HAIL.SO / DISPATCH · 2026-07-23 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

3 models
Alibaba
Qwen3.6-Flash
×
Mistral
Codestral 25.08
×
Perplexity
Sonar
×
Output $/MTok$1.50$0.90$1.00
Input $/MTok$0.25$0.30$1.00
Cached input $/MTok
Context window1,048,576131,072128,000
Output cap65,5368,1928,000
Modalitiesin: text, image, video / out: textin: text / out: textin: text / out: text
Tool use
Structured output
FamilyQwen 3.6 FlashCodestralSonar
Knowledge cutoff
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

2 models
Speechmatics
Speechmatics Enhanced
×
Cartesia
Ink 2
×
$/min$0.002150$0.009000
$/min batch
Streaming
Realtime
Languages56+en
Diarizationincluded
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 ↗