theserverless.dev InferenceList

Models

Showing 101–150 of 202 · Sorted by input price, low to high.

More filters
Model Provider Modality Input ↑ Output Context
sesame/csm-1b DeepInfra audio $7/character Not published— —
Orpheus 3B 0.1 FT Together audio $15/1M 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— —
Cartesia Sonic Together audio $65/1M Not published— —
Cartesia Sonic 2 Together audio $65/1M Not published— 448
Cartesia Sonic 3 Together audio $65/1M Not published— 448
Alibaba: Wan 3.0 Alibaba text image video audio Not published— Not published— —
Alibaba: Wan 3.0 Prime Alibaba text image video audio Not published— Not published— —
AssemblyAI: TTS 1 Assemblyai text audio Not published— Not published— —
AssemblyAI: Universal-3.5 Pro Assemblyai audio Not published— Not published— —
AssemblyAI: Universal-3.6 Pro Assemblyai audio Not published— Not published— —
Auto Router Openrouter text image audio video Not published— Not published— 2M
Auto Router (Beta) Openrouter text image audio video Not published— Not published— 2M
ByteDance: Seedance 2.0 ByteDance text image video audio Not published— Not published— —
ByteDance: Seedance 2.0 Fast ByteDance text image video audio Not published— Not published— —
ByteDance: Seedance 2.0 Mini ByteDance text image video audio Not published— Not published— —
ByteDance: Seedance 2.5 ByteDance text image video audio Not published— Not published— —
Canopy Labs: Orpheus 3B Canopylabs text audio Not published— Not published— 4K
Cartesia Sonic 3.5 Together audio Not published— Not published— 448
Deepgram Aura 2 Together audio Not published— Not published— 448
Deepgram Flux Together audio Not published— Not published— 448
Deepgram Nova 3 Together audio Not published— Not published— 448
Deepgram Nova 3 Multilingual Together audio Not published— Not published— 448
Deepgram: Aura-2 Deepgram text audio Not published— Not published— —
Deepgram: Flux TTS Deepgram text audio Not published— Not published— —
Deepgram: Nova-3 Deepgram audio Not published— Not published— —
ElevenLabs: Eleven Flash v2 Elevenlabs text audio Not published— Not published— —
ElevenLabs: Eleven Flash v2.5 Elevenlabs text audio Not published— Not published— —
ElevenLabs: Eleven Multilingual v2 Elevenlabs text audio Not published— Not published— —
ElevenLabs: Eleven Turbo v2 Elevenlabs text audio Not published— Not published— —
ElevenLabs: Eleven Turbo v2.5 Elevenlabs text audio Not published— Not published— —
ElevenLabs: Eleven v3
Cheaper on fal (−99.8%)
Elevenlabs text audio Not published— Not published— —
ElevenLabs: Eleven v3 Conversational Elevenlabs text audio Not published— Not published— —
ElevenLabs: Eleven v4
Cheaper on fal (−99.9%)
Elevenlabs text audio Not published— Not published— —
ElevenLabs: Eleven v4 Turbo Elevenlabs text audio Not published— Not published— —
ElevenLabs: Scribe v2
Cheaper on fal (−100%)
Elevenlabs audio Not published— Not published— —
ElevenLabs: Scribe v2 Medical Elevenlabs audio Not published— Not published— —
Fish Audio: Drama 3 Fish Audio text audio Not published— Not published— —
Fish Audio: S1 Fish Audio text audio Not published— Not published— —
Fish Audio: S2 Pro Fish Audio text audio Not published— Not published— —
Fish Audio: S2.1 Pro Fish Audio text audio Not published— Not published— —
Fish Audio: Transcribe 1 Fish Audio audio Not published— Not published— —
Fish Audio: Transcribe 1 Pro Fish Audio audio Not published— Not published— —
Google: Chirp 3 Google audio Not published— Not published— —
Google: Lyria 3 Clip Preview Google text image audio Not published— Not published— 1.0M

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