables adding video context into the video generation process. This approach allows for video-to-video control on top of the text-to-video model, providing more precise control over the generated content by conditioning the model on reference video frames during inference. comfy compatible model: ltxv-098-ic-lora-detailer-comfyui.safetensors
Input Text→ Output Video
Price not verifiedCheck multimodal and channel pricing separately
View details ↗LTX-Video-ICLoRA-pose-13b-0.9.7
Lightricks基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Video
Price not verifiedCheck multimodal and channel pricing separately
View details ↗ltxv-spatial-upscaler-0.9.7
Lightricks基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗T5-XXL-8bit
Lightricks基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Inkling-MXFP4
lightseekorg基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗kimi-k2.5-eagle3
lightseekorg基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗kimi-k2.5-eagle3-mla
lightseekorg基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗kimi-k2.6-eagle3
lightseekorg基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗kimi-k2.6-eagle3.1-mla
lightseekorg基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗kimi-k2.6-eagle3-mla
lightseekorgkimi-k2.6-eagle3-mla is an Eagle3 MTP draft model with MLA (Multi-Latent Attention) for accelerating inference of Kimi-K2.6, trained with TorchSpec — an online speculative decoding training framework that runs FSDP training and inference concurrently. If you find this draft model useful, please give our project TorchSpec a star on GitHub. Compared with an MHA draft model, the MLA variant is a better fit for Kimi-K2.6 deployment: - Uses less KV cache, which reduces serving memory pressure. - Matches Kimi-K2.6's MLA architecture, so it fits more naturally into the inference engine's KV-cache handling under different serving scenarios such as PD-Disaggregation.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗kimi-k3-dflash2
lightseekorgDraft model for speculative decoding on `moonshotai/Kimi-K3`, served with TokenSpeed (`--speculative-algorithm DFLASH`). Acceptance length `acc_len = 1 + accepted/steps` at 7 speculative proposals, served with TokenSpeed DFLASH on two GB300 nodes (8 GPUs, TP8), MLA target and drafter. Target is `moonshotai/Kimi-K3` with the serving flags shown at the bottom of this card. Production sampling only: `temperature=1.0`, `top_p=0.95`, reasoning effort `max`, no `top_k`. RULER multi-key needle retrieval over natural-text paragraphs, with only the input length varying. `retrieval` is exact match on the needle value, recorded so that acceptance cannot be credited to a model that has stopped reading its context.
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗kimi-k3-eagle3.1-mla
lightseekorg基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗kimi-k3-eagle3-mla
lightseekorg基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗parakeet-tdt-0.6b-v3
lightware-dev基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Audio→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗XBrush-Pro4
lightweight基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Image
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Autoencoders
lightx2v*From Official Models to Lightx2v Distilled Optimized Versions - Balancing Quality, Speed and Memory* For VAE, the LightX2V team has conducted a series of deep optimizations, deriving two major series: **LightVAE** and **LightTAE**, which significantly reduce memory consumption and improve inference speed while maintaining high quality. ✅ Best reconstruction accuracy ✅ Complete detail preservation ❌ Large memory usage (~8-12 GB) ❌ Slow inference speed
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Encoders
lightx2v基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Hy1.5-Distill-Models
lightx2v基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Video
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Hy1.5-Quantized-Models
lightx2v基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Image→ Output Video
Price not verifiedCheck multimodal and channel pricing separately
View details ↗LightVAE
lightx2v基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗LightWan2.2-A14B
lightx2v> **An extremely efficient Wan 2.2 14B variant: NVFP4 Quantization-Aware Step Distillation with Sparse Attention for Blackwell Architecture** Follow the LightX2V environment setup and NVFP4 kernel installation. Use a Blackwell GPU with the required sparse-attention dependencies. In each launch script, set `lightx2v_path`, `model_path`, `CUDA_VISIBLE_DEVICES`, and the input/output paths. Keep `model_path` pointed at the complete corresponding Wan2.2 base model directory.
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗No matching models
Adjust provider, category or input/output filters. New models are added continuously.
COST EXPLORER
Great models. Clear costs.
Adjust monthly token usage to compare estimated API costs.
1 M = 1 million tokens · USD
Compares base text-token rates within the same channel
Compares base text-token rates within the same channel
Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.
MODEL HANDBOOK
Understand before you choose
How should API prices be compared?+
Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.
Do open weights mean free commercial use?+
Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.
Is the top-ranked model the best for me?+
Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.