HAIL.SO / DISPATCH · 2026-06-09 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

2 models
Alibaba
Qwen3-Coder-Plus
×
Perplexity
Sonar
×
Output $/MTok$5.00$1.00
Input $/MTok$1.00$1.00
Cached input $/MTok
Context window1,048,576128,000
Output cap65,5368,000
Modalitiesin: text / out: textin: text / out: text
Tool use
Structured output
FamilyQwen 3 CoderSonar
Knowledge cutoff
Verified2026-05-192026-05-19
Sourceprovider page ↗provider page ↗
02

Speech to text

2 models
AssemblyAI
Universal-2
×
Speechmatics
Speechmatics Enhanced
×
$/min$0.002500$0.004000
$/min batch
Streaming
Realtime
Languages99+55+
Diarizationextra-costincluded
TTFW
Verified2026-05-05stale 35d2026-05-19
Sourceprovider 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
Verified2026-05-192026-05-19
Sourceprovider page ↗provider page ↗