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
×
Perplexity
Sonar
×
Alibaba
Qwen3.7-Plus
×
Output $/MTok$1.50$1.00$1.60
Input $/MTok$0.25$1.00$0.40
Cached input $/MTok
Context window1,048,576128,0001,048,576
Output cap65,5368,00065,536
Modalitiesin: text, image, video / out: textin: text / out: textin: text, image / out: text
Tool use
Structured output
FamilyQwen 3.6 FlashSonarQwen 3.7 Plus
Knowledge cutoff
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

2 models
Cartesia
Ink 2
×
Rev.ai
Rev.ai Reverb
×
$/min$0.009000$0.003300
$/min batch
Streaming
Realtime
Languagesenen
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 ↗