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

side by side.

← all costsclear
01

Large language models

2 models
Alibaba
Qwen3.6-Flash
×
DeepSeek
DeepSeek V3
×
Output $/MTok$1.50$0.28
Input $/MTok$0.25$0.14
Cached input $/MTok$0.0028
Context window1,048,5761,048,576
Output cap65,536384,000
Modalitiesin: text, image, video / out: textin: text / out: text
Tool use
Structured output
FamilyQwen 3.6 FlashDeepSeek V3
Knowledge cutoff
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗
02

Speech to text

2 models
Google
Chirp 3
×
Speechmatics
Speechmatics Enhanced
×
$/min$0.016000$0.002150
$/min batch
Streaming
Realtime
Languages98+56+
Diarizationincludedincluded
TTFW
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗
03

Text to speech

2 models
Rime
Rime Mist v3
×
Smallest.ai
Lightning v3.1 Pro
×
$/1M chars$30.00$19.50
Voice qualityneuralneural
Voice cloning
Voice count94
Languagesenen, 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
TTFB37ms200ms
Output formatspcm, mp3, wav, ulaw, alaw
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗