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
×
DeepSeek
DeepSeek V3
×
Output $/MTok$1.50$1.00$0.28
Input $/MTok$0.25$1.00$0.14
Cached input $/MTok$0.0028
Context window1,048,576128,0001,048,576
Output cap65,5368,000384,000
Modalitiesin: text, image, video / out: textin: text / out: textin: text / out: text
Tool use
Structured output
FamilyQwen 3.6 FlashSonarDeepSeek V3
Knowledge cutoff
Verified2026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗
02

Speech to text

2 models
Speechmatics
Speechmatics Enhanced
×
Google
Chirp 3
×
$/min$0.002150$0.016000
$/min batch
Streaming
Realtime
Languages56+98+
Diarizationincludedincluded
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 ↗