HAIL.SO / DISPATCH · 2026-07-25 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

1 model
Mistral
Ministral 3 8B
×
Output $/MTok$0.15
Input $/MTok$0.15
Cached input $/MTok
Context window262,144
Output cap8,192
Modalitiesin: text, image / out: text
Tool use
Structured output
FamilyMinistral
Knowledge cutoff
Verified2026-07-19
Sourceprovider page ↗
02

Speech to text

2 models
Speechmatics
Speechmatics Enhanced
×
Rev.ai
Rev.ai Whisper Fusion
×
$/min$0.002150$0.005000
$/min batch
Streaming
Realtime
Languages56+en
Diarizationincludedincluded
TTFW
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗
03

Text to speech

3 models
Smallest.ai
Lightning v3.1
×
Rime
Rime Mist v3
×
Cartesia
Sonic 2
×
$/1M chars$17.50$30.00$50.00
Voice qualityneuralneuralneural
Voice cloning✓ included✓ included
Voice count21794
Languagesen, hi, es, mr, kn, ta, bn, gu, te, ml, pa, orenen, fr, de, es, pt, zh, ja, ko
SSML support
TTFB200ms37ms90ms
Output formatspcm, mp3, wav, ulaw, alaw
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗