theserverless.dev InferenceList

Models

Showing 1–50 of 202 · Sorted by input price, low to high.

More filters
Model Provider Modality Input ↑ Output Context
Fish Audio: S2.1 Pro Free (free) Fish Audio text audio $0/1M $0/1M —
HeyGen: HeyGen Voice Turbo (free) Heygen text audio $0/1M $0/1M —
NVIDIA: Nemotron 3 Nano Omni (free) NVIDIA text audio image video $0/1M $0/1M 256K
Thinking Machines: Inkling (free) Thinkingmachines text image audio $0/1M $0/1M 1.0M
Thinking Machines: Inkling Small (free) Thinkingmachines text image audio $0/1M $0/1M 1.0M
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— —
Demucs fal audio $0.0007/second Not published— —
Wizper (Whisper v3 -- fal.ai edition) fal audio $0.0011/compute second Not published— —
Elevenlabs Sound Effects V2 fal audio $0.002/second Not published— —
ByteDance Seed: Seed Audio 1.0 ByteDance text audio $0.0025/second Not published— —
ElevenLabs Speech to Text - Scribe V2 fal audio $0.008/minute Not published— —
Whisper Large v3 NEAR AI audio text $0.01/1M $0.01/1M 448
Gemini 3.8 Flash TTS fal audio $0.045/1000 characters Not published— —
Eleven v4 fal audio $0.08/1000 characters Not published— —
Elevenlabs Tts Eleven V3 fal audio $0.1/1000 characters Not published— —
ElevenLabs TTS Multilingual v2 fal audio $0.1/1000 characters Not published— —
Google: Gemini 2.5 Flash Lite Google text image audio video $0.1/1M $0.4/1M 1.0M
Google: Gemini 2.5 Flash Lite Phala text image audio video $0.1/1M $0.4/1M 1.0M
Google: Gemini Embedding 2 (batch) Google text image audio video $0.1/1M $0/1M 8K
MiniMax Speech 2.8 [HD] fal audio $0.1/1000 characters Not published— —
MiniMax Speech-02 HD fal audio $0.1/1000 characters Not published— —
Mistral: Voxtral Small 24B 2507
Cheaper on DeepInfra (−100%)
Mistral AI text audio $0.1/1M $0.3/1M 33K
Google: Gemini 3.1 Flash Lite (batch) Google text image video audio $0.125/1M $0.75/1M 1.0M
MiMo V2.6 Flash Novita text image video audio $0.14/1M $0.28/1M 1.0M
Xiaomi: MiMo-V2.6-Flash
Cheaper on Relace (−36%)
Xiaomi text image video audio $0.14/1M $0.28/1M 1.1M
Cloudflare: Clef Omni Cloudflare text image audio video $0.15/1M $0/1M 66K
Google: Gemini 3.5 Flash Lite (batch) Google text image video audio $0.15/1M $1.25/1M 1.0M
Perceptron: Perceptron Mk1.5 Perceptron text image video audio $0.15/1M $1.5/1M 37K
Qwen: Qwen3.8 Omni Flash Alibaba text image audio video $0.15/1M $0.47/1M 1M
Google: Gemini Embedding 2 Google text image audio video $0.2/1M $0/1M 8K
Google: Gemini Embedding 2 Preview Google text image audio video $0.2/1M $0/1M 8K
Google: Gemini 3 Flash Preview (batch) Google text image audio video $0.25/1M $1.5/1M 1.0M
Google: Gemini 3.1 Flash Lite Google text image video audio $0.25/1M $1.5/1M 1.0M
Google: Gemini 3.1 Flash Lite Preview Google text image video audio $0.25/1M $1.5/1M 1.0M
Qwen3 Omni 30B A3B Thinking Novita text audio video image $0.25/1M $0.97/1M 66K
Rime Labs Arcana v2 Together audio $0.27/1M Not published— —
Whisper large-v3 Together audio $0.27/1M $0.85/1M 1
Google: Gemini 2.5 Flash Google text image audio video $0.3/1M $2.5/1M 1.0M
Google: Gemini 2.5 Flash Phala image text audio video $0.3/1M $2.5/1M 1.0M
Google: Gemini 3.5 Flash Lite Google text image video audio $0.3/1M $2.5/1M 1.0M
Google: Gemini 3.5 Flash Lite Phala text image video audio $0.3/1M $2.5/1M 1.0M
Google: Gemini 3.6 Flash (batch) Google text image video audio $0.375/1M $1.875/1M 1.0M
Google: Gemini 3.7 Flash (batch) Google text image video audio $0.375/1M $1.875/1M 1.0M
Google: Gemini 3.8 Flash (batch) Google text image video audio $0.375/1M $1.875/1M 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.