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

53 matches in speech-to-text · clear

no live models match — see the roadmap below or clear the filter.

model	task	tier	realtime	batch

On the roadmap

53 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.

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