HAIL.SO / DISPATCH · 2026-07-23 · 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

3 models
Rev.ai
Rev.ai Reverb
×
Speechmatics
Speechmatics Enhanced
×
Google
Chirp 3
×
$/min$0.003300$0.002150$0.016000
$/min batch
Streaming
Realtime
Languagesen56+98+
Diarizationincludedincludedincluded
TTFW
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗
03

Text to speech

2 models
Deepgram
Deepgram Aura 2
×
Smallest.ai
Lightning v3.1
×
$/1M chars$30.00$17.50
Voice qualityneuralneural
Voice cloning✓ included
Voice count217
Languagesen, es, de, fr, nl, it, jaen, hi, es, mr, kn, ta, bn, gu, te, ml, pa, or
SSML support
TTFB200ms
Output formatswav, mp3, linear16, mulaw, alaw, opuspcm, mp3, wav, ulaw, alaw
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗