rate card
Models & pricing
The specialist models we've benchmarked, hosted and priced — with the long tail we're onboarding next below. Prices are in each model's native unit; realtime is the on-demand rate, batch is a discounted flexible tier (send X-Tier: batch).
allembeddingsspeech-to-textvision-languagezero-shot imagererankerimage-to-texttext-to-speechobject detectiondepth estimationtext generation
49 matches in zero-shot image · clear
no live models match — see the roadmap below or clear the filter.
| model | task | tier | realtime | batch |
|---|
On the roadmap
49 modelsHigh-demand specialist models with no hosted API. We benchmark and onboard them by task - each has a page; sign in and tell us which you need to jump the queue.
zero-shot image · 49
clip-vit-base-patch32clip-vit-large-patch14CLIP-ViT-B-32-laion2B-s34B-b79Kclip-vit-large-patch14-336PickScore_v1fashion-clipsiglip-so400m-patch14-384clip-vit-base-patch16siglip2-giant-opt-patch16-384siglip-base-patch16-224siglip2-base-patch16-naflexsiglip2-so400m-patch16-naflexsiglip2-so400m-patch14-384marqo-fashionSigLIPCLIP-convnext_base_w-laion2B-s13B-b82K-augregBiomedCLIP-PubMedBERT_256-vit_base_patch16_224siglip2-so400m-patch16-256CLIP-ViT-H-14-laion2B-s32B-b79Ksiglip2-base-patch16-224CLIP-ViT-B-16-laion2B-s34B-b88KCLIP-ViT-L-14-laion2B-s32B-b82Ksiglip2-so400m-patch16-512TinyCLIP-ViT-8M-16-Text-3M-YFCC15MPE-Core-L14-336ViT-SO400M-14-SigLIP-384siglip2-base-patch16-256chinese-clip-vit-base-patch16one-alignMobileCLIP-S2-OpenCLIPViT-B-16-SigLIP2-256clip-vit-base-patch32siglip2-base-patch16-512CLIP-convnext_large_d_320.laion2B-s29B-b131K-ft-soupViT-SO400M-14-SigLIPAltCLIPViT-B-16-SigLIPsiglip2-large-patch16-256CLIP-ViT-bigG-14-laion2B-39B-b160kCLIP-ViT-L-14-DataComp.XL-s13B-b90KCLIP-ViT-B-32-DataComp.XL-s13B-b90Ksiglip-large-patch16-384CLIP-ViT-B-16-DataComp.XL-s13B-b90Ksiglip-large-patch16-256CLIP-ViT-g-14-laion2B-s34B-b88Ksiglip-base-patch16-256siglip-base-patch16-256-multilingualsiglip-base-patch16-384align-basesiglip-base-patch16-512