HAIL.SO / DISPATCH · 2026-06-27 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

1 model
Alibaba
Qwen3-Coder-Plus
×
Output $/MTok$5.00
Input $/MTok$1.00
Cached input $/MTok
Context window1,048,576
Output cap65,536
Modalitiesin: text / out: text
Tool use
Structured output
FamilyQwen 3 Coder
Knowledge cutoff
Verified2026-05-19stale 39d
Sourceprovider page ↗
02

Speech to text

3 models
Cartesia
Ink
×
Rev.ai
Rev.ai Reverb
×
Speechmatics
Speechmatics Enhanced
×
$/min$0.003000$0.003300$0.004000
$/min batch
Streaming
Realtime
Languages42+en55+
Diarizationunsupportedincludedincluded
TTFW
Verified2026-05-05stale 53d2026-05-19stale 39d2026-05-19stale 39d
Sourceprovider page ↗provider page ↗provider page ↗
03

Text to speech

2 models
Smallest.ai
Lightning v3.1
×
Deepgram
Deepgram Aura 2
×
$/1M chars$25.00$30.00
Voice qualityneuralneural
Voice cloning✓ included
Voice count217
Languagesen, hi, es, mr, kn, ta, bn, gu, te, ml, pa, oren, es, de, fr, nl, it, ja
SSML support
TTFB200ms
Output formatspcm, wav, mp3, mulawwav, mp3, linear16, mulaw, alaw, opus
Verified2026-05-19stale 39d2026-05-19stale 39d
Sourceprovider page ↗provider page ↗