theserverless.dev InferenceList

Models

Showing 1–20 of 20 · Sorted by input price, low to high.

Cheaper elsewhere
More filters
DeepInfra × Clear
Model Provider Modality Input ↑ Output Context
nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b DeepInfra audio $0.000003/second audio Not published— —
openai/whisper-large-v3-turbo DeepInfra audio $0.000003/second audio Not published— —
Qwen/Qwen3-ASR-0.6B DeepInfra audio $0.000003/second audio Not published— —
openai/whisper-large-v3 DeepInfra audio $0.000008/second audio Not published— —
Qwen/Qwen3-ASR-1.7B DeepInfra audio $0.000008/second audio Not published— —
mistralai/Voxtral-Mini-3B-2507 DeepInfra audio $0.000017/second audio Not published— —
mistralai/Voxtral-Small-24B-2507 DeepInfra audio $0.00005/second audio Not published— —
hexgrad/Kokoro-82M DeepInfra audio $0.99/character Not published— —
ResembleAI/chatterbox-multilingual DeepInfra audio $1/character Not published— —
ResembleAI/chatterbox-turbo DeepInfra audio $1/character Not published— —
Audio8/Audio8-TTS-Preview-0.6b DeepInfra audio $5/character Not published— —
sesame/csm-1b DeepInfra audio $7/character Not published— —
bosonai/HiggsAudioV2.5 DeepInfra audio $20/character Not published— —
Qwen/Qwen3-TTS DeepInfra audio $20/character Not published— —
Qwen/Qwen3-TTS-VoiceDesign DeepInfra audio $20/character Not published— —
inworld-ai/realtime-tts-1.5-mini DeepInfra audio $25/character Not published— —
inworld-ai/realtime-tts-2 DeepInfra audio $35/character Not published— —
inworld-ai/realtime-tts-1.5-max DeepInfra audio $50/character Not published— —
XiaomiMiMo/MiMo-V2.5-tts DeepInfra audio Not published— Not published— —
XiaomiMiMo/MiMo-V2.5-tts-voicedesign DeepInfra audio Not published— Not published— —

Token rates are USD per 1M tokens. A dash means the source did not publish that amount. A zero is a real zero.