HAIL.SO / DISPATCH · 2026-07-24 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

3 models
Mistral
Ministral 3 3B
×
OpenAI
OpenAI o3
×
Perplexity
Sonar
×
Output $/MTok$0.10$8.00$1.00
Input $/MTok$0.10$2.00$1.00
Cached input $/MTok$0.5000
Context window262,144200,000128,000
Output cap8,192100,0008,000
Modalitiesin: text, image / out: textin: text, image / out: textin: text / out: text
Tool use
Structured output
FamilyMinistralo-seriesSonar
Knowledge cutoff2024-06-01
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

2 models
Rev.ai
Rev.ai Reverb
×
AssemblyAI
Whisper-Streaming
×
$/min$0.003300$0.005000
$/min batch
Streaming
Realtime
Languagesen99+
Diarizationincludedextra-cost
TTFW
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗
03

Text to speech

1 model
Smallest.ai
Lightning v3.1 Pro
×
$/1M chars$19.50
Voice qualityneural
Voice cloning
Voice count
Languagesen, hi, mr, ta, ml, te, kn, pa, bn, or, gu, ar, zh, id, ja, ko, ms, tr, vi, de, es, fr, it, pt, ru, el, fi, no, pl
SSML support
TTFB200ms
Output formatspcm, mp3, wav, ulaw, alaw
Verified2026-07-19
Sourceprovider page ↗