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).

all embeddings speech-to-text vision-language zero-shot image reranker image-to-text text-to-speech object detection depth estimation text generation

model	task	tier	realtime	batch
cross-encoder/ms-marco-MiniLM-L6-v2	reranker	A	$0.008/1k docs	$0.0025/1k docs
jinaai/jina-reranker-v2-base-multilingual	reranker	A	$0.008/1k docs	$0.0025/1k docs
Qwen/Qwen3-Reranker-0.6B	reranker	A	$0.008/1k docs	$0.0025/1k docs
Qwen/Qwen3-Embedding-0.6B	embeddings	A	$0.008/1M tok	$0.0025/1M tok
BAAI/bge-small-en-v1.5	embeddings	A	$0.008/1M tok	$0.0025/1M tok
BAAI/bge-reranker-base	reranker	A	$0.008/1k docs	$0.0025/1k docs
Qwen/Qwen3-Embedding-4B	embeddings	A	$0.008/1M tok	$0.0025/1M tok

On the roadmap

509 models

High-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.

embeddings · 88

nomic-embed-text-v1.5 nomic-embed-text-v1 w2v-bert-2.0 all-MiniLM-L6-v2 jina-embeddings-v3 granite-embedding-small-english-r2 bge-base-en-v1.5 wavlm-large all-MiniLM-L6-v2-onnx jina-embeddings-v2-small-en gte-multilingual-base gte-large-en-v1.5 Qwen3-VL-Embedding-8B jina-embeddings-v5-text-nano SFR-Embedding-2_R nomic-embed-text-v2-moe indobert-base-p1 gte-Qwen2-1.5B-instruct wavlm-base-plus bm25 llama-nemotron-embed-1b-v2 Qwen3-Embedding-4B-W4A16-G128 gte-base-en-v1.5 e5-mistral-7b-instruct jina-embeddings-v2-base-en snowflake-arctic-embed-m-v2.0 LLM2Vec-Meta-Llama-3-8B-Instruct-mntp-supervised gte-Qwen2-7B-instruct jina-embeddings-v5-omni-small stella_en_400M_v5 jina-clip-v1 e5-v snowflake-arctic-embed-m-long granite-embedding-english-r2 F2LLM-v2-4B stella_en_1.5B_v5 cde-small-v2 jina-embeddings-v5-omni-nano LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcse NV-Embed-v2 SFR-Embedding-Mistral Linq-Embed-Mistral gme-Qwen2-VL-2B-Instruct mmlw-e5-large inf-retriever-v1-1.5b F2LLM-v2-1.7B jina-embedding-b-en-v1 MiniCPM-Embedding opensearch-neural-sparse-encoding-doc-v3-gte LCO-Embedding-Omni-3B LCO-Embedding-Omni-7B bilingual-embedding-base gme-Qwen2-VL-7B-Instruct bge-en-icl F2LLM-v2-8B KaLM-embedding-multilingual-mini-instruct-v2 KaLM-embedding-multilingual-mini-instruct-v1 jina-embedding-s-en-v1 BidirLM-Omni-2.5B-Embedding nomic-embed-text-v1-unsupervised LLM2Vec-Meta-Llama-3-8B-Instruct-mntp-unsup-simcse LLM2Vec-Sheared-LLaMA-mntp-supervised mmlw-e5-base inf-retriever-v1 udever-bloom-560m udever-bloom-1b1 LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised nomic-embed-text-v1-ablated lodestone-base-4096-v1 Ivysaur embedder-100p slx-v0.1 b1ade-embed udever-bloom-3b Bulbasaur cde-small-v1 gte-micro-v4 Zeta-Alpha-E5-Mistral DenseOn-unsupervised LENS-d8000 LENS-d4000 ColBERT-Zero-supervised ColBERT-Zero-unsupervised gte-Qwen1.5-7B-instruct cadet-embed-base-v1 LLM2Vec-Llama-2-7b-chat-hf-mntp-unsup-simcse LLM2Vec-Llama-2-7b-chat-hf-mntp-supervised static-retrieval-mrl-en-v1

speech-to-text · 53

speaker-diarization-3.1 whisperkit-coreml whisper-base wav2vec2-large-xlsr-53-japanese wav2vec2-large-xlsr-53-polish wav2vec2-large-xlsr-53-dutch wav2vec2-indonesian-javanese-sundanese speaker-diarization-community-1 wav2vec2-large-xlsr-53-arabic wav2vec2-large-xlsr-53-hungarian whisper-small mms-300m-1130-forced-aligner wav2vec2-large-xlsr-53-portuguese wav2vec2-large-xlsr-53-russian romanian-wav2vec2 wav2vec2-large-xlsr-53-telugu wav2vec2-large-xlsr-53-persian wav2vec2-large-voxrex-swedish wav2vec2-large-xls-r-300m-Urdu Wav2Vec2-large-xlsr-hindi voice-activity-detection Voxtral-Mini-4B-Realtime-2602 wav2vec2-xls-r-300m-hebrew wav2vec2-xls-r-300m-mixed wav2vec2-large-xlsr-53-th whisper-tiny wav2vec2-large-xlsr-53-chinese-zh-cn parakeet-tdt-0.6b-v2 wav2vec2-xls-r-300m-bengali faster-whisper-base Qwen3-ASR-1.7B Qwen3-ASR-0.6B parakeet-ctc-1.1b Phi-4-multimodal-instruct GLM-ASR-Nano-2512 whisper-large-v2 whisper-medium.en whisper-small.en moonshine-base parakeet-rnnt-0.6b whisper-large whisper-base.en parakeet-ctc-0.6b moonshine-streaming-medium moonshine-streaming-small canary-1b-flash distil-large-v3.5 parakeet-rnnt-1.1b ARK-ASR-3B ARK-ASR-0.6B MOSS-Transcribe-preview-2B pingala-v1-universal stt-2.6b-en

vision-language · 52

Qwen2.5-VL-7B-Instruct Qwen3.6-35B-A3B-FP8 Qwen2.5-VL-3B-Instruct gemma-4-26B-A4B-it-AWQ-4bit Qwen3.6-27B-FP8 Qwen3-VL-4B-Instruct Qwen2-VL-2B-Instruct DeepSeek-OCR-2 llava-1.5-7b-hf gemma-4-31B-it-FP8-block Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive Florence-2-base Qwen3.5-0.8B Qwen3-VL-2B-Instruct gemma-4-26B-A4B-it-FP8-Dynamic Qwen3.6-35B-A3B-AWQ-4bit Qwen2-VL-7B-Instruct Qwen2-VL-7B-Instruct-AWQ Qwen3.6-27B-MTP-GGUF Qwen2.5-VL-7B-Instruct-AWQ moondream2 gemma-4-26B-A4B-it-GGUF InternVL2-2B Qwythos-9B-Claude-Mythos-5-1M-GGUF chandra-ocr-2 Unlimited-OCR Qwen3.6-35B-A3B-GGUF Qwen3.6-35B-A3B-MTP-GGUF blip2-opt-2.7b Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NEO-CODE-Di-IMatrix-MAX-GGUF dots.mocr surya-ocr-2 dots.ocr Qianfan-OCR LightOnOCR-2-1B chandra granite-vision-4.1-4b Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced MinerU2.5-Pro-2605-1.2B Qwopus3.6-35B-A3B-Coder-MTP-GGUF Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP Unlimited-OCR-GGUF MinerU2.5-2509-1.2B Infinity-Parser2-Flash UI-Venus-1.5-8B UI-TARS-2B-SFT KDL-Frontier-Parser-nano GTA1-7B UI-Venus-1.5-2B UI-TARS-7B-SFT UI-Venus-Ground-7B UI-AGILE-3B

zero-shot image · 49

clip-vit-base-patch32 clip-vit-large-patch14 CLIP-ViT-B-32-laion2B-s34B-b79K clip-vit-large-patch14-336 PickScore_v1 fashion-clip siglip-so400m-patch14-384 clip-vit-base-patch16 siglip2-giant-opt-patch16-384 siglip-base-patch16-224 siglip2-base-patch16-naflex siglip2-so400m-patch16-naflex siglip2-so400m-patch14-384 marqo-fashionSigLIP CLIP-convnext_base_w-laion2B-s13B-b82K-augreg BiomedCLIP-PubMedBERT_256-vit_base_patch16_224 siglip2-so400m-patch16-256 CLIP-ViT-H-14-laion2B-s32B-b79K siglip2-base-patch16-224 CLIP-ViT-B-16-laion2B-s34B-b88K CLIP-ViT-L-14-laion2B-s32B-b82K siglip2-so400m-patch16-512 TinyCLIP-ViT-8M-16-Text-3M-YFCC15M PE-Core-L14-336 ViT-SO400M-14-SigLIP-384 siglip2-base-patch16-256 chinese-clip-vit-base-patch16 one-align MobileCLIP-S2-OpenCLIP ViT-B-16-SigLIP2-256 clip-vit-base-patch32 siglip2-base-patch16-512 CLIP-convnext_large_d_320.laion2B-s29B-b131K-ft-soup ViT-SO400M-14-SigLIP AltCLIP ViT-B-16-SigLIP siglip2-large-patch16-256 CLIP-ViT-bigG-14-laion2B-39B-b160k CLIP-ViT-L-14-DataComp.XL-s13B-b90K CLIP-ViT-B-32-DataComp.XL-s13B-b90K siglip-large-patch16-384 CLIP-ViT-B-16-DataComp.XL-s13B-b90K siglip-large-patch16-256 CLIP-ViT-g-14-laion2B-s34B-b88K siglip-base-patch16-256 siglip-base-patch16-256-multilingual siglip-base-patch16-384 align-base siglip-base-patch16-512

image segmentation · 9

clipseg-rd64-refined BiRefNet RMBG-1.4 modnet PP-DocLayoutV3 BEN2 BiRefNet_lite BiRefNet_HR BiRefNet-portrait

time series forecasting · 3

chronos-2 chronos-bolt-small chronos-2

multimodal · 3

gemma-4-E4B-it gemma-4-12B-it gemma-4-E2B-it-qat-mobile-transformers

visual document retrieval · 3

e5-omni-7B OmniEmbed-v0.1 e5-omni-3B

mask generation · 2

sam3 Falcon-Perception

image generation · 2

Krea-2-Raw Krea-2-Turbo-GGUF

text-gen · 2

Qwen3-0.6B Qwen2.5-0.5B-Instruct

image classification · 1

mobilenetv3_small_100.lamb_in1k

audio classification · 1

clap-htsat-fused

fill mask · 1

ModernBERT-base

voice activity detection · 1

segmentation-3.0

image-to-video · 1

image feature extraction · 1

nomic-embed-vision-v1.5

text-to-video · 1

audio text to text · 1

VibeVoice-ASR-HF

grounding · 1

LocateAnything-3B