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
38 matches in reranker · clear
| 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 |
| BAAI/bge-reranker-base | reranker | A | $0.008/1k docs | $0.0025/1k docs |
On the roadmap
34 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.
reranker · 34
ms-marco-MiniLM-L4-v2gte-reranker-modernbert-basems-marco-MiniLM-L12-v2Qwen3-Reranker-4Bmmarco-mMiniLMv2-L12-H384-v1ms-marco-MiniLM-L2-v2Qwen3-Reranker-8Bjina-reranker-v3mxbai-rerank-xsmall-v1Qwen3-VL-Reranker-8Bjapanese-reranker-cross-encoder-small-v1Qwen3-VL-Reranker-2Bstsb-roberta-largems-marco-TinyBERT-L2-v2ruri-v3-reranker-310mmxbai-rerank-base-v1Qwen3-Reranker-0.6B-seq-clsllama-nemotron-rerank-1b-v2gte-multilingual-reranker-basecrossencoder-camembert-base-mmarcoFRstsb-roberta-basellama-nemotron-rerank-vl-1b-v2mxbai-rerank-base-v2stsb-distilroberta-basebge-reranker-basemxbai-rerank-large-v1japanese-reranker-cross-encoder-xsmall-v1mxbai-rerank-large-v2ctxl-rerank-v2-instruct-multilingual-1bjapanese-reranker-xsmall-v2jina-reranker-v1-turbo-enzerank-2-rerankerQwen3-Reranker-0.6B-Q8_0-GGUFqnli-electra-base