HAIL.SO / DISPATCH · 2026-07-12 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

2 models
Perplexity
Sonar
×
Mistral
Codestral 25.08
×
Output $/MTok$1.00$0.90
Input $/MTok$1.00$0.30
Cached input $/MTok
Context window128,000131,072
Output cap8,0008,192
Modalitiesin: text / out: textin: text / out: text
Tool use
Structured output
FamilySonarCodestral
Knowledge cutoff
Verified2026-07-022026-07-02
Sourceprovider page ↗provider page ↗
02

Speech to text

1 model
Google
Chirp 2
×
$/min$0.016000
$/min batch
Streaming
Realtime
Languages20+
Diarizationincluded
TTFW
Verified2026-07-02
Sourceprovider page ↗
03

Text to speech

3 models
Deepgram
Deepgram Aura 2
×
Smallest.ai
Lightning v3.1
×
Cartesia
Sonic 2
×
$/1M chars$30.00$17.50$50.00
Voice qualityneuralneuralneural
Voice cloning✓ included✓ included
Voice count217
Languagesen, es, de, fr, nl, it, jaen, hi, es, mr, kn, ta, bn, gu, te, ml, pa, oren, fr, de, es, pt, zh, ja, ko
SSML support
TTFB200ms90ms
Output formatswav, mp3, linear16, mulaw, alaw, opuspcm, mp3, wav, ulaw, alaw
Verified2026-07-022026-07-022026-07-02
Sourceprovider page ↗provider page ↗provider page ↗