HAIL.SO / DISPATCH · 2026-07-22 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

2 models
Mistral
Mistral Small 3
×
DeepSeek
DeepSeek V3
×
Output $/MTok$0.30$0.28
Input $/MTok$0.10$0.14
Cached input $/MTok$0.0028
Context window32,7681,048,576
Output cap8,192384,000
Modalitiesin: text / out: textin: text / out: text
Tool use
Structured output
FamilyMistral SmallDeepSeek V3
Knowledge cutoff
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗
02

Speech to text

2 models
Rev.ai
Rev.ai Whisper Fusion
×
Speechmatics
Speechmatics Enhanced
×
$/min$0.005000$0.002150
$/min batch
Streaming
Realtime
Languagesen56+
Diarizationincludedincluded
TTFW
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗
03

Text to speech

2 models
Deepgram
Deepgram Aura 2
×
LMNT
LMNT Blizzard
×
$/1M chars$30.00$50.00
Voice qualityneuralneural
Voice cloning✓ included
Voice count
Languagesen, es, de, fr, nl, it, ja31+
SSML support
TTFB
Output formatswav, mp3, linear16, mulaw, alaw, opus
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗